JP6374542B2 - Gaming machine and game medium discrimination device - Google Patents

Description

  The present invention relates to a gaming machine and a game medium discrimination device.

  Conventionally, a game called pachislot, comprising a plurality of reels each having a plurality of symbols arranged on each surface, a start switch, a stop switch, a stepping motor provided for each reel, and a control unit. The machine is known. The start switch detects that the start lever has been operated by the player after a game medium such as a medal has been inserted into the gaming machine (hereinafter also referred to as “start operation”), and starts the rotation of all reels. Output the requested signal. The stop switch detects that a stop button provided for each reel has been pressed by the player (hereinafter also referred to as “stop operation”), and outputs a signal requesting the rotation of the corresponding reel to stop. To do. The stepping motor transmits the driving force to the corresponding reel. Further, the control unit controls the operation of the stepping motor based on the signals output from the start switch and the stop switch, and performs the rotation operation and stop operation of each reel.

  In such a gaming machine, when a start operation is detected, lottery processing using random numbers (hereinafter referred to as “internal lottery processing”) is performed on the program, and the result of the lottery (hereinafter referred to as “internal winning combination”). And the rotation of the reel is stopped based on the timing of the stop operation. Then, when the rotation of all the reels is stopped and the symbol combination related to the winning is displayed, a privilege corresponding to the symbol combination is given to the player.

  In addition, such a gaming machine is provided with a medal selector for detecting a medal inserted at the end of the medal slot. In addition, for this medal selector, a medal (illegal medal) that is not a proper medal (regular medal) is inserted into the medal insertion slot, or a device is inserted into the medal insertion slot, so that a regular medal is inserted into the gaming machine. Measures are taken against fraudulent acts in which a game is played by misunderstanding that it has been inserted.

  For example, in Patent Document 1, two medal detection proximity sensors are provided in a medal passage, and it is determined whether a game medal has passed through the medal passage based on the output of each proximity sensor. A slot machine is described that detects fraud using a tool such as a body.

  Patent Document 2 discloses a technique related to an image processing method for performing image processing by dividing an image into a plurality of images, and Patent Document 3 discloses a technique related to an image similarity calculation system using a local region. Has been.

JP 2002-342814 A JP 2001-43371 A Japanese Patent No. 4175413

  However, in the slot machine described in Patent Document 1, medals are inserted by illegally operating the counting function of the medal selector by inserting various shapes of fraudulent instruments other than plates into the medal slot. It is impossible to detect fraudulent acts that seem to be performed and obtain a large number of credits, or fraudulent acts that are performed using illegal medals.

  For example, if the lending unit loaned in the hall where this slot machine is installed is a medals with 20 yen per piece and medals with 5 yen per piece having the same diameter and only different colors and stamps (patterns), Can not be discriminated, and there are those who perform illegal games such as using medals obtained with low betting game machines (so-called 5 slots) with normal gaming machines (so-called 20 slots), Damage has occurred.

  In addition, the slot machine described in Patent Document 1 is attached to a medal lent out in a hall in which a gaming machine is installed, a medal lent out in another hall, or a gaming machine purchased at a used machine dealer. When a medal or a counterfeit medal (including an instrument pretending to be a medal) is the same diameter and only differs in color or stamp (pattern), these cannot be discriminated. For this reason, it has been difficult to detect (detect) an illegal act of playing a game using medals other than regular medals (unauthorized medals).

  Furthermore, the image processing method disclosed in Patent Document 2 and the image similarity calculation system disclosed in Patent Document 3 cannot easily and accurately determine the authenticity of game media inserted into a slot machine or the like.

  Therefore, in the fraud determination in the prior art, such as the slot machine described in Patent Document 1, the image processing method described in Patent Document 2, and the image similarity calculation system of Patent Document 3, Inability to respond to actions, the effect is limited.

  The present invention has been made to solve the above-mentioned problems, and an object of the present invention is to provide a gaming machine and a gaming medium discriminating apparatus capable of detecting an illegal act that misidentifies that a regular gaming medium is used. Is to provide.

The invention according to the first embodiment of the present invention has the following configuration.
An insertion slot (for example, medal insertion slot 21) into which a game medium (for example, medal 510) is inserted;
A gaming machine comprising gaming medium detection means (for example, a medal selector 501 including a camera unit 509) for detecting gaming media inserted from the insertion slot,
The game medium detection means includes
A game medium passage part (for example, medal rail 511) that becomes a passage through which the game medium passes;
An imaging means (for example, means comprising a CMOS image sensor included in the camera unit 509) for imaging a passing object that is an object passing through the passage;
By performing image processing based on image data (for example, captured image 562B) obtained through the imaging unit, a game medium determining unit (for example, determining whether or not the game medium is genuine) A control LSI included in the camera unit 509),
The game medium determining means is
The image data is converted into first color space image data corresponding to a color space (for example, YUV image data converted by the ISP circuit 245), and the game is based on data relating to luminance of the first color space image data. A counting means for counting the medium (for example, medal counting circuit 246);
The image data is converted into second color space image data (for example, HSV image data converted by the ISP circuit 245) corresponding to the color space, and based on data relating to hue and saturation of the second color space image data. Color determination means (for example, a color recognition circuit 247) for determining the color of the game medium;
Extraction means (for example, an extracting unit 564) that converts the image data into grayscale image data and extracts an area (for example, a medal area 573) in which the game medium is reflected from the grayscale image data;
An area dividing means (for example, an area dividing unit 565) that divides an area in which the game medium is displayed into a plurality of divided areas (for example, divided areas 580, 581);
A feature amount acquisition means (for example, a feature amount acquisition unit 566) for acquiring a feature amount indicating a feature of the region in which the game medium is shown based on the plurality of divided regions;
Determination means (for example, a determination unit 567) for determining whether or not the game medium corresponding to the image of the game medium included in the grayscale image data is regular based on the feature amount;
The region dividing means includes
Based on the entropy of the luminance histogram over the entire area in which the game medium is shown, determine a threshold value used to determine whether to perform area division;
Regardless of the threshold value, the initial division is performed on the area where the game medium is shown,
For each of the divided areas where the initial division has been performed, calculate the entropy of the luminance histogram,
After the initial division, the entropy of the luminance histogram is calculated for each of the divided regions, and when the calculated entropy of the luminance histogram is equal to or greater than the threshold, the corresponding divided region is Further, it is divided into a plurality of divided areas,
The feature amount acquisition unit acquires the feature amount based on a two-dimensional histogram related to predetermined information for each of the plurality of divided regions, and the predetermined information includes information (large) indicating a size of the corresponding divided region. Information), and information (distance information) indicating the distance from the center of the area where the game medium is shown to the corresponding divided area,
The determination means compares the feature amount with a standard feature amount indicating a feature of a regular game medium, and based on the comparison result, determines whether or not the game medium according to the image data is a regular one. Configured to determine.

  With such a configuration of the present invention, the region is divided according to the luminance distribution, and the threshold value is determined based on the entropy of the luminance histogram in the entire region where the game medium is shown, and each of the divided regions is determined. When the entropy of the calculated luminance histogram is equal to or greater than the threshold value, the corresponding divided region is further divided. As a result, it is possible to appropriately divide into a plurality of uniformly divided areas according to the imaged game media, and to compare the characteristics of the area in which the game media are shown as compared with the case where the threshold value is determined in advance. Appropriate feature quantities can be acquired, and as a result, the determination accuracy when determining whether or not the game medium is regular is improved. In addition, since the feature amount is acquired based on the size information or the distance information regarding each of the divided areas, even if there is a variation in the rotation posture of the game medium included in the image data, there is little risk of variation with the variation. By using the size information and the distance information, it is possible to acquire a feature amount that is not easily affected by the rotation posture of the game medium, and as a result, determination when determining whether or not the game medium is regular Accuracy is improved.

The invention according to the second embodiment of the present invention has the following configuration.
A game medium passage portion serving as a passage through which the game medium passes;
Imaging means for imaging a passing object that is an object passing through the passage;
A game medium discriminating device (for example, a game medium discriminating unit) that determines whether or not the game medium is legitimate by performing image processing based on the image data obtained through the imaging unit (for example, , Medal selector 501),
The game medium determining means is
Counting means for converting the image data into first color space image data corresponding to a color space and counting the game media based on data relating to luminance of the first color space image data;
Color determination means for converting the image data into second color space image data corresponding to a color space, and determining the color of the game medium based on data relating to hue and saturation of the second color space image data;
Extraction means for converting the image data into grayscale image data and extracting an area in which the game medium is shown from the grayscale image data;
Area dividing means for dividing an area in which the game medium is displayed into a plurality of divided areas;
Feature quantity acquisition means for acquiring a feature quantity indicating a feature of an area in which the game medium is shown based on the plurality of divided areas;
Determination means for determining whether or not a game medium corresponding to an image of a game medium included in the grayscale image data is regular based on the feature amount;
The region dividing means includes
Based on the entropy of the luminance histogram over the entire area in which the game medium is shown, determine a threshold value used to determine whether to perform area division;
Regardless of the threshold value, the initial division is performed on the area where the game medium is shown,
For each of the divided areas where the initial division has been performed, calculate the entropy of the luminance histogram,
After the initial division, the entropy of the luminance histogram is calculated for each of the divided regions, and when the calculated entropy of the luminance histogram is equal to or greater than the threshold, the corresponding divided region is Further, it is divided into a plurality of divided areas,
The feature amount acquisition unit acquires the feature amount based on a two-dimensional histogram related to predetermined information for each of the plurality of divided regions, and the predetermined information includes information indicating a size of the corresponding divided region, and , Information indicating the distance from the center of the area where the game medium is shown to the corresponding divided area,
The determination means compares the feature amount with a standard feature amount indicating a feature of a regular game medium, and based on the comparison result, determines whether or not the game medium according to the image data is a regular one. Configured to determine.

  With such a configuration of the present invention, the region is divided according to the luminance distribution, and the threshold value is determined based on the entropy of the luminance histogram in the entire region where the game medium is shown, and each of the divided regions is determined. When the entropy of the calculated luminance histogram is equal to or greater than the threshold value, the corresponding divided region is further divided. As a result, it is possible to appropriately divide into a plurality of uniformly divided areas according to the imaged game media, and to compare the characteristics of the area in which the game media are shown as compared with the case where the threshold value is determined in advance. Appropriate feature quantities can be acquired, and as a result, the determination accuracy when determining whether or not the game medium is regular is improved. In addition, since the feature amount is acquired based on the size information or the distance information regarding each of the divided areas, even if there is a variation in the rotation posture of the game medium included in the image data, there is little risk of variation with the variation. By using the size information and the distance information, it is possible to acquire a feature amount that is not easily affected by the rotation posture of the game medium, and as a result, determination when determining whether or not the game medium is regular Accuracy is improved.

The invention according to the third embodiment of the present invention has the following configuration.
An insertion slot (for example, medal insertion slot 21) into which a game medium (for example, medal 510) is inserted;
Game medium detection means (for example, a medal selector 501 including a camera unit 509) for detecting a game medium inserted from the insertion slot;
Start operation detecting means for detecting a start operation by the player based on detection of the game medium by the game medium detecting means (for example, a start switch 79 for detecting operation of the start lever 23);
An internal winning combination determining means (for example, a main control circuit 91 for performing an internal lottery process) for determining an internal winning combination with a predetermined probability based on detection of the start operation by the start operation detecting means;
In the display means constituted by a plurality of display rows (for example, reels 3L, 3C, 3R displayed on the reel display window 4) based on the detection of the start operation by the start operation detection means. Fluctuating display control means for controlling fluctuating display (for example, a stepping motor provided corresponding to each reel);
Stop operation detecting means for detecting a stop operation by the player (for example, a stop switch for detecting that each stop button 19L, 19C, 19R is pressed by the player);
Stop control means (for example, a main control circuit 91 that performs reel stop control) for stopping the change display of the symbol based on the determination result of the internal winning combination determining means and detection of the stop operation by the stop operation detecting means; ,
By stopping the variable display in the plurality of display columns, a predetermined privilege (for example, paying out medals) is given based on the symbol combination displayed along the winning determination line extending over the plurality of display columns. A privilege granting means (for example, main control circuit 91),
The game medium detection means includes
A game medium passage part (for example, medal rail 511) that becomes a passage through which the game medium passes;
An imaging means (for example, means comprising a CMOS image sensor included in the camera unit 509) for imaging a passing object that is an object passing through the passage;
By performing image processing based on image data (for example, captured image 562B) obtained through the imaging unit, a game medium determining unit (for example, determining whether or not the game medium is genuine) A control LSI included in the camera unit 509),
The game medium determining means is
It is configured as an LSI dedicated to image processing control,
Extraction means (for example, an extraction unit 564) for extracting an area (for example, the medal area 573) in which the game medium is shown from the image related to the image data;
An area dividing means (for example, an area dividing unit 565) that divides an area in which the game medium is shown into a plurality of divided areas (for example, divided areas 580, 581);
The region dividing means includes
Based on the entropy of the luminance histogram over the entire area in which the game medium is shown, determine a threshold value used to determine whether to perform area division;
Regardless of the threshold value, the initial division is performed on the area where the game medium is shown,
For each of the divided areas where the initial division has been performed, calculate the entropy of the luminance histogram,
After the initial division, the entropy of the luminance histogram is calculated for each of the divided regions, and when the calculated entropy of the luminance histogram is equal to or greater than the threshold, the corresponding divided region is Further, it is configured to be divided into a plurality of divided regions.

  With such a configuration of the present invention, the region is divided according to the luminance distribution, and the threshold value is determined based on the entropy of the luminance histogram in the entire region where the game medium is shown, and each of the divided regions is determined. When the entropy of the calculated luminance histogram is equal to or greater than the threshold value, the corresponding divided region is further divided. As a result, it is possible to appropriately divide into a plurality of uniformly divided areas according to the imaged game media, and to compare the characteristics of the area in which the game media are shown as compared with the case where the threshold value is determined in advance. Appropriate feature quantities can be acquired, and as a result, the determination accuracy when determining whether or not the game medium is regular is improved.

  According to the present invention, it is possible to detect a fraudulent act that misidentifies that a legitimate game medium is used.

It is explanatory drawing explaining the functional flow in the gaming machine of 1st Embodiment of this invention. It is a perspective view which shows the example of an external appearance structure in the gaming machine of 1st Embodiment of this invention. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a perspective view showing an internal structure of a gaming machine according to a first embodiment of the present invention, with a middle door closed. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a perspective view showing an internal structure of a gaming machine according to a first embodiment of the present invention, with a middle door opened. It is explanatory drawing which shows the inside of the cabinet in the gaming machine of 1st Embodiment of this invention. It is explanatory drawing which shows the back surface side of the front door in the gaming machine of 1st Embodiment of this invention. It is the perspective view which looked at the medal selector in the gaming machine of a 1st embodiment of the present invention from the slanting back of the gaming machine. It is an exploded view of the medal selector in the gaming machine of the first embodiment of the present invention. It is the perspective view which looked at the medal selector in the gaming machine of a 1st embodiment of the present invention from the slant front of the gaming machine. It is a perspective view of the select plate of the medal selector in the gaming machine of the first embodiment of the present invention. It is a figure which shows the path | route of a medal when the medal selector in the gaming machine of 1st Embodiment of this invention guides a medal to a hopper apparatus. It is a figure which shows the path | route of a medal when the medal selector in the gaming machine of 1st Embodiment of the invention guides the medal to the medal shoot. It is a block diagram which shows the control system in the game machine of 1st Embodiment of this invention. It is a block diagram which shows the structural example of the main control circuit in the gaming machine of 1st Embodiment of this invention. It is a block diagram which shows the structural example of the sub control circuit in the gaming machine of 1st Embodiment of this invention. It is a block diagram which shows the circuit structural example of the medal selector in the gaming machine of 1st Embodiment of this invention. It is a block diagram which shows the circuit structural example of control LSI in the gaming machine of 1st Embodiment of this invention. It is a functional block diagram of the camera unit in the gaming machine of the first embodiment of the present invention. It is a figure which shows an example of the regular medal used for the game machine of 1st Embodiment of this invention, A shows one side of a regular medal, B is a figure which shows the image data of a regular medal. It is a figure for demonstrating the production | generation (synthesis | combination) of the gradient average image data regarding the regular medal used for the game machine of 1st Embodiment of this invention. It is a figure for demonstrating the regular medal discrimination | determination process of control LSI in the gaming machine of 1st Embodiment of this invention. It is a figure which shows the example of the image data of one side of an unauthorized medal, and an unauthorized medal. It is a figure which shows the example of one side of an unauthorized medal, the image data of an unauthorized medal, and the gradient average image data of an unauthorized medal. It is a functional block diagram of the camera unit in the gaming machine of the second embodiment of the present invention. It is a figure which shows typically an example of the captured image in the game machine of 2nd Embodiment of this invention. It is a functional block diagram which shows the structure of a characteristic image generation part in detail. It is a figure which shows an example of a medal area typically. It is a figure which shows an example of a background image typically. It is a figure which shows an example of a background difference image typically. It is a figure which shows an example of an external shape template typically. It is a figure for demonstrating template matching. It is a figure for demonstrating the extraction process of a medal area. It is a figure which shows an example of an edge image typically. It is a figure for demonstrating the production | generation method of a rotation synthetic | combination image. It is a figure for demonstrating the production | generation method of a template characteristic image. It is a figure for demonstrating the production | generation method of a feature image. It is a figure for demonstrating the production | generation method of a feature image. It is a figure for demonstrating the production | generation method of a feature image. It is a figure for demonstrating the production | generation method of a feature image. It is a functional block diagram of the camera unit in the gaming machine of the third embodiment of the present invention. It is a figure which shows typically an example of the captured image in the game machine of 3rd Embodiment of this invention. It is a figure which shows an example of a medal area typically. It is a figure which shows an example of a background image typically. It is a figure which shows an example of a background difference image typically. It is a figure which shows an example of an external shape template typically. It is a figure for demonstrating template matching. It is a figure for demonstrating the extraction process of a medal area. It is a figure showing typically an example of a local field specified in a medal field. It is a figure which shows an example of the ellipse fitted with respect to a local region. It is a figure which shows an example of a rotation ellipse. It is a flowchart which shows operation | movement of a determination part. It is a figure which shows a mode that a rotation ellipse and a standard ellipse are similar. It is a figure for demonstrating the method to acquire the position of a rotation ellipse. It is a figure which shows an example of the standard ellipse fitted to a local area | region. It is a figure which shows an example of the object ellipse fitted to a local area | region. It is a figure which shows a mode that a medal | token area | region is divided | segmented concentrically. It is a figure which shows a mode that a local area | region is divided | segmented into several division area. It is a figure which shows a mode that a local area | region is divided | segmented into several division area. It is a figure which shows a mode that several ellipses are each fitted with respect to several division area of a local area | region. It is a figure which shows a mode that several ellipses are each fitted with respect to several division area of a local area | region. It is a functional block diagram of the camera unit in the gaming machine of the fourth embodiment of the present invention. It is a figure which shows typically an example of the captured image in the game machine of 4th Embodiment of this invention. It is a figure which shows an example of a medal area typically. It is a figure which shows an example of a background image typically. It is a figure which shows an example of a background difference image typically. It is a figure which shows an example of an external shape template typically. It is a figure for demonstrating template matching. It is a figure for demonstrating the extraction process of a medal area. It is a flowchart which shows operation | movement of an area | region division part. It is a figure which shows an example which calculates | requires an example of the brightness | luminance histogram in a medal area, and the entropy of a brightness | luminance histogram. It is a figure which shows a mode that a medal | token area | region is divided | segmented. It is a figure which shows the mode which further divides | segments a division area, and the formula which calculates | requires the entropy of a brightness | luminance histogram. It is a figure which shows an example of the several uniform division area produced | generated by an area division part. It is a figure which shows an example of the two-dimensional histogram of magnitude | size information and distance information. It is a figure which shows an example of the one-dimensional histogram of magnitude | size information. It is a figure which shows the some medal area from which the rotation angle of a medal differs mutually. It is a figure which shows a mode that the center of a medal area and the center of the medal shown in the said medal area have shifted. It is a figure which shows the medal area from which a standard feature-value is acquired. It is a figure which shows the relationship between a 1st determination evaluation value and a 2nd determination evaluation value.

<< First Embodiment >>
Hereinafter, a pachislot machine that is a gaming machine according to a first embodiment of the present invention will be described with reference to FIGS.

<Function flow>
First, the functional flow of the pachislot will be described with reference to FIG. In the pachislot of this embodiment, medals are used as game media for playing games. Note that all embodiments of the present invention are not limited to pachislot machines, and can be applied to other gaming machines other than pachislot machines (for example, pachinko machines). In addition to medals, the game media can be coins, game balls, game point data, tokens, or the like.

  At the start of the game, when a player inserts a medal and operates the start lever, one value (hereinafter referred to as a random value) is extracted from random numbers in a predetermined numerical range (for example, 0 to 65535). Is done.

  The internal lottery means performs lottery based on the extracted random number value and determines an internal winning combination. This internal lottery means is carried out by a main control circuit described later. By determining the internal winning combination, a combination of symbols that permits display along a winning determination line described later is determined. The types of symbol combinations include those related to “winning” in which benefits such as paying out medals, re-games, bonuses, etc. are given to players, and other so-called “loses”. Is provided.

  Further, when the start lever is operated, a plurality of reels are rotated. Thereafter, when the player presses the stop button corresponding to the predetermined reel, the reel stop control means performs control to stop the rotation of the corresponding reel based on the internal winning combination and the timing when the stop button is pressed. Do. The reel stop control means is responsible for a main control circuit described later.

  In the pachislot, basically, a control for stopping the rotation of the corresponding reel is performed within a specified time (190 msec or 75 msec) from when the stop button is pressed. In the present embodiment, the number of symbols that move with the rotation of the reel within the specified time is referred to as “the number of sliding symbols”. When the specified period is 190 msec, the maximum number of sliding symbols is set to 4 symbols, and when the specified period is 75 msec, the maximum number of sliding symbols is set to 1 symbol.

  When the internal winning combination allowing the symbol combination display related to winning is determined, the reel stop control means usually displays the symbol combination within the specified time of 190 msec (four symbols) for the winning determination line. The rotation of the reel is stopped so as to display as much as possible. In addition, the reel stop control means is defined for one or more reels when, for example, a challenge bonus (CB), which is a second-type special accessory, and a middle bonus (MB) for continuously operating the CB are operated. The reel rotation is stopped so that the combination of symbols is displayed as much as possible along the winning determination line within a time of 75 msec (for one symbol). Furthermore, the reel stop control means uses various specified times corresponding to the gaming state to rotate the reels so that combinations of symbols that are not permitted to be displayed by the internal winning combination are not displayed along the winning determination line. Stop.

  Thus, when the rotation of the plurality of reels is all stopped, the winning determination means determines whether or not the combination of symbols displayed along the winning determination line is related to winning. This winning determination means is carried out by a main control circuit described later. When it is determined by the winning determination means that it is related to winning, a privilege such as paying out medals is given to the player. In the pachislot, a series of flows as described above is performed as one game.

  Further, in the pachislot, in the above-described series of flows, video display performed by a display device such as a liquid crystal display device, light output performed by various lamps, sound output performed by a speaker, or a combination thereof is used. Various productions are performed.

  When the start lever is operated, an effect random number value (hereinafter referred to as effect random number value) is extracted separately from the random number value used for determining the internal winning combination. When the effect random number value is extracted, the effect content determining means determines, by lottery, what is to be executed this time from among a plurality of types of effect contents associated with the internal winning combination. This effect content determination means is carried out by a sub-control circuit described later.

  When the contents of the effect are determined, the effect executing means executes the corresponding effect in conjunction with each opportunity, such as when the rotation of the reels starts, when the rotation of each reel stops, or when determining whether there is a winning. In this way, in the pachislot, the player is given an opportunity to know or predict the determined internal winning combination (in other words, the combination of symbols to be aimed at) by executing the production contents associated with the internal winning combination. It is possible to improve the player's interest.

<Pachislot structure>
Next, the structure of the pachislot machine 1 according to one embodiment will be described with reference to FIGS.

[Appearance structure]
FIG. 2 is a perspective view showing the external structure of the pachi-slot 1.

  As shown in FIG. 2, the pachi-slot 1 includes an exterior body 2. The exterior body 2 includes a cabinet 2a that houses a hopper device 51, a medal auxiliary storage 52, and the like (see FIG. 5), which will be described later, and a front door 2b that is attached to the cabinet 2a so as to be opened and closed. Handles 7 are provided on both side surfaces of the cabinet 2a (only one handle 7 is shown in FIG. 2). The handle 7 is a recess that is put on when carrying the pachi-slot 1.

  Three reels 3L, 3C, and 3R are provided side by side in the exterior body 2. Hereinafter, the reels 3L, 3C, and 3R are referred to as a left reel 3L, a middle reel 3C, and a right reel 3R, respectively. Each reel 3L, 3C, 3R has a reel body formed in a cylindrical shape and a translucent sheet material mounted on the peripheral surface of the reel body. A plurality of (for example, 20) symbols are drawn on the surface of the sheet material at predetermined intervals along the circumferential direction.

  The front door 2b includes a door body 9, a front panel 10, and a liquid crystal display device 11 showing a specific example of the display device.

  The door body 9 is attached to the cabinet 2a using a hinge (not shown), and opens and closes the opening of the cabinet 2a. The hinge is provided at the left end of the door body 9 when the door body 9 is viewed from the front of the pachi-slot 1. The liquid crystal display device 11 is attached to the upper part of the door body 9. The liquid crystal display device 11 includes a display unit (display screen) 11a, and the liquid crystal display device 11 performs an effect by displaying an image.

  The front panel 10 is disposed so as to overlap the display unit 11 a side of the liquid crystal display device 11, and is formed in a frame shape having a panel opening 10 a that exposes the display unit 11 a of the liquid crystal display device 11. A lamp group 18 is provided on the front panel 10. The lamp group 18 is configured by an LED (Light Emitting Diode) or the like, and turns on and off the light in a pattern corresponding to the effect content.

  A pedestal 12 is formed in the center of the front door 2b. The pedestal portion 12 is provided with a symbol display area 4 and various devices to be operated by the player.

  The symbol display area 4 is arranged on the front side superimposed on the three reels 3L, 3C, 3R when viewed from the front, and is provided corresponding to the three reels 3L, 3C, 3R. The symbol display area 4 functions as a display window, and is configured to be able to pass through the reels 3L, 3C, and 3R provided behind it. Hereinafter, the symbol display area 4 is referred to as a reel display window 4.

  When the reels 3L, 3C, and 3R provided behind the reel display window 4 are stopped from rotating, the reel display window 4 has an upper stage, a middle stage, and a lower stage within the frame among the plural types of symbols of the reels 3L, 3C, and 3R. One symbol (three in total) is displayed in each area. In the present embodiment, a target for determining whether or not to win a pseudo line configured by combining any one of the three regions including the upper, middle and lower regions of the reel display window 4 is determined. Is defined as a line (winning determination line).

  The reel display window 4 is formed by a frame member 13 provided on the pedestal portion 12. The frame member 13 has a reel display window 4, an information display window 14, and a stop button attachment portion 15.

  The information display window 14 is provided continuously below the reel display window 4 and opens upward. That is, the reel display window 4 and the information display window 14 are formed as one continuous opening. The information display window 14 and the reel display window 4 are covered with a transparent window cover 16.

  The window cover 16 is disposed on the inner surface side of the frame member 13 and cannot be removed from the front side of the front door 2b. In addition, the frame member 13 includes a sheet placement portion 17 that faces the opening of the information display window 14 with the window cover 16 interposed therebetween. And between the sheet | seat mounting part 17 and the window cover 16, the sheet | seat member (information sheet) in which the information regarding a game was described is arrange | positioned. Therefore, the information sheet is covered with the window cover 16 having a smooth surface without unevenness or gaps.

  The window cover 16 that constitutes the information sheet attachment portion cannot be removed from the front side of the front door 2b, and has a smooth surface with no irregularities or gaps. Can prevent fraudulent access to the inside.

  The stop button mounting portion 15 is provided below the information display window 14 and is formed on a plane facing the front. The stop button mounting portion 15 is provided with a through hole through which the stop buttons 19L, 19C, 19R pass. The stop buttons 19L, 19C, 19R are associated with the three reels 3L, 3C, 3R, respectively, and are provided to stop the rotation of the corresponding reels. Hereinafter, the stop buttons 19L, 19C, and 19R are referred to as a left stop button 19L, a middle stop button 19C, and a right stop button 19R, respectively.

  The stop buttons 19L, 19C, and 19R show examples of various devices that are targets of operations by the player. In addition, the pedestal portion 12 is provided with a medal slot 21, a BET button 22, and a start lever 23 as various devices to be operated by the player.

  The medal slot 21 is provided to accept a medal dropped from the outside by the player. The medals accepted by the medal slot 21 will be inserted into one game with a predetermined number (for example, three) as the upper limit. (So-called credit function).

  The BET button 22 is provided to determine the number of coins to be inserted into one game from medals deposited inside the pachislot 1. The start lever 23 is provided to start the rotation of all the reels (3L, 3C, 3R).

  In addition, a 7-segment display 24 including a 7-segment LED (Light Emitting Diode) is provided on the left side of the reel display window 4 when the front door 2b is viewed from the front. The 7-segment display 24 digitally displays information such as the number of medals to be paid out to the player as a privilege (hereinafter referred to as payout number) and the number of medals deposited in the pachislot (hereinafter referred to as credit number). .

  A settlement button 27 is provided on the left side of the base 12 when the front door 2b is viewed from the front. The checkout button 27 is provided to pull out (discharge) the outside stored in the interior of the pachislot machine 1. A lower panel unit 31 is provided below the pedestal 12. The waist panel unit 31 includes a decorative panel on which an arbitrary image is drawn and a light source that emits light for illuminating the decorative panel from the back side.

  Below the waist panel unit 31, a medal payout port 32, speaker holes 33L and 33R, and a medal tray unit 34 are provided. The medal payout port 32 guides medals discharged from a medal selector 201 described later and medals discharged by driving a hopper device 51 described later to the outside. The medals discharged from the medal payout opening 32 are stored in the medal tray unit 34. The speaker holes 33L and 33R are provided to output sound such as sound effects and music corresponding to the contents of the performance.

[Internal structure]
3 and 4 are perspective views showing the internal structure of the pachi-slot 1. FIG. 3 shows a state in which the front door 2b is opened and the middle door 41 provided on the back side of the front door 2b is closed with respect to the front door 2b. FIG. 4 shows a state where the front door 2b is opened and the middle door 41 is opened with respect to the front door 2b. FIG. 5 is an explanatory diagram showing the inside of the cabinet 2a. FIG. 6 is an explanatory view showing the back side of the front door 2b.

  The cabinet 2a includes a top plate 20a, a bottom plate 20b, left and right side plates 20c and 20d, and a back plate 20e (see FIG. 5). A cabinet-side speaker 42 is disposed on the upper side inside the cabinet 2a. The cabinet-side speaker 42 is attached to the back plate 20e of the cabinet 2a via attachment brackets 43L and 43R. The cabinet side speaker 42 is, for example, a speaker for outputting sound effects.

  A cabinet-side relay board 44 is disposed on the left side of the cabinet-side speaker 42 when the inside of the cabinet 2a is viewed from the front. The cabinet side relay board 44 is attached to the left side plate 20c of the cabinet 2a. The cabinet-side relay board 44 includes a main control board 71 (see FIG. 13), which will be described later, attached to the middle door 41 (see FIGS. 3 and 4), a hopper device 51, a medal auxiliary storage switch (not shown), and a medal payout. The wiring connecting the count switch (not shown) is relayed.

  An amplifier board 45 that controls the output of sound from the cabinet-side speaker 42 is disposed in the center of the cabinet 2a. The amplifier board 45 is attached to an attachment shelf 46 fixed to the left and right side plates 20c and 20d.

  Further, an external concentrated terminal plate 47 is disposed on the right side of the amplifier board 45 when the inside of the cabinet 2a is viewed from the front (see FIG. 5). The external concentrated terminal plate 47 is attached to the right side plate 20d of the cabinet 2a. The external concentration terminal board 47 is provided for outputting signals such as a medal insertion signal, a medal payout signal, and a security signal to the outside of the pachislot machine 1.

  A sub power supply device 48 is disposed on the left side of the amplifier board 45 when the inside of the cabinet 2a is viewed from the front. The sub power supply 48 is attached to the left side plate 20c of the cabinet 2a. The sub power supply device 48 supplies power with an AC voltage of 100 V to the power supply device 53 described later. Further, the power of the AC voltage 100V is converted into the power of the DC voltage and supplied to the amplifier board 45.

  A medal payout device (hereinafter referred to as a hopper device) 51, a medal auxiliary storage 52, and a power supply device 53 are disposed on the lower side of the cabinet 2a.

  The hopper device 51 is attached to the central portion of the bottom plate 20b in the cabinet 2a. This hopper device 51 can accommodate a large amount of medals, and has a structure capable of discharging them one by one. For example, when the settlement button 27 (see FIG. 2) is pressed to settle the medals stored in the pachislot, the hopper device 51 discharges the stored medals by the number of credits. The medals paid out by the hopper device 51 are discharged from the medal payout port 32 (see FIG. 2).

  The medal auxiliary storage 52 stores medals overflowing from the hopper device 51. The medal auxiliary storage 52 is disposed on the right side of the hopper device 51 when the inside of the cabinet 2a is viewed from the front. The medal auxiliary storage 52 is engaged with the bottom plate 20b of the cabinet 2a, and is configured to be detachable from the bottom plate 20b.

  The power supply device 53 is disposed on the left side of the hopper device 51 when the inside of the cabinet 2a is viewed from the front, and is attached to the left side plate 20c. The power supply device 53 includes a power switch 53a and a power supply board 53b (see FIG. 13). The power supply device 53 converts the power of the AC voltage 100V supplied from the sub power supply device 48 into the power of the DC voltage necessary for each part, and supplies the converted power to each part.

  As shown in FIGS. 3, 4 and 6, the middle door 41 is arranged at the center of the back surface of the front door 2b, and is configured to open and close the reel display window 4 (see FIG. 4) from the back side. Door stoppers 41a, 41b, and 41c are provided at the upper and lower portions of the middle door 41. The door stoppers 41a, 41b, 41c fix (prohibit) the opening operation of the middle door 41 in a state where the reel display window 4 is closed from the back side. That is, in order to open the middle door 41, it is necessary to rotate the door stoppers 41a, 41b, 41c to release the middle door 41 from being fixed.

  A main control board case 55 that houses a main control board 71 (see FIG. 13) and three reels 3L, 3C, and 3R are attached to the middle door 41. Stepping motors are connected to the three reels 3L, 3C, and 3R through gears having a predetermined reduction ratio.

  As shown in FIG. 6, the main control board case 55 is provided with a setting key type switch 56. The setting key type switch 56 is used when changing the setting of the pachislot 1 or confirming the setting of the pachislot 1. In the present embodiment, a main control board unit is configured by the main control board case 55 and the main control board 71 accommodated in the main control board case 55.

  The main control board 71 accommodated in the main control board case 55 constitutes a main control circuit 91 (see FIG. 14) described later. The main control circuit 91 is a circuit that controls the main flow of the game in the pachislot 1 such as determination of an internal winning combination, rotation and stop of the reels 3L, 3C, 3R, and determination of the presence or absence of winning. A specific configuration of the main control circuit 91 will be described later.

  A sub control board case 57 that accommodates the sub control board 72 (see FIG. 13) is disposed above the middle door 41, and a center speaker 58 is disposed above the sub control board case 57. The sub control board 72 housed in the sub control board case 57 constitutes the sub control circuit 101 (see FIG. 15). The sub-control circuit 101 is a circuit that controls execution of effects by displaying images. A specific configuration of the sub control circuit 101 will be described later.

  A sub relay board 61 is disposed on the right side of the sub control board case 57 when the front door 2b is viewed from the back side. The sub relay board 61 relays the wiring connecting the sub control board 72 and the main control board 71. Further, it is a board that relays the wiring that connects the sub-control board 72 and the board disposed around the sub-control board 72. In addition, as a board | substrate arrange | positioned around the sub control board 72, LED board 62A, 62B, 62C mentioned later is mentioned.

  The LED boards 62A, 62B, and 62C are disposed on both sides of the sub control board case 57 when viewed from the back side of the front door 2b. These LED boards 62A, 62B, and 62C have a plurality of LEDs (Light Emitting Diodes) 85 (see FIG. 13) showing a specific example of the light source in accordance with the effects executed by the control of the sub-control circuit 101 (see FIG. 15). ) To display a blinking pattern. The pachislot machine 1 of the present embodiment includes a plurality of LED boards in addition to the LED boards 62A, 62B, and 62C.

  Below the sub-relay board 61, a 24h door opening / closing monitoring unit 63 is disposed. The 24h door opening / closing monitoring unit 63 stores the opening / closing history of the middle door 41. When the middle door 41 is opened, a signal for displaying an error on the liquid crystal display device 11 is output to the sub control board 72 (sub control circuit 101).

  Below the middle door 41, a board speaker 64 and lower speakers 65L and 65R are arranged. The board speaker 64 faces the waist panel unit 31 (see FIG. 2), and the lower speakers 65L and 65R face the speaker holes 33L and 33R (see FIG. 2), respectively.

  Above the lower speaker 65L, a medal selector 201, a medal chute 202, and a door open / close monitoring switch 67 are disposed. The medal selector 201 is a device that determines whether or not the material and shape of the medal are appropriate. The medal selector 201 guides the medal inserted into the medal insertion slot 21 to the hopper device 51 via the slope 203 or the medal. Guide to the chute 202. A specific configuration of the medal selector 201 will be described later.

  The medal chute 202 is a substantially Y-shaped cylindrical member, and guides the medal guided by the medal selector 201 and the medal discharged from the hopper device 51 to the medal payout opening 32 (see FIG. 2).

  The door open / close monitoring switch 67 is disposed on the left side of the medal selector 201 when the front door 2b is viewed from the back side. The door open / close monitoring switch 67 outputs a security signal for notifying the opening / closing of the front door 2b to the outside of the pachi-slot 1.

  Further, a door relay terminal plate 68 is disposed in a region below the reel display window 4 and opened and closed by the middle door 41 (see FIG. 4). The door relay terminal board 68 includes a main control board 71 (see FIG. 13) in the main control board case 55, various buttons and switches, a sub-control board 72 (see FIG. 13), a medal selector 201, and a game operation display board. It is a board | substrate which relays wiring with 81 (refer FIG. 13). Examples of the various buttons and switches include a BET button 22, a settlement button 27, a door open / close monitoring switch 67, a BET switch 77, a start switch 79, and the like, which will be described later.

<Composition of medal selector>
Next, a specific configuration of the medal selector 201 will be described with reference to FIGS. FIG. 7 is a perspective view of the medal selector 201 when viewed from an oblique rear side of the pachi-slot 1. FIG. 8 is an exploded view of the medal selector 201. FIG. 9 is a perspective view of the medal selector 201 as viewed obliquely from the front of the pachi-slot 1. FIG. 10 is a perspective view of a select plate 207, which will be described later, of the medal selector 201. FIG. FIG. 11 is a diagram showing a medal path when the medal selector 201 guides the medal to the hopper device 51. FIG. 12 is a diagram showing a medal path when the medal selector 201 guides the medal to the medal chute 202. In addition, the arrow X shown in FIGS. 7-12 shows the left-right direction of the pachislot 1, the arrow Y shows the front-back direction of the pachislot 1, and the arrow Z shows the up-down direction.

  As shown in FIGS. 7 to 9, the medal selector 201 includes a base plate portion 204, a sub plate 205, a cancel shooter 206, a select plate 207, a medal solenoid 208 (see FIG. 9), a camera unit 209, It has.

  The base plate portion 204 is a substantially plate-like member that constitutes the outer frame housing of the medal selector 201, and is molded so that both left and right end portions of the pachi-slot 1 bend to the rear of the pachi-slot 1. The base plate portion 204 has a rear surface 204b that is one plane orthogonal to the front-rear direction of the pachislot 1 and a front surface 204a (see FIG. 9) that is the other plane. A medal rail 210 is formed on the rear surface 204b so as to be recessed forward of the pachi-slot 1 and in a substantially L shape. A plurality of ridges are formed on the surface of the medal rail 210.

  At the upper end portion of the base plate portion 204, a medal entrance portion 211 that receives a medal inserted from the medal insertion port 21 (see FIG. 2) is provided. A medal inserted into the medal selector 201 from the medal entrance 211 moves along the medal rail 210 from above to below. A medal outlet portion 204c (see FIG. 8) is provided at the lower portion of the base plate portion 204. The medals that have moved in the medal selector 201 are discharged from the medal outlet 204c and are accommodated in the hopper device 51 via the slope 203 (see FIG. 4).

  A central hole 212 penetrating in the front-rear direction is formed at a substantially intermediate position of the medal rail 210, and an end of the medal pressure 213 (see FIG. 8) is exposed from the central hole 212. As shown in FIG. 9, the medal pressure 213 is rotatably supported by a shaft portion 214 provided on the front surface 204 a of the base plate portion 204. A coil spring 215 is attached to the shaft portion 214, and the medal pressure 213 is urged by the coil spring 215 so that the medal pressure 213 protrudes from the central hole 212.

  As shown in FIG. 9, a magnet 217 is provided on the front surface 204 a of the base plate portion 204. The magnet 217 attracts (magnetizes) an illegal medal that is not an appropriate material among medals moving on the medal rail 210.

  As shown in FIG. 8, an upper exposure hole 219 that penetrates in the front-rear direction and exposes a rear end portion of an after-medal pressure 218, which will be described later, is formed in a substantially central portion of the downstream region of the medal rail 210. . Further, a lower exposure hole 220 that penetrates in the front-rear direction and exposes a later-described medal stopper portion 227 of the select plate 207 is formed in the lower portion of the downstream area of the medal rail 210.

  As shown in FIG. 9, the after medal pressure 218 is pivotally supported on the front surface 204 a of the base plate portion 204 so as to be rotatable. When the front end of the after medal pressure 218 is pressed rearward of the pachislot 1 by the medal solenoid 208, the after medal pressure 218 rotates, and the rear end of the after medal pressure 218 passes through the upper exposure hole 219 (see FIG. 8). Exposed.

  As shown in FIGS. 7 and 8, the cancel shooter 206 is a substantially plate-like member, and is molded so that both ends in the left-right direction of the pachislot 1 bend forward of the pachislot 1. The cancel shooter 206 is detachably fixed to the base plate portion 204 and covers the lower portion of the base plate portion 204 from the rear. The cancel shooter 206 guides the medals discharged without going through the medal outlet 204c to the medal chute 202 (see FIG. 4). A cutout portion 206 a that is cut out in a substantially rectangular shape is formed at the upper portion of the substantially central portion in the left-right direction of the cancel shooter 206.

  As shown in FIG. 7, the sub plate 205 is a plate-like member that covers the medal rail 210 from behind. The sub-plate 205 has a flat plate-like main body part 221 and a shaft part 222 provided on the upper part of the main body part 221. A through hole 221a penetrating in the front-rear direction is provided in a substantially central portion of the main body portion 221, and a downstream region is exposed from the substantially central portion of the medal rail 210 from the through hole 221a.

  The shaft portion 222 is supported by the base plate portion 204, and the sub-plate 205 is attached to the base plate portion 204 so as to be rotatable about the shaft portion 222. A coil spring 223 is attached to the shaft portion 222. Under normal conditions, the sub plate 205 is pressed against the base plate portion 204 side by the biasing force of the coil spring 223. At this time, a space through which medals can pass is formed between the sub plate 205 and the upper part of the medal rail 210 covered with the sub plate 205. That is, the sub plate 205 functions as a guide plate that allows the medal to pass therethrough.

  Here, for example, when a medal jam occurs in the medal selector 201, the sub plate 205 can be rotated against the urging force of the coil spring 223 to eliminate the medal jam.

  As shown in FIG. 8, the select plate 207 is a member that guides a medal that moves in a substantially central portion of the medal rail 210 that is not covered by the sub plate 205. As shown in FIG. 10, the select plate 207 includes a substantially trapezoidal plate main body 224 and a pair of bearing portions formed by bending both left and right end portions of the plate main body 224 forward of the pachislot 1. 225. A flange portion 226 is formed on the upper portion of the plate main body 224. The flange portion 226 is formed by bending the pachislot 1 forward and bending the rear end portion upward. One bearing portion 225 is formed with a medal stopper portion 227 extending downward.

  As shown in FIG. 8, the plate main body 224 is opposed to the substantially central portion of the medal rail 210 not covered by the sub-plate 205 in the front-rear direction of the pachislot 1.

  As shown in FIG. 9, the select plate 207 is rotatably supported by a shaft portion 228 provided on the front surface 204 a of the base plate portion 204. The shaft portion 228 is provided with a coil spring 229 and biases the flange portion 226 forward of the pachislot 1. The flange portion 226 is in contact with one end portion of the medal solenoid 208. When the medal solenoid 208 is in the ON state, the flange portion 226 is pressed by one end of the medal solenoid 208 and moves to the rear of the pachislot 1 against the urging force of the coil spring 229. The rotation position of the select plate 207 at this time is referred to as a “guide position”. The distance between the plate body 224 of the select plate 207 at the guide position and the medal rail 210 is set to a predetermined distance that allows the medal to be guided to the hopper device 51 without discharging the medal to the cancel shooter 206 side. At this time, the medal stopper portion 227 does not protrude from the lower exposure hole 220 (see FIG. 8).

  When the medal solenoid 208 is in the OFF state, the flange portion 226 is released from the pressing of the medal solenoid 208 and moves forward of the pachislot 1 by the biasing force of the coil spring 229. The rotation position of the select plate 207 at this time is referred to as a “discharge position”. The distance between the plate body 224 of the select plate 207 at the discharge position and the medal rail 210 is set to be longer than a predetermined distance. At this time, the flange portion 226 that moves forward of the pachislot 1 is pressed, and one end of the medal solenoid 208 moves forward of the pachislot 1. Along with this, the other end of the medal solenoid 208 moves to the rear of the pachislot 1 and presses the front end of the after medal pressure 218. As a result, the after medal pressure 218 rotates and the rear end of the after medal pressure 218 is exposed from the upper exposure hole 219 (see FIG. 8).

  The medal stopper 227 does not protrude from the lower exposure hole 220 (see FIG. 8) when the select plate 207 is at the guide position, and protrudes from the lower exposure hole 220 when at the discharge position.

  As shown in FIG. 11, when the medal moving on the medal rail 210 satisfies the standard dimension, the select plate 207 at the guide position comes into contact with the upper part of the moving medal and the medal outlet 204c (see FIG. 8). ) When the medal is guided by the select plate 207, the medal pressure 213 is pressed forward of the pachislot 1. In FIG. 11, illustration of the sub plate 205 and the cancel shooter 206 of the medal selector 201 is omitted.

  On the other hand, as shown in FIG. 12, the select plate 207 in the discharge position has a distance between the plate body 224 and the medal rail 210 even if the medal moving on the medal rail 210 satisfies the standard dimension. Therefore, the medal cannot be guided to the medal outlet 204c (see FIG. 8). The medal is pushed out by the medal pressure 213, the after medal pressure 218 protruding from the upper exposure hole 219, or the medal stopper portion 227 protruding from the lower exposure hole 220, and is discharged toward the cancel shooter 206. In FIG. 12, as in FIG. 11, the sub-plate 205 and the cancel shooter 206 of the medal selector 201 are not shown.

  In this embodiment, the select plate 207 is normally positioned at the guide position. However, under a predetermined condition (for example, when a predetermined number of medals are inserted, when an error occurs, when a game starts, etc.), the select plate 207 is positioned at the discharge position. It is positioned.

  If the medal moving on the medal rail 210 has a smaller diameter than the standard dimension, even if the select plate 207 is in the guide position, the medal is not guided to the select plate 207 but pushed out to the medal pressure 213 and the cancel shooter 206 It is discharged toward

  As shown in FIGS. 7 and 8, the camera unit 209 includes a first board 230 and a second board 231, and determines whether or not an object moving on the medal rail 210 is a regular medal. It is. The first substrate 230 is provided with a CMOS image sensor 232 (see FIG. 16) and an LED 233 (see FIG. 16). The second substrate 231 is provided with a control LSI 234 (see FIG. 16) connected to the CMOS image sensor 232 and the LED 233 so as to be communicable and controllable. The first substrate 230 and the second substrate 231 are connected by a BtoB (Board-to-Board) type connector (not shown), and by legs 235 provided at the corners of the substrates 230 and 231. It is fixed. The specific configuration of the camera unit 209 circuit will be described later. Further, in the present embodiment, the mode in which the camera unit 209 is configured by the two substrates 230 and 231 has been described, but instead of this, the camera unit 209 is configured by a single substrate provided with the CMOS image sensor 232, the LED 233, and the control LSI 234. May be configured.

  The camera unit 209 is fixed by screwing the first substrate 230 into a screw hole 206b provided around a notch 206a at the top of the cancel shooter 206. The CMOS image sensor 232 (see FIG. 16) is provided at a substantially central portion of the first substrate 230. The CMOS image sensor 232 images a medal that moves on the medal rail 210 and outputs image data of the imaged medal to the control LSI 234 (see FIG. 16). The LED 233 (see FIG. 16) emits light around the CMOS image sensor 232, and irradiates the medal moving on the medal rail 210 with light. The control LSI 234 (see FIG. 16) determines whether the object moving on the medal rail 210 is a regular medal based on the image data output from the CMOS image sensor 232, and outputs the determination result. In this embodiment, the mode in which the camera unit 209 is fixed to the cancel shooter 206 by screwing in the screw hole 206b formed around the notch portion 206a has been described. However, the camera unit fixing mode is limited to this. Not. For example, an attachment rail is provided between the first substrate 230 and the second substrate 231, and a recess is provided in the upper part of the cancel shooter 206. The attachment rail and the cancel shooter 206 are fitted in the recess. May be fixed with screws or an adhesive.

<Pachislot circuit configuration>
Next, a configuration of a circuit included in the pachislo 1 will be described with reference to FIGS. First, the outline of the entire circuit provided in the pachislot machine 1 will be described with reference to FIG. FIG. 13 is a block configuration diagram of the entire circuit provided in the pachi-slot 1.

  The pachi-slot 1 has a main control board 71 disposed on the middle door 41 and a sub-control board 72 disposed on the front door 2b. The main control board 71 includes a reel relay terminal board 74, a setting key switch 56, an external concentration terminal board 47, a hopper device 51, a medal auxiliary storage switch 75, and a power supply board 53b of the power supply 53. It is connected. The setting key switch 56, the external concentration terminal board 47, the hopper device 51, and the medal auxiliary storage switch 75 are connected to the main control board 71 via the cabinet-side relay board 44. Since the external concentration terminal board 47 and the hopper device 51 have been described above, description thereof will be omitted.

  The reel relay terminal board 74 is disposed inside the reel body of each of the reels 3L, 3C, 3R. The reel relay terminal plate 74 is electrically connected to stepping motors (not shown) of the reels 3L, 3C, and 3R, and relays signals output from the main control board 71 to the stepping motors.

  The medal auxiliary storage switch 75 passes through a switch through hole (not shown) of the medal auxiliary storage 52. The medal auxiliary storage switch 75 detects whether or not the medal auxiliary storage 52 is full of medals.

  A power switch 53 a is connected to the power supply board 53 b of the power supply device 53. The power switch 53a is turned on when supplying necessary power to the pachislot machine 1.

  The main control board 71 has a medal selector 201, a door open / close monitoring switch 67, a BET switch 77, a settlement switch 78, a start switch 79, a stop switch board 80, and a game operation display board 81 via a door relay terminal board 68. The sub-relay board 61 is connected. Since the door opening / closing monitoring switch 67 and the sub relay board 61 have been described above, the description thereof will be omitted. The circuit configuration of the medal selector 201 will be described later.

  The BET switch 77 detects that the BET button 22 has been pressed by the player. The settlement switch 78 detects that the settlement button 27 has been pressed by the player. The start switch 79 detects that the start lever 23 has been operated by the player (start operation).

  The stop switch substrate 80 is a substrate constituting a circuit for stopping the rotating reel and a circuit for displaying the stopable reel by an LED or the like. The stop switch substrate 80 is provided with a stop switch. The stop switch detects that each stop button 19L, 19C, 19R has been pressed by the player (stop operation).

  The game operation display board 81 displays the number of inserted medals on the 7-segment display 24 when accepting insertion of medals, when the three reels 3L, 3C, 3R are rotatable and when replaying. It is a substrate for making it. A 7-segment display 24 and an LED 82 are connected to the game operation display board 81. The LED 82 lights, for example, a mark for displaying the start of a game or a mark for performing a re-game.

  The sub control board 72 is connected to the main control board 71 via the door relay terminal board 68 and the sub relay board 61. A sound I / O board 84, LED boards 62A, 62B, 62C, and a 24h door open / close monitoring unit 63 are connected to the sub control board 72 through a sub relay board 61. Since these LED substrates 62A, 62B, 62C and the 24h door opening / closing monitoring unit 63 have been described above, the description thereof will be omitted.

  The sound I / O board 84 outputs sound to a center speaker 58, a board speaker 64, lower speakers 65L and 65R, and a speaker (not shown) provided on the front door 2b.

  The sub-control board 72 is connected to a ROM cartridge board 86 and a liquid crystal relay board 87. The ROM cartridge substrate 86 and the liquid crystal relay substrate 87 are housed in the sub control board case 57 together with the sub control board 72. The ROM cartridge substrate 86 is a substrate for managing production images (video), sound, LED substrates 62A and 62B, other LED substrates (not shown), and communication data. The liquid crystal relay substrate 87 is a substrate that relays wiring that connects the sub-control board 72 and the liquid crystal display device 11.

[Main control circuit]
Next, the main control circuit 91 constituted by the main control board 71 will be described with reference to FIG. FIG. 14 is a block diagram illustrating a configuration example of the main control circuit 91 of the pachi-slot 1.

  The main control circuit 91 includes a microcomputer 92 installed on the main control board 71 as a main component. The microcomputer 92 includes a main CPU 93, a main ROM 94, and a main RAM 95. The main CPU 93 and the hopper device 51 described above constitute a game medium payout device of the present invention.

  The main ROM 94 is used to transmit various control commands (commands) to the control program executed by the main CPU 93 (for example, the program for executing the internal lottery process described above), the data table, and the sub-control circuit 101. Data etc. are stored. The main RAM 95 is provided with a storage area for storing various data such as an internal winning combination determined by execution of the control program.

  The main CPU 93 is connected to a clock pulse generation circuit 96, a frequency divider 97, a random number generator 98, and a sampling circuit 99. The clock pulse generation circuit 96 and the frequency divider 97 generate clock pulses. The main CPU 93 executes a control program based on the generated clock pulse. The random number generator 98 generates a random number in a predetermined range (for example, 0 to 65535). The sampling circuit 99 extracts one value from the generated random numbers.

  The main CPU 93 counts the number of times pulses are output to the stepping motors of the reels 3L, 3C, and 3R after detecting the reel index. Thereby, the main CPU 93 manages the rotation angle of each reel 3L, 3C, 3R (mainly, how many symbols the reel has rotated). The reel index is information indicating that the reel has made one revolution. For example, the reel index is provided at a predetermined position of each of the reels 3L, 3C, and 3R, and the light sensor and the light receiving unit are rotated by rotation of the reels 3L, 3C, and 3R. Detection is performed by a reel position detection unit (not shown) including a detection piece interposed therebetween.

  Here, management of the rotation angles of the reels 3L, 3C, and 3R will be specifically described. The number of pulses output to the stepping motor is counted by a pulse counter provided in the main RAM 95. Each time the output of a predetermined number of pulses (for example, 16 times) necessary for the rotation of one symbol is counted by the pulse counter, the symbol counter provided in the main RAM 95 is incremented by one. The symbol counter is provided for each reel 3L, 3C, 3R. The value of the symbol counter is cleared when a reel index is detected by a reel position detector (not shown).

  In other words, in the present embodiment, by managing the symbol counter, it is possible to manage how many symbols have been rotated since the reel index was detected. Therefore, the position of each symbol on each reel 3L, 3C, 3R is detected with reference to the position where the reel index is detected.

  As described above, when the maximum number of sliding symbols is set to four symbols, the symbol of the left reel 3L in the middle of the reel display window 4 when the left stop button 19L is pressed, and the four symbols. Each symbol within the range up to the previous symbol becomes a symbol that can be stopped at the middle stage of the reel display window 4.

[Sub control circuit]
Next, the sub control circuit 101 constituted by the sub control board 72 will be described with reference to FIG. FIG. 15 is a block diagram illustrating a configuration example of the sub control circuit 101 of the pachi-slot 1.

  The sub control circuit 101 is electrically connected to the main control circuit 91 and performs processing such as determination and execution of effect contents based on a command transmitted from the main control circuit 91. The sub control circuit 101 basically includes a sub CPU 102, a sub RAM 103, a rendering processor 104, a drawing RAM 105, and a driver 106.

  The sub CPU 102 controls the output of video, sound, and light according to the control program stored in the ROM cartridge substrate 86 in accordance with the command transmitted from the main control circuit 91. The ROM cartridge substrate 86 basically includes a program storage area and a data storage area.

  A control program executed by the sub CPU 102 is stored in the program storage area. For example, the control program includes a main board communication task for controlling communication with the main control circuit 91 and an effect registration task for extracting and registering effect contents (effect data) by extracting effect random numbers. Is included. Further, a drawing control task for controlling display of an image by the liquid crystal display device 11 (see FIG. 2) based on the determined contents of the effect, a lamp control task for controlling light output by a light source such as the LED 85, and the speakers 58, 64, and 65L. , 65R, etc., a voice control task for controlling the output of sound by a speaker.

  The data storage area includes a storage area for storing various data tables, a storage area for storing effect data constituting each effect content, and a storage area for storing animation data related to creation of video. Also included are a storage area for storing sound data related to BGM and sound effects, a storage area for storing lamp data related to the light on / off pattern, and the like.

  The sub-RAM 103 is provided with a storage area for registering the determined contents and effects data, and a storage area for storing various data such as an internal winning combination transmitted from the main control circuit 91.

  The sub CPU 102, the rendering processor 104, the drawing RAM (including the frame buffer) 105, and the driver 106 create a video according to the animation data designated by the content of the presentation, and display the created video on the liquid crystal display device 11.

  Further, the sub CPU 102 causes a speaker such as speakers 58, 64, 65L, and 65R to output a sound such as BGM according to the sound data specified by the production contents. Further, the sub CPU 102 controls the turning on and off of the light source such as the LED 85 according to the lamp data designated by the contents of the effect.

<Circuit configuration of medal selector>
Next, the circuit configuration of the medal selector 201 will be described with reference to FIG. FIG. 16 is a block diagram illustrating a circuit configuration example of the medal selector 201.

  As shown in FIG. 16, the medal selector 201 includes a camera unit 209 and a medal solenoid 208. The medal selector 201 is connected to the main control board 71 via the door relay terminal board 68. That is, the medal selector 201 is electrically connected to the main control circuit 91. Therefore, the main control circuit 91 can set the medal solenoid 208 of the medal selector 201 to the ON state or the OFF state.

  The camera unit 209 includes a control LSI 234, a CMOS image sensor 232, and an LED 233. The control LSI 234 of the camera unit 209 is configured as an LSI dedicated to image processing control such as an application specific integrated circuit (ASIC) or a field-programmable gate array (FPGA), and is electrically connected to the CMOS image sensor 232 and the LED 233, for example. Has been. The control LSI 234 controls the light emission of the LED 233. Further, the control LSI 234 determines whether the insertion is a regular medal based on the image data output from the CMOS image sensor 232, and outputs the determination result to the main control board 71 via the door relay terminal board 68. . In the present embodiment, the adopted CMOS image sensor 232 is a CMOS image sensor having a resolution of 648 × 488 pixels and a frame rate of 240 fps (Frames Per Second), but is limited to such an image sensor. Need not be done (an imaging device other than CMOS may also be used). Moreover, light-emitting devices other than LED can also be used.

[Control LSI circuit configuration]
Next, the circuit configuration of the control LSI 234 will be described with reference to FIGS. FIG. 17 is a block diagram illustrating a circuit configuration example of the control LSI 234. 18 is a functional block diagram of the camera unit 209 including the control LSI 234, FIG. 19 is a diagram for explaining a regular medal, FIG. 19A shows one side of the regular medal, and FIG. 19B is an image of the regular medal. Data are shown. FIG. 20 is a diagram for explaining generation (combination) of gradient average image data related to a regular medal. The camera unit 209 includes a light emitting unit made of an LED or the like, but is not shown in FIG.

  The control LSI 234 includes a host controller 241, an image recognition DSP (digital signal processor) circuit 242, an SRAM (Static Random Access Memory) 243, a flash memory 244, an ISP (Image Signal Processing) circuit 245, and a medal count circuit 246. The control LSI 234 includes a color recognition circuit 247, a fisheye correction scaler circuit 248, an image recognition accelerator circuit 249, and a GPIO (General Purpose Input / Output) 250. These devices constituting the control LSI 234 are connected to each other via a bus, and the control LSI 234 of this embodiment employs AXI (Advanced eXtensible Interface) as a bus protocol.

  The control LSI 234 includes an ISI (Image Sensor Interface) circuit 251. The ISI circuit 251 is electrically connected to the CMOS image sensor 232 and the ISP circuit. The ISI circuit 251 converts the image data output from the CMOS image sensor 232 by the LVDS (Low voltage differential signaling) method into an RGB Bayer image and outputs the RGB data to the ISP circuit 245.

  Here, the CMOS image sensor 232 and the ISI circuit 251 (and the host controller 241 that controls the ISI circuit 251) correspond to the imaging unit 261 shown in FIG. The captured image 262 is sent from the imaging unit 261 to the conversion unit 263 described later (the captured image 262 is an RGB Bayer image output from the ISI circuit 251 in this example).

  When receiving the RGB Bayer image from the ISI circuit 251, the ISP circuit 245 outputs a VSYNC (Vertical Synchronization) interrupt signal to the host controller 241. The ISP circuit 245 performs a conversion process for converting the RGB Bayer image output from the ISI circuit 251 into various formats. In the conversion process, the ISP circuit 245 converts the RGB Bayer image into Y (the luminance of each pixel), and stores the converted image data in the SRAM 243. Further, the ISP circuit 245 converts the RGB Bayer image into image data (YUV image data) corresponding to the YUV color space, and outputs data relating to the luminance in the YUV image data to the medal count circuit 246. Further, the ISP circuit 245 converts the RGB Bayer image into image data (HSV image data) corresponding to the HSV color space, and outputs data relating to hue and saturation in the HSV image data to the color recognition circuit 247.

  Here, a part of the ISP circuit 245 (at least a processing function unit that converts an RGB Bayer image into image data (YUV image data) corresponding to a YUV color space) and a host controller 241 that controls the processing unit are shown in FIG. Corresponds to the conversion unit 263.

  The medal count circuit 246 performs count processing based on the data relating to the luminance output from the ISP circuit 245. In the counting process, the medal count circuit 246 compares data relating to the brightness of the count area, which is a predetermined area in the image, with the count threshold value, and determines whether or not a medal has passed by the background difference method. The count threshold value is a threshold value determined in advance based on data relating to the brightness of the count area in the regular medal image. The medal count circuit 246 determines that the medal has passed if the difference is small, and determines that the medal has not passed (other than the medal has passed) if the difference is large. Then, the medal count circuit 246 stores the determination result in the SRAM 243. The count area can be arbitrarily set according to the medal used as a regular medal by the pachislot 1. However, it is preferable to set the count area so that the rotation angle of the medal does not greatly affect the difference in luminance. For example, when a regular medal 280 having the same marking (pattern) on both sides as shown in FIG. 19A is used, the image data 282 (see FIG. 19B) of the regular medal 280 indicates one of the regular medals in the area. The place (area 283 in FIG. 19B) is set as the count area so that the marking (pattern) on the surface of the face does not change with the rotation angle of the medal, that is, the rotation angle of the medal does not greatly affect the luminance difference. Is preferred. Further, the count process can be speeded up as the range of the count area is narrowed.

  The color recognition circuit 247 performs color determination processing based on data relating to hue and saturation output from the ISP circuit 245. In the color determination process, the color recognition circuit 247 first expresses an integrated value of data related to hue and saturation near the center of the image data as a vector (vector conversion), and calculates the angle of the vector in a three-dimensional space. To do. Next, the color recognition circuit 247 compares the calculated vector angle with a predetermined color threshold value, and determines whether or not it matches the color of the regular medal. The predetermined threshold value is a threshold value determined in advance based on the vector angle calculated by the same method as that described above for the image data related to the regular medal (for example, 3 for the regular medal to be compared). (Within ± 10 degrees of the angle on the individual coordinates (XYZ) of the vector in the dimensional space). The color recognition circuit 247 stores the determination result in the SRAM 243.

  The fish-eye correction scaler circuit 248 acquires image data obtained by Y-converting the RGB Bayer image from the SRAM 243 and performs fish-eye correction processing. In the fisheye correction process, the fisheye correction scaler circuit 248 corrects the acquired image data with fisheye to create reduced image data reduced to 1/2, 1/4, and 1/8. Then, the fisheye correction scaler circuit 248 stores the created reduced image data in the SRAM 243.

  The fisheye correction scaler circuit 248 and the host controller 241 that controls the fisheye correction scaler circuit 248 are included in the conversion unit 263 of FIG.

  The image recognition DSP circuit 242 acquires reduced image data (in this embodiment, reduced image data reduced to ¼) from the SRAM 243 and performs preprocessing. In the preprocessing, the image recognition DSP circuit 242 converts the acquired reduced image data into edge image data through a non-linear diffusion filter, and stores the edge image data in the SRAM 243.

  Here, a part of the image recognition DSP circuit 242 (the above-described processing function unit that converts the acquired reduced image data into edge image data through a non-linear diffusion filter) and the host controller 241 that controls this are shown in FIG. It is included in the conversion unit 263.

  The image recognition accelerator circuit 249 performs a rotation integration process for creating gradient average image data. In the rotation integration process, the image recognition accelerator circuit 249 acquires edge image data from the SRAM 243, and generates the acquired edge image data (for example, the image data 282 shown in FIG. 19B) by rotating it by one degree, for example. The image data for 360 degrees is integrated (superposed) to generate gradient average image data. The gradient average image data generated by the image recognition accelerator circuit 249 is stored in the SRAM 243. As an example of generating (combining) the gradient average image data, the gradient average image data 285 of the regular medal 280 shown in FIG. 19A is shown in FIG. The gradient average image data 285 is image data in which edge image data having the shape of “A” is integrated while rotating 360 degrees (that is, integrated 360 times), but here, this is simplified. Shall be shown. Note that a processing function unit that generates gradient average image data and a host controller 241 that controls the processing function unit of the image recognition accelerator circuit 249 correspond to the feature image generation unit 264 of FIG.

  Further, the image recognition DSP circuit 242 performs a stamp determination process for determining whether or not the stamp (pattern) of the medal matches the stamp of the regular medal. In the marking determination process, the image recognition DSP circuit 242 acquires from the SRAM 243 gradient average image data created by the image recognition accelerator circuit 249 through the rotation integration process. Next, the image recognition DSP circuit 242 obtains the acquired gradient average image data, template data for engraving determination processing (for example, the gradient average image data of regular medals stored in the SRAM 243 or the flash memory 244 prepared in advance). The difference is calculated. Then, the image recognition DSP circuit 242 determines whether or not the medal stamp matches the stamp of the regular medal based on the calculated difference value and the threshold value for stamp determination, and stores the determination result in the SRAM 243. . For example, the image recognition DSP circuit 242 compares the luminance of each pixel of the acquired gradient average image data and the template data, and determines whether or not they match (in the case of multi-tone, whether the difference is within a predetermined range). If there are more than a certain number of matching pixels (difference is within a predetermined range), it is determined that the medal stamp (pattern) matches the stamp of the regular medal. If the number of matching pixels is less than the predetermined number, the medal stamp is determined. It is determined that (pattern) does not match the stamp of the regular medal. Note that the processing function unit related to the marking determination process of the image recognition DSP circuit 242 and the host controller 241 that controls the processing function unit correspond to the determination unit 265 shown in FIG. 18, and the template data is the template data 267. Corresponding to

  The image recognition DSP circuit 242 and the host controller 241 that perform the above-described marking determination processing and the like operate according to programs (sequence programs), and these programs are stored in, for example, the SRAM 243 and the flash memory 244. The template data is stored in, for example, the SRAM 243.

  The host controller 241 controls each device, that is, the medal count circuit 246, the color recognition circuit 247, the fisheye correction scaler circuit 248, the image recognition DSP circuit 242, the image recognition accelerator circuit 249, and the GPIO 250. In addition, the host controller 241 outputs a signal relating to a lighting instruction or a lighting instruction to the LED 233 via the GPIO 250. Further, the host controller 241 outputs, via the GPIO 250, the determination result related to the count process, the determination result related to the color determination process, and the determination result related to the marking determination process stored in the SRAM 243. Note that the GPIO 250 that outputs a determination result related to the color determination process or the marking determination process and the host controller 241 that controls the GPIO 250 correspond to the input / output unit 266 shown in FIG. 18, and the determination result is the determination of FIG. Corresponds to result 268.

  The flash memory 244 stores parameters and data (including the template data described above) used by the host controller 241, the image recognition DSP circuit 242, the fisheye correction scaler circuit 248, and the image recognition accelerator circuit 249 for various processes.

  Next, referring to FIG. 21, a process performed by control LSI 234 to determine whether or not an object moving on medal rail 210 is a regular medal (hereinafter, sometimes referred to as “regular medal discrimination process”). Will be described.

  FIG. 21 is a diagram for explaining the regular medal discrimination process of the control LSI 234. FIG. 21 shows the relationship of processing in each device constituting the control LSI 234 in time series, and the relatively thick line portion of the vertical line extending below each device name indicates the various processing described above for that device. It shows that it is in a state of performing. A broken line arrow extending from a line corresponding to each device toward a vertical line extending below “IN” in the host controller indicates an interrupt signal output from each device to the host controller 241. A broken line arrow extending from a vertical line extending below “OUT” in the host controller toward a line corresponding to each device indicates a signal output from the host controller 241 to each device. In addition, a solid arrow between a vertical line extending below “IN” and a vertical line extending below “OUT” in the host controller indicates an interrupt signal detected by the host controller 241 and the host controller 241. The correspondence relationship with the output signal is shown. FIG. 21 shows a regular medal discrimination process when six medals are successively inserted into the medal slot 21 (see FIG. 2). In addition, in order to clarify the number of medals related to the signal, a number indicating the order of insertion of medals is attached to the head of the code attached to each signal. For example, a VSYNC interrupt signal output to the host controller 241 from an ISP circuit 245, which will be described later, related to the first medal is labeled with “1IH”, and the same VSYNC interrupt related to the second medal is assigned. The signal was labeled “2IH”.

  First, when the CMOS image sensor 232 (see FIG. 17) images an object moving on the medal rail 210 (in this example, the first medal) and outputs the image data to the control LSI 234, the ISP circuit 245 causes the ISI circuit Image data is acquired (received) via 251 and a VSYNC (Vertical Synchronization) interrupt signal is output to the host controller 241 (1IH). Further, the ISP circuit 245 performs conversion processing for converting the RGB Bayer image into various formats. Then, the converted image data and the hue, saturation, and luminance data relating to the image data are output to the SRAM 243, the medal count circuit 246, and the color recognition circuit 247. The detailed description of the conversion process has been described above, and will not be repeated.

  When receiving data from the ISP circuit 245, the color recognition circuit 247 performs color determination processing, stores the determination result in the SRAM 243, and outputs a color determination interrupt signal to the host controller 241 (1CH). Note that the detailed description of the color determination process has been described above, and will be omitted.

  When the medal count circuit 246 receives data from the ISP circuit 245, the medal count circuit 246 performs count processing, stores the determination result in the SRAM 243, and outputs a medal count interrupt signal to the host controller 241 (1MH). Note that the detailed description of the count process has been described above, and is therefore omitted.

  When the host controller 241 detects the color determination interrupt signal, the host controller 241 acquires the determination result of the color determination processing from the SRAM 243 and outputs it to the allocation PORT of the GPIO 250 (1HG1). That is, the host controller 241 outputs the determination result of the color determination process to the main control board 71 (main control circuit 91) via the GPIO 250.

  When the host controller 241 detects the count interrupt signal, the host controller 241 acquires the determination result of the count process from the SRAM 243 and outputs it to the allocation PORT of the GPIO 250 (1HG2). That is, the host controller 241 outputs the determination result of the count process to the main control board 71 (main control circuit 91) via the GPIO 250. When the determination result of the counting process is “medal has passed”, the main control circuit 91 sets the value of the inserted number counter, which is a counter provided for the main CPU 93 to count the number of inserted medals. Add one. When the value of the inserted number counter is the maximum value (for example, 3), 1 is added to the value of a credit counter that is a counter provided for the main CPU 93 to count the number of credited medals. When the credit counter is the maximum value (for example, 50), the main control circuit 91 sets the medal solenoid 208 of the medal selector 201 to the OFF state. As a result, the select plate 207 is positioned at the “discharge position”, and medals inserted after the credit counter reaches the maximum value are guided to the medal chute 202 and discharged from the medal payout opening 32 to the medal tray unit 34. In the present embodiment, when the value of the insertion number counter is a specified value (for example, 2 or 3), when the start lever is operated, the main CPU 93 performs the above-described internal lottery process.

  When the image data converted by the ISP circuit 245 is stored in the SRAM 243, the fish-eye correction scaler circuit 248 performs fish-eye correction processing, stores the generated reduced image data in the SRAM 243, and causes the host controller 241 to reduce the reduction completion rate. Send a signal (1SH). Since the detailed description of the fisheye correction process has been described above, it will be omitted.

  Between the output of the determination result of the count process by the host controller 241 to the GPIO 250 (1HG2) and the transmission of the reduction end interrupt signal by the fisheye correction scaler circuit 248 (1SH), the second circuit by the ISP circuit 245 An output (2IH) of a VSYNC interrupt signal related to a medal is generated. However, since the storage area of the SRAM 243 is individually set to store determination results of various processes (counting process, color determination process, engraving determination process, etc.) related to each medal, data overwriting does not occur.

  When the host controller 241 detects the reduction end signal, the host controller 241 refers to the SRAM 243, and the determination result of the count process is “the medal has passed”, and the determination result of the color determination process is “matches the color of the regular medal” On the condition that the image recognition DSP circuit 242 is instructed to start preprocessing (1HD).

  The image recognition DSP circuit 242 performs preprocessing according to an instruction from the host controller 241, stores the edge image data in the SRAM 243, and outputs a preprocessing end interrupt signal to the host controller 241 (1DH1). Note that the detailed description of the pre-processing has been described above and is omitted.

  When the host controller 241 detects the preprocessing completion interrupt signal, it instructs the image recognition accelerator circuit 249 to start the rotation integration process (1HA).

  The image recognition accelerator circuit 249 performs rotation integration processing in accordance with an instruction from the host controller 241, stores the gradient average image data in the SRAM 243, and outputs an integration end interrupt signal to the image recognition DSP circuit 242 (1AD). Since the detailed description of the rotation integration process has been described above, the description thereof will be omitted.

  When detecting the integration end interrupt signal, the image recognition DSP circuit 242 acquires gradient average image data stored in the SRAM 243, performs a marking determination process, and stores the determination result in the SRAM 243. Then, the image recognition DSP circuit 242 outputs a marking determination end interrupt signal to the host controller 241 (1DH2).

  When the host controller 241 detects the marking determination end interrupt signal, the host controller 241 acquires the determination result of the marking determination process stored in the SRAM 243 and outputs it to the GPIO allocation PORT (1HG3). That is, the host controller 241 outputs the determination result of the marking determination process to the main control board 71 (main control circuit 91) via the GPIO 250.

  As shown in FIG. 21, in the present embodiment, the preprocessing and the marking determination process by the image recognition DSP circuit 242 and the rotation integration process by the image recognition accelerator circuit 249 take a relatively long time. For this reason, when medals are continuously inserted, when the host controller 241 detects the reduction end signal, the host controller 241 checks whether the image recognition DSP circuit 242 or the image recognition accelerator circuit 249 is processing (busy state). When none of them are being processed, an instruction is given to start preprocessing and marking determination processing by the image recognition DSP circuit 242 and rotation accumulation processing by the image recognition accelerator circuit 249.

  Therefore, in the present embodiment, as shown in FIG. 21, when the host controller 241 detects the reduction end signals (2SH and 3SH) relating to the second and third medals, the image recognition DSP circuit 242 or the image recognition Since the accelerator circuit 249 is being processed (busy state), the host controller 241 does not issue the start instruction. Therefore, for the second and third medals, the count process and the color determination process are performed, but the marking determination process is not performed. On the other hand, when the host controller 241 detects the reduced signal (4SH) related to the fourth medal, the image recognition DSP circuit 242 and the image recognition accelerator circuit 249 are not in processing (busy state). Accordingly, for the fourth medal, a count process, a color determination process, and a stamp determination process are performed.

  In addition, by speeding up the pre-processing and marking determination processing by the image recognition DSP circuit 242 and the rotation integration processing by the image recognition accelerator circuit 249, the count processing, color determination processing, and marking determination processing are performed for all inserted medals. It may be performed.

  Various signals related to the second, third, fourth, fifth, and sixth medals shown in FIG. 21 (the code starts with “2”, “3”, “4”, “5”, The “6” signals) are the same as the various signals related to the first medal described above (only the first symbol is “1”), which is different only in the first digit, and detailed description thereof is omitted. Note that the processing timing of each device in the regular medal discrimination process of the control LSI 234 shown in FIG. 21 is merely an example. The regular medal determination process can be performed at various processing timings according to the processing capability, processing content, and processing procedure of each device.

<Action>
In the pachi-slot 1 of the present embodiment, the control LSI 234 of the medal selector 201 performs a regular medal discrimination process including a color determination process, a count process, and a marking determination process. When an unauthorized device that is not a medal moves on the medal rail 210, it is determined that the color does not match the color of the regular medal in the color determination process, and it is determined that the medal has not passed in the count process. Therefore, it is possible to detect an illegal act of playing a game by misrecognizing that a regular medal is used in the pachislot 1.

  Further, an illegal medal 290 shown in FIG. 22A moves on the medal rail 210 (the medal having the same diameter and the same color as the regular medal 280 (see FIG. 19A), but only a stamp (pattern) applied to the surface of the medal). In this case, in the color determination process, it is determined that “matches the color of the regular medal”. However, in the counting process, the imprinted medal image data 292 shown in FIG. 22B is engraved (pattern) in the count area (area 293 surrounded by a dotted line) and the regular medal image data count area (in FIG. 19B, the dotted line). Since the engraving (pattern) in the enclosed region 283) is significantly different, it is determined that “the medal has not passed”. Therefore, it is possible to detect an illegal act of playing a game by misrecognizing that a regular medal is used in the pachislot 1.

  Further, on the medal rail 210, there is an illegal medal 295 shown in FIG. 23A (other medal having the same diameter and the same color as the regular medal 280 (see FIG. 19A), but different only in the stamp (pattern) applied to the surface of the medal). If it has moved, it is determined in the color determination process that it “matches the color of the regular medal”. Further, in the counting process, the imprinted medal image data 297 shown in FIG. 23B is engraved (pattern) in the count area (area 298 surrounded by a dotted line) and the regular medal image data count area (indicated by the dotted line in FIG. 19B). Since the difference between the engraving (pattern) in the enclosed region 283) is small, it is determined that “the medal has passed”. However, in the marking determination process, the gradient average image data 299 of the illegal medal shown in FIG. 23C and the gradient average image data 285 (see FIG. 20) of the regular medal 280 are greatly different. It is determined that it does not match the medal stamp. Therefore, it is possible to detect an illegal act of playing a game by misrecognizing that a regular medal is used in the pachislot 1.

  Also, the medal of the same color as the regular medal 280 (see FIG. 19A) and a different diameter (slightly smaller or larger than the regular medal and guideable by the select plate 207) moved on the medal rail 210. In this case, in the color determination process, it is determined that “matches the color of the regular medal”. However, in the image data of this medal, if this medal is slightly smaller than the diameter of the regular medal and the count area has a boundary between the outer edge of the medal and the background, the “no medal has passed” in the counting process. It is determined. Even if it is determined that the medal has passed in the counting process, the gradient average image data of this medal and the gradient average image data 285 of the regular medal 280 are obtained from the difference in diameter between this medal and the regular medal 280 (see FIG. 20)). Therefore, in the marking determination process, it is determined that “the medal stamp (pattern) does not match the stamp of the regular medal”. Therefore, it is possible to detect an illegal act of playing a game by misrecognizing that a regular medal is used in the pachislot 1.

  Further, when a medal having the same diameter and different color as the regular medal 280 (see FIG. 19A) moves on the medal rail 210, it is determined that the color does not match the color of the regular medal in the color determination process. Therefore, it is possible to detect an illegal act of playing a game by misrecognizing that a regular medal is used in the pachislot 1.

  Further, the control LSI 234 outputs the determination results of the color determination process, the count process, and the marking determination process to the main control circuit 91 including the main control board 71 via GPIO. Therefore, it is possible to cause the main control circuit 91 to perform various processes when there is an illegal act. Here, the various processes when there is a fraudulent action are, for example, that the main control circuit 91 forcibly interrupts the game and notifies the fact that the fraudulent act has occurred via the sub-control circuit 101 (for example, , Displaying that the fraud has occurred on the liquid crystal display device 11).

  Further, when an illegal act is detected based on the determination result of the color determination process and the count process, the main control circuit 91 may set the medal solenoid 208 of the medal selector 201 to the OFF state. As a result, the select plate 207 is positioned at the “discharge position”, so that the illegal medal can be guided to the medal chute 202 and discharged from the medal payout opening 32. The main control circuit 91 sets the medal solenoid 208, which has been set to the OFF state by detecting the cheating by the color determination process and the counting process, to the ON state after guiding the cheating medal related to the cheating to the medal chute 202. May be.

  Further, even when an illegal act is detected by the stamp determination process, the main control circuit 91 may set the medal solenoid 208 of the medal selector 201 to the OFF state. In the present embodiment, as shown in FIG. 21, after the VSYNC interrupt signal (4IH) related to the fourth medal is output from the ISP circuit 245 to the main control circuit 91, the VSYNC interrupt related to the fifth medal. Until the signal (5IH) is output, the determination result of the marking determination process related to the first medal is output to the main control circuit (1HG3). Therefore, when illegal medals are continuously inserted, the illegal medals inserted after the fifth one can be guided to the medal chute 202 and discharged from the medal payout opening 32. As a result, the spread of damage caused by fraud can be suppressed. If the imprint taken by the camera unit 209 passes through the after medal pressure 218 or the medal stopper unit 227 by speeding up the imprint determination process, an improper act can be detected by the imprint determination process. Since the main control circuit 91 immediately sets the medal solenoid 208 to the OFF state, it is possible to prevent the occurrence of damage due to fraud. In addition, the main control circuit 91 determines that the medal solenoid 208 that has been set to the OFF state by detecting an illegal act by the stamp determination process indicates that the determination result of the next stamp determination process indicates that the medal stamp (pattern) matches the stamp of the regular medal. If “Yes”, it may be set to ON. As a result, since illegal medals were accidentally mixed, if the player inserts illegal medals without intending fraud, and the medal solenoid 208 is set to the OFF state and the game becomes impossible, the player If a medal is inserted, the game can be resumed.

<Modification of First Embodiment>
The gaming machine according to the first embodiment of the present invention has been described above including the effects thereof. However, the gaming machine of the present invention is not limited to the above-described embodiment, and various modifications can be made without departing from the gist of the present invention described in the claims.

  For example, in the above description, an example was described in which medals having the same marking (pattern) on both sides were used as game media, but instead of this, different markings were made on one side and the other side of the medal. You may use the given medal. In this case, data relating to each face of the medal may be prepared in advance as data relating to the threshold value in the count process, the color determination process, and the marking determination process.

  Further, as a method for setting data relating to the threshold value, a certain unit game period (for example, 100 games) is set as the data collection period relating to the threshold value, and the camera unit 209 captures images during this unit game period. A method of setting based on the image data of medals may be adopted.

  The gaming machine according to the first embodiment described above can determine a medal or the like through image conversion and image recognition processing performed based on a captured image acquired by the imaging unit 261 including the CMOS image sensor 232 and the like. Therefore, it is possible to determine the difference in the pattern of medals and the like. Further, since the control LSI 234 of the camera unit 209 is configured as an ASIC or the like, the manufacturing cost can be effectively suppressed. Further, since the control LSI 234 is provided in a packaged state such as an ASIC, an illegal act from the outside (for example, invalidate the regular medal discrimination process or steal the processing logic of the regular medal discrimination process) And has a significant security advantage.

<< Second Embodiment >>
Hereinafter, a pachislot machine that is a gaming machine according to a second embodiment of the present invention will be described with reference to FIGS. The pachislot machine 300, which is a gaming machine according to the second embodiment of the present invention, has the functional flow, the pachislot structure, the medal selector structure, the pachislot circuit structure, and the medal selector circuit structure described above in the first embodiment. It is the same as the pachislot machine 1 that is a gaming machine according to the above. Hereinafter, the regular medal discrimination process executed by the pachislot machine 1 that is the gaming machine according to the first embodiment will be described in more detail, and a new regular medal discrimination process method will be described.

  As described above, the pachislot machine 300 that is a gaming machine according to the second embodiment includes the control LSI 334 (corresponding to the control LSI 234 of the gaming machine according to the first embodiment), similarly to the gaming machine according to the first embodiment. A camera unit 309 (corresponding to the camera unit 209 of the gaming machine according to the first embodiment) is provided, and further, a medal selector 301 including the camera unit 309 (corresponding to the medal selector 201 of the gaming machine according to the first embodiment) is provided. . FIG. 24 is a functional block diagram of such a camera unit 309, which is substantially the same configuration as that shown in the functional block diagram related to the gaming machine according to the first embodiment shown in FIG.

  As shown in FIG. 24, the camera unit 309 according to this embodiment includes an imaging unit 361, a conversion unit 363, a feature image generation unit 364, a determination unit 365, and an input / output unit 366. Note that the camera unit 309 includes a light emitting unit made of an LED or the like, which is not shown in FIG.

  The imaging unit 361 includes a CMOS image sensor 332 (for example, corresponding to the CMOS image sensor 232 of the gaming machine according to the first embodiment), and image data captured by the CMOS image sensor 332 (predetermined if necessary) Conversion) and output as a captured image 362A.

  The conversion unit 363 (for example, corresponding to the ISP circuit 245 of the gaming machine according to the first embodiment) converts the captured image 362A input from the imaging unit 361 from a color image to a grayscale image, and converts the converted captured image The captured image 362B is output.

  The feature image generation unit 364 (for example, corresponding to the image recognition accelerator circuit 249 of the gaming machine according to the first embodiment) is a feature image indicating the features of the medal 310 based on the captured image 362B in which the medal 310 is captured. 362C is generated. Based on the feature image 362C generated by the feature image generation unit 364, the determination unit 365 determines that the medal 310 shown in the captured image 362B (that is, the medal 310 corresponding to the image of the medal 310 included in the captured image 362C) is valid. It is determined whether it is a thing, and the determination result 368 is output via the input / output part 366 (for example, corresponding to GPIO250 of the gaming machine according to the first embodiment).

  The determination unit 365 (for example, corresponding to the image recognition DSP circuit 242 of the gaming machine according to the first embodiment) is a feature image 362C generated from the captured image 362B by the feature image generation unit 364, and a template indicating the features of the regular medal Data (template feature image) 367 is compared, and based on the comparison result, it is determined whether or not the medal 310 related to the captured image 362B is genuine.

  FIG. 25 is a diagram schematically illustrating an example of a captured image 362A obtained by the imaging unit 361. The captured image 362A illustrated in FIG. 25 includes an image of the captured medal 310. Further, the medal rail 311 as a background is imaged, and the image is included in the captured image 362A. The medal rail 311 corresponds to the medal rail 210 of the first embodiment described above, but here, the shape of the rail is simplified.

  On one main surface 310a of the medal 310, for example, a pattern of alphabet “A” is shown. This shows a pattern of a regular medal, but other patterns may be used. Moreover, a pattern may be attached | subjected to both the main surfaces of a regular medal.

  In the present embodiment, the medal 310 moves on the medal rail 311 while rotating around the rotation axis along the thickness direction passing through the centers of both main surfaces. Then, the imaging unit 361 images the medal 310 from the one main surface 310a side of the medal 310. Therefore, the captured image 362A includes an image of the one main surface 310a of the medal 310. In the present embodiment, the captured image 362A generated by the imaging unit 361 is a color image, but may be a grayscale image.

  FIG. 26 is a diagram illustrating a configuration of the feature image generation unit 364. As illustrated in FIG. 26, the feature image generation unit 364 includes a first image generation unit 370 and a second image generation unit 380. The first image generation unit 370 generates a first image 374 showing the medal 310 based on the captured image 362B. The second image generation unit 380 combines at least a part of the rotation composite image obtained by combining the plurality of rotation images obtained by rotating the first image 374 generated by the first image generation unit 370 with the feature image 362C (second image). ).

  The first image generation unit 370 includes an extraction unit 371 and an edge image generation unit 372. The extraction unit 371 extracts a medal area 373 where the medal 310 is shown from the captured image 362B. The edge image generation unit 372 performs edge detection on the medal area 373 extracted by the extraction unit 371 and generates an edge image (first image 374).

<Flow of regular medal discrimination processing>
Next, a series of operations of the regular medal discrimination process performed by the camera unit 309 in the present embodiment will be described.

  First, when the captured image 362A is input from the imaging unit 361, the conversion unit 363 converts the captured image 362A from a color image to a grayscale image, and the captured image 362B obtained thereby is set as a processing target.

  Next, the extraction unit 371 extracts a medal area 373 in which the medal 310 appears from the captured image 362B that is the processing target. After that, the edge image generation unit 372 performs edge detection on the medal area 373 extracted by the extraction unit 371 and generates an edge image as the first image 374 showing the medal 310. Next, the second image generation unit 380 features at least a part of a rotation composite image obtained by combining a plurality of rotation images obtained by rotating the edge image (first image 374) generated by the edge image generation unit 372. Generated as an image 362C.

  Next, the determination unit 365 compares the feature image 362C generated by the second image generation unit 380 with the feature image included in the template data 367, and based on the comparison result, determines the captured image 362B to be processed. It is determined whether or not the displayed medal 310 is genuine. In other words, the determination unit 365 determines whether the medal 310 shown in the captured image 362A generated by the imaging unit 261 is genuine based on the comparison result between the feature image 362C and the feature image included in the template data 367. Determine whether or not. Then, the determination unit 365 sends the determination result 368 to the main control circuit (corresponding to the main control circuit 91 in the gaming machine of the first embodiment) via the input / output unit 366 (corresponding to the GPIO 250 of the first embodiment). Output. In this way, when the medal 310 shown in the captured image 362A is not a regular one, the main control circuit forcibly interrupts the game, similarly to the gaming machine of the first embodiment, and the sub control circuit (first Via the sub-control circuit 101 in the gaming machine of the embodiment, it can be notified that there has been an illegal act. For example, it is possible to issue a warning to the outside by outputting a warning sound from a speaker or displaying warning information on a display which is a liquid crystal display device.

  Thereafter, when a new captured image 362A is input, the determination unit 365 performs the above-described regular medal determination process using the captured image 362B obtained from the captured image 362A as a new processing target. Thereafter, the determination unit 365 performs the same operation every time the captured image 362A is input.

<Detailed description of each component>
Next, operations of the extraction unit 371, the edge image generation unit 372, the second image generation unit 380, and the determination unit 365 of the first image generation unit 370 will be described in more detail.

[Extractor]
FIG. 27 is a diagram schematically illustrating an example of the medal area 373 extracted by the extraction unit 371 from the captured image 362B. There are various methods for extracting the medal area 373 from the captured image 362B.

  For example, there is a first extraction method that uses the fact that the outer shape of the medal 310 is circular. In this first extraction method, first, edge detection is performed on the captured image 362B to generate an edge image. As an edge image generation method, for example, Sobel method, Laplacian method, Canny method and the like are used. Next, a circular area is extracted from the generated edge image. For example, Hough transform is used as a method for extracting a circular region. A circular area in the captured image 362B existing at the same position as the position of the circular area in the edge image is set as a medal area 373.

  As another method, there is a second extraction method for extracting the medal region 373 from the captured image 362B using the background difference method and labeling. In the second extraction method, first, a background difference image indicating a difference between the captured image 362B and a background image (an image showing only the background of the captured image 362B) is generated, and the generated background difference image is binarized. The Then, labeling such as 4-connection is performed on the binary background difference image. A partial area in the captured image 362B existing at the same position as the position of the connected area (independent area) obtained as a result of labeling in the binary background difference image is set as a medal area 373.

  In the present embodiment, the extraction unit 371 extracts the medal area 373 from the captured image 362B by a method different from the above two methods. The operation of the extraction unit 371 according to this embodiment will be described below. Note that the extraction unit 371 may extract the medal area 373 from the captured image 362B using one of the two methods described above.

  First, the extraction unit 371 generates a background difference image indicating a difference between the captured image 362B and the background image 375 (an image showing only the background of the captured image 362B), and binarizes the generated background difference image. FIG. 28 is a diagram schematically showing the background image 375, and FIG. 29 is a diagram schematically showing a binary background difference image 376. Note that, in the binary image schematically shown in FIG. 29 and later-described drawings in the present embodiment, the region having the pixel value “1” (high luminance region) is shown in black and the pixel value is “0”. This region (low luminance region) is shown in white. The background image 375 can be stored in, for example, an SRAM (corresponding to the SRAM 243 of the camera unit 209 according to the first embodiment).

  Next, the extraction unit 371 performs template matching on the binary background difference image 376 using a binary outer shape template 377 indicating the outer shape of the medal 310. That is, the extraction unit 371 specifies where in the background difference image 376 a region similar to the outer shape template 377 exists. In other words, the extraction unit 371 specifies where in the background difference image 376 there is an area that matches the outline of the medal 310 indicated by the outline template 377. FIG. 30 is a diagram schematically showing the outer shape template 377. The outline template 377 can be stored in, for example, an SRAM (corresponding to the SRAM 243 of the camera unit 209 according to the first embodiment).

  In template matching, the extraction unit 371 moves the outline template 377 little by little (for example, one pixel (pixel) at a time) in the raster scan direction on the background difference image 376 as shown in FIG. In other words, the extraction unit 371 raster scans the outline template 377 on the background difference image 376. At this time, the extraction unit 371 generates an AND image of the outline template 377 and a partial region of the background difference image 376 that overlaps the outline template 377 at each position of the outline template 377. Thereby, a plurality of binary AND images are generated. The extraction unit 371 then extracts the background difference image 376 of the outer shape template 377 used in generating the AND image having the largest number of pixels (high luminance pixels) having the pixel value “1” among the plurality of generated AND images. Identify the top position. This position is a position where an area similar to the outline template 377 exists in the background difference image 376.

  Then, as illustrated in FIG. 32, the extraction unit 371 extracts a partial area 378 in the captured image 362B existing at the same position as the identified position as a medal area 373. In other words, the extraction unit 371 extracts, as the medal area 373, the partial area 378 in the captured image 362B that overlaps the external shape template 377 when the external shape template 377 is arranged in the captured image 362B at the same position as the specified position. . At this time, in the partial area 378, a medal area 373 may be obtained by setting the pixel value of each pixel outside the circle indicated by the outer shape template 377 on the partial area 378 to zero. The medal area 373 extracted by the extraction unit 371 is a grayscale image. In the present embodiment, the outer shape of the medal area 373 is a quadrangle, but may be another shape such as a circle.

[Edge image generator]
The edge image generation unit 372 performs edge detection on the medal area 373 extracted by the extraction unit 371 using, for example, the Sobel method, the Laplacian method, the Canny method, and the like, and generates an edge image (first image 374). Generate. In the present embodiment, the edge image generation unit 372 uses, for example, a Sobel method that is light in processing. The edge image is a binary image. FIG. 33 is a diagram schematically showing an edge image.

[Second image generation unit]
The second image generation unit 380 combines, as a feature image 362C, at least a part of a rotation composite image obtained by combining a plurality of rotation images obtained by rotating the first image (edge image) 374 generated by the edge image generation unit 372. Generate. In the present embodiment, the second image generation unit 380 generates, as the feature image 362C, for example, a rotation composite image obtained by combining a plurality of rotation images obtained by rotating the first image (edge image) 374. Here, the rotation of the first image (edge image) 374 includes a case where the rotation angle is 0 °. Below, the production | generation method of the said rotation synthetic | combination image is demonstrated.

  FIG. 34 is a diagram for describing a method in which the second image generation unit 380 generates the rotation composite image 379. The second image generation unit 380 rotates the first image (edge image) 374 by a predetermined angle α to generate a plurality of rotated images 374a as shown in FIG. Here, the second image generation unit 380 rotates the first image (edge image) 374 by a predetermined angle α until the total rotation angle reaches (360 ° −α). In the present embodiment, the second image generation unit 380 rotates the first image (edge image) 374, for example, by 2 ° (α = 2 °), and generates 180 rotated images 374a. The angle α described above can be adjusted to various angles such as 1 ° and 4 °.

  Then, the second image generation unit 380 combines the generated plurality of rotation images 374a to generate a rotation combination image 381. Specifically, the second image generation unit 380 adds and averages the plurality of rotated images 374a with their centers coincided with each other, and sets the averaged image obtained thereby as the rotation synthesized image 381. The second image generation unit 380 uses the generated rotation composite image 381 as a feature image 362C indicating the feature of the medal 310 shown in the captured image 362B.

  When the second image generation unit 380 combines the plurality of rotation images 374a, the rotation image 374a having a total rotation angle of 0 ° in each rotation image 374a (that is, the first image that has not been rotated ( Edge image) The region that protrudes from the outer shape of 374) is not used. Therefore, the rotation composite image 381 becomes a gray scale image having the same size as the first image (edge image) 374.

  As described above, the imaging unit 361 images the rotating medal 310 and generates a captured image 362A in which the medal 310 is reflected. Therefore, the rotation angle of the medal 310 of the captured image 362B generated by the conversion unit 363 (the rotation angle of the pattern attached to the medal 310) is not always the same. On the other hand, the rotation composite image 381 is a combination of a plurality of rotation images 374a obtained by rotating the first image (edge image) 374 showing the medal 310 of the captured image 362B, and thus the medal of the captured image 362B. Even if there is a variation in the rotation angle of 310, if the medal 310 is genuine, the rotation composite image 381 obtained from the captured image 362B hardly changes. Therefore, it can be said that the rotation composite image 381 is a feature image 362C showing the characteristics of the medal 310 that is not easily influenced by the rotation angle of the medal 310 of the captured image 362B.

[Determining part]
The determination unit 365 compares the rotation composite image 381 (feature image 362C) generated by the second image generation unit 380 with the feature image of the template data 267 indicating the feature of the regular medal 310, and based on the comparison result. Thus, it is determined whether or not the medal 310 included in the captured image 362B is genuine. As a feature image of the template data 267, a feature image 362C (rotation) indicating the feature of the regular medal 310 generated by the feature image generation unit 364 in the same manner as described above from the captured image 362B including the image of the regular medal 310. A composite image 381) is used.

  The medal 310 can be inserted into the gaming machine to obtain a feature image of the template data 367. For example, a captured image 362B in which the inserted regular medal 310 is captured is generated, and this captured image 362B is referred to as a “standard image 391”. Next, the feature image generation unit 364 generates a feature image 362C (rotation synthesized image 381) indicating the features of the regular medal 310 included in the standard image 391 based on the standard image 391. This feature image 362C is referred to as a “standard feature image 392”. In the present embodiment, the standard feature image 392 is a feature image of the template data 367. Such template data 367 is stored in the SRAM or the like of the camera unit 309 as described above. Hereinafter, the feature image 362C generated during actual operation of the gaming machine (the feature image 362C generated to determine the regular medal) is referred to as the “target feature image 362C” in order to distinguish it from the standard feature image 392. There is.

  For example, the determination unit 365 obtains a similarity (difference) between the rotation composite image 381 (target feature image 362C) and the feature image of the template data 367, and compares them. In the present embodiment, the determination unit 365 uses, for example, SAD (Sum of Absolute Difference) as a value indicating the similarity. A large SAD means that the similarity is low, and a small SAD means that the similarity is high. Other values such as SSD (Sum of Squared Difference) or NCC (Normalized Correlation Coffiecient) may be used as the value indicating the degree of similarity.

  When the similarity between the rotation synthesized image 381 and the feature image of the template data 367 is high, the determination unit 365 determines that the medal 310 included in the captured image 362B is genuine, and the similarity is If it is low, it is determined that the medal 310 included in the captured image 362B is not genuine. Specifically, the determination unit 365 determines that the medal 310 of the captured image 362B is genuine when the SAD between the rotation composite image 381 and the feature image of the template data 367 is equal to or less than a threshold value. If the SAD is larger than the threshold value, it is determined that the medal 310 of the captured image 362B is not genuine. Then, the determination unit 365 outputs a determination result 368.

  The threshold value used in the determination unit 365 is determined by using a plurality of medals 310, for example. Specifically, when the gaming machine is not actually operating, a plurality of regular medals are sequentially inserted into the gaming machine. Then, a plurality of captured images 362B in which a plurality of inserted regular medals are respectively captured are generated. The determination unit 365 obtains the SAD between the rotation composite image 381 generated by the feature image generation unit 364 from the captured image 362B and the feature image of the template data 367 for each of the generated plurality of captured images 362B. Then, the maximum value among the plurality of SADs obtained by the determination unit 365 is determined as the threshold value. The determined threshold value is stored in, for example, an SRAM (corresponding to the SRAM 243 of the camera unit 209 according to the first embodiment).

  Note that the threshold value can be determined by such a gaming machine when a predetermined mode is selected in the gaming machine. Further, the threshold value may be determined in advance by a gaming machine or other device and stored in the SRAM or the like of each gaming machine.

  By determining the threshold value used in the determination unit 365 in this manner, when the type of the regular medal 310 is changed, the changed medal 310 is inserted into a gaming machine that is not actually operating. As a result, a threshold value corresponding to the changed medal 310 is determined. Therefore, even if the type of the medal 310 is changed, it is possible to appropriately determine whether or not the medal 310 inserted into the gaming machine is a regular one.

  In the above example, the binary first image (edge image) 374 is input to the second image generation unit 380 as the first image 374 indicating the medal 310 of the captured image 362B. An image indicating the region 373 may be input to the second image generation unit 380 as the first image. In this case, a rotation composite image obtained by combining a plurality of rotation images obtained by rotating the medal area 373 is used as the feature image 362C.

  As described above, in the pachislot machine 300 that is the gaming machine according to the second embodiment, at least the rotation composite image 381 obtained by combining a plurality of rotation images obtained by rotating the first image (edge image) 374 showing the medal 310. A part is generated as the second image (feature image 362C). This feature image 362C is not easily affected by the rotation angle of the medal 310 included in the captured image 362B. Therefore, even when the rotation angle (rotation posture) of the medal 310 included in the captured image 362B varies, the medal 310 included in the captured image 362B using the feature image 362C (target feature image 362C, standard feature image 392). Can be more accurately determined whether or not is genuine, and the determination accuracy is improved.

  In this embodiment, since the binary edge image is the first image 374, the brightness of the imaging region in the imaging unit 361 is compared to the case where the medal region 373 of the grayscale image is the first image 374. It is possible to suppress the first image 374 from being affected by the change in height. Therefore, it is possible to suppress the characteristic image 362C from being affected by the change in the brightness of the imaging area where the medal 310 is imaged, and as a result, the accuracy of determining a regular medal is improved.

  In the present embodiment, the extraction unit 371 uses the template matching to extract the medal area 373 from the captured image 362B. Therefore, the first extraction method using the Hough transform and the labeling are used. Compared with the second extraction method, the extraction process is simplified.

  In the present embodiment, the determination unit 365 compares the feature image 362C generated from the captured image 362B with the feature image of the template data 367 using SAD or the like, and based on the comparison result, the captured image 362B. Since it is determined whether or not the medal 310 according to is genuine, the determination process is simplified.

<Modification of Second Embodiment>
Various modifications will be described below.

[Modification 1]
In the above example, the standard feature image 392 is adopted as the feature image of the template data 367 to be compared with the target feature image 362C. However, from the plurality of captured images 362A in which a plurality of different regular medals 310 are respectively captured. A composite image obtained by combining a plurality of standard feature images 392 generated respectively may be used as the feature image of the template data 367.

  FIG. 35 is a diagram for explaining a method for generating a feature image of template data 367 according to this modification. In the example of FIG. 35, four standard feature images 392 respectively generated from captured images 362B in which four different regular medals 310 are captured are used to generate the template data 367. Here, when both main surfaces of one medal 310 have different patterns, these can be individually used as the standard feature image 392 for generating the template data 367.

  In this modification, when the template data 367 is generated, a plurality of regular medals 310 are sequentially inserted into the gaming machine when the gaming machine is not actually operating. Then, a plurality of captured images 362A in which a plurality of regular medals 310 inserted into the gaming machine are respectively captured are generated. The feature image generation unit 364 generates a standard feature image 392 based on the captured image 362A for each of the generated captured images 362A. Next, the feature image generation unit 364 combines the plurality of generated standard feature images 392, and uses the combined image 382 (see FIG. 35) obtained thereby as the feature image of the template data 367. For example, the feature image generation unit 364 adds and averages a plurality of standard feature images 392, and uses the obtained addition average image (synthesized image 382) as a feature image of the template data 367.

  Note that the generation of the template data 367 by such a gaming machine can be performed when a predetermined mode is selected in the gaming machine. Alternatively, the template data 367 may be generated in advance by a gaming machine or other device and stored in the SRAM or the like of each gaming machine.

  As described above, the combined image 382 obtained by combining a plurality of standard feature images 392 showing the features of the different regular medals 310 is used as the feature image of the template data 367, so that the standard feature image 392 is directly used as the template data 367. Compared to the case, the influence of individual differences of the regular medals 310 on the regular medal discrimination process can be suppressed. In addition, even when the distance between the medal 310 and the imaging device (for example, a CMOS image sensor) of the imaging unit 361 varies when the imaging unit 361 captures the medal 310, this affects the regular medal discrimination process. Therefore, the accuracy of the regular medal discrimination process is improved.

  Further, unlike the present example, when the first image 374 showing the regular medal 310 is used as it is as the standard feature image 392, the plurality of standard feature images 392 are combined when the plurality of standard feature images 392 are combined. It is necessary to match the orientations of the plurality of standard feature images 392 so that the rotation angles (rotation postures) of the plurality of regular medals 310 included in each of them match.

  On the other hand, in the present modified example, a rotation composite image 381 obtained by combining a plurality of rotation images obtained by rotating the first image 374 showing the regular medal 310 is used as the standard feature image 392. When combining a plurality of standard feature images 392, it is not necessary to match the orientation of the plurality of standard feature images 392. Therefore, the feature image generation process of the template data 367 is simplified.

  If the regular medal 310 used in generating the feature image of the template data 367 has a large flaw, even if the template data 367 is generated by combining a plurality of standard feature images 392, the effect of the flaw is generated. Appears in the template data 367, and the accuracy of the regular medal discrimination process may deteriorate.

  Therefore, when pixel values of a plurality of pixels at the same position included in the plurality of standard feature images 392 respectively indicating the features of the plurality of regular medals 310 have pixel values that are extremely different from other pixel values. Alternatively, the feature image of the template data 367 may be generated without using the standard feature image 392 including the pixels having extremely different pixel values. Thereby, it is possible to suppress the use of the standard feature image 392 indicating the features related to the regular medal 310 having a large scratch for the generation of the feature image of the template data 367. Therefore, it can suppress that the precision of a regular medal discrimination process deteriorates.

[Modification 2]
In the above example, the second image generation unit 380 uses the rotation composite image 381 obtained by combining a plurality of rotation images obtained by rotating the first image 374 showing the medal 310 as the feature image 362C. May be a feature image 362C. Hereinafter, a part of the rotation composite image 381 that becomes the feature image 362C is referred to as a “feature portion region 383”.

  FIG. 36 is a diagram illustrating an example in which a feature partial region 383 that is a part of the rotation composite image 381 is a feature image 362C. In the example shown in FIG. 36, a rectangular partial region that extends from the center 381c to the upper side 381B in the quadratic rotation synthesized image 381 is defined as a feature partial region 383. In the example of the feature portion region 383 shown in FIG. 36, a plurality of pixels are included in each of the vertical direction and the horizontal direction. The shape of the feature portion region 383 may be other than a rectangle.

  For example, the second image generation unit 380 generates the rotation composite image 381 based on the first image 374 showing the medal 310, and then extracts the feature partial region 383 from the rotation combination image 381, thereby generating the feature image 362C. Generate.

  Further, the second image generation unit 380 can also generate the feature image 362C without generating the rotation composite image 381. FIG. 37 is a diagram for explaining the method. As shown in FIG. 37, the second image generation unit 380 sets an extraction window 384 for the first image 374 generated by the first image generation unit 370, and sets a partial region 385 (first area) in the extraction window 384. A partial region of one image 374) is extracted. The extraction window 384 is, for example, the same size as the feature portion region 383 shown in FIG. In addition, the extraction window 384 is set to the same position as the position (see FIG. 36) of the feature part region 383 to be generated in the rotation composite image 381 in the first image 374. The extracted partial area 385 is referred to as “reference partial area 385A”.

  Next, the second image generation unit 380 rotates the extraction window 384 by a predetermined angle β around the center 374c of the first image 374, and extracts the partial region 385 in the extraction window 384 at each rotation angle. Here, the second image generation unit 380 rotates the extraction window 384 by a predetermined angle β around the center 374c of the first image 374 until the total rotation angle becomes (360 ° −β). β can be set to various angles, but in this example is 2 °. Then, the second image generation unit 380 combines the obtained partial areas 385 to generate a combined image. At this time, the second image generation unit 380 rotates the partial regions 385 other than the reference partial region 385A so as to match the outer shape of the reference partial region 385A in the obtained partial regions 385, and then A plurality of partial regions 385 are synthesized. The second image generation unit 380 generates a composite image of the plurality of partial regions 385 by, for example, averaging the obtained partial regions 385 and generating an addition average image. This added average image (synthesized image) corresponds to the feature portion region 383 shown in FIG.

  As described above, by setting a part of the rotation composite image 381 as the feature image 362C, the number of pixels of the feature image 362C is reduced. Therefore, the process in the determination unit 365 that uses the feature image 362C is simplified.

  Further, the second image generation unit 380 rotates the extraction window 384 by a predetermined angle, extracts the partial area 385 in the extraction window 384 at each rotation angle, and synthesizes the obtained partial areas 385. When the feature image 362C is generated, the number of pixels of the image handled when the feature image 362C is generated is reduced, so that the generation process of the feature image 362C is simplified.

  Note that which part of the rotation composite image 381 is to be the feature part region 383 is determined based on the position of the pattern shown on the regular medal 310 or the like. That is, it is preferable to set a part of the rotation composite image 381 in the feature portion region 383 so that the features of the medal 310 are sufficiently expressed in the feature portion region 383.

  For example, as shown in FIG. 25, when the pattern of the regular medal 310 is present over almost the entire surface of the one main surface 310a of the medal 310, the center 381c of the rotation synthesized image 381 as in this example. It is desirable that the feature portion region 383 is set so as to reach the side 381B (see FIG. 36).

  Further, when the pattern of the medal 310 is present only on the peripheral end portion of the one main surface 310a of the medal 310, only the end portion of the rotation composite image 381 is used as the feature portion region 383 as shown in FIG. Good.

  Further, when the pattern of the medal 310 exists over almost the entire surface of the one main surface 310a of the medal 310, a linear feature portion region 383 may be used as shown in FIG. In the feature portion region 383 shown in FIG. 39, a plurality of pixels are included in the vertical direction, but only one pixel is included in the horizontal direction.

<< Third Embodiment >>
Hereinafter, a pachislot machine that is a gaming machine according to a third embodiment of the present invention will be described with reference to FIGS. 40 to 60. The pachislot machine 400, which is a gaming machine according to the third embodiment of the present invention, has the functional flow, the pachislot structure, the medal selector structure, the pachislot circuit structure, and the medal selector circuit structure described above in the first embodiment. It is the same as the pachislot machine 1 that is a gaming machine according to the above. Below, the regular medal discrimination process executed by the pachislot machine 400 that is the gaming machine according to the third embodiment will be described.

  As described above, the pachislot machine 400 that is a gaming machine according to the third embodiment includes the control LSI 434 (corresponding to the control LSI 234 of the gaming machine according to the first embodiment), similarly to the gaming machine according to the first embodiment. It includes a camera unit 409 (corresponding to the camera unit 209 of the gaming machine according to the first embodiment), and further includes a medal selector 401 including the camera unit 409 (corresponding to the medal selector 201 of the gaming machine according to the first embodiment). . FIG. 40 is a functional block diagram of such a camera unit 409.

  As shown in FIG. 40, the camera unit 409 according to the present embodiment includes an imaging unit 461, a conversion unit 463, an extraction unit 464, a specifying unit 465, a fitting unit 466, a determination unit 467, and an input / output unit 468. Yes. Note that the camera unit 409 includes a light emitting unit made of an LED or the like, but is not shown in FIG.

  The imaging unit 461 includes a CMOS image sensor 432 (for example, corresponding to the CMOS image sensor 232 of the gaming machine according to the first embodiment), and image data captured by the CMOS image sensor 432 (predetermined if necessary) Conversion) and output as a captured image 462A.

  The conversion unit 463 (for example, corresponding to the ISP circuit 245 of the gaming machine according to the first embodiment) converts the captured image 462A input from the imaging unit 461 from a color image to a grayscale image, and converts the converted captured image to It outputs as a captured image 462B.

  The extraction unit 464 (for example, corresponding to the image recognition accelerator circuit 249 of the gaming machine according to the first embodiment) extracts a medal area (object area) 473 in which the medal 410 is captured from the captured image 462B.

  The specifying unit 465 (for example, corresponding to the image recognition DSP circuit 242 of the gaming machine according to the first embodiment) specifies a characteristic local area (partial area) in the medal area 473. In other words, the specifying unit 465 specifies a meaningful local area in the medal area 473. The processing in the specifying unit 465 is called “segmentation”. Hereinafter, simply speaking “local region” means a characteristic local region that the specifying unit 465 specifies in the medal region 473.

  The fitting unit 466 (for example, corresponding to the image recognition DSP circuit 242 of the gaming machine according to the first embodiment) fits an ellipse with respect to the local region specified by the specifying unit 465. In the present specification, “ellipse” is a concept including a circle (perfect circle).

  The determination unit 467 (for example, corresponding to the image recognition DSP circuit 242 of the gaming machine according to the first embodiment) uses the ellipse information regarding the ellipse obtained by the fitting unit 466 as the feature of the medal 410 included in the captured image 462B. It is set as the feature amount shown. In the present embodiment, for example, position information and shape information of the ellipse are employed as the ellipse information regarding the ellipse. However, such ellipse information is only an example, and is not limited to such information. Then, the determination unit 467 determines whether or not the medal 410 included in the captured image 462B is genuine based on such a feature amount, and the determination result 469 is used as the input / output unit 468 (for example, Output via the GPIO 250 of the gaming machine according to the first embodiment. In the present embodiment, the determination unit 467 compares the feature amount obtained from the captured image 462B with the standard feature amount (reference feature amount) 467A indicating the feature of the regular medal 410, and based on the comparison result, It is determined whether or not the medal 410 related to the captured image 462B is genuine. The standard feature quantity 467A can be stored in, for example, an SRAM (corresponding to the SRAM 243 of the camera unit 209 according to the first embodiment).

  FIG. 41 is a diagram schematically illustrating an example of a captured image 462A obtained by the imaging unit 461. The captured image 462A illustrated in FIG. 41 includes the captured image of the medal 410. In the captured image 462A, a medal rail 411 as a background is captured. The medal rail 411 corresponds to the medal rail 210 of the first embodiment described above, but here, the shape of the rail is shown in a simplified manner.

  On one main surface 410a of the medal 410, for example, a pattern of alphabet “A” and a pattern of alphabet “B” are shown. This shows a pattern of a regular medal, but other patterns may be used. Moreover, a pattern may be attached | subjected to both the main surfaces of a regular medal.

  In the present embodiment, the medal 410 moves on the medal rail 411 while rotating around the rotation axis along the thickness direction passing through the centers of both main surfaces. Then, the imaging unit 461 images the medal 410 from the one main surface 410a side of the medal 410. Therefore, the captured image 462A includes an image of the one main surface 410a of the medal 410. In the present embodiment, the captured image 462A generated by the imaging unit 461 is a color image, but may be a grayscale image.

<Flow of regular medal discrimination processing>
Next, a series of operations of the regular medal discrimination process performed by the camera unit 409 in the present embodiment will be described.

  First, when a captured image 462A is input from the imaging unit 461, the conversion unit 463 converts the captured image 462A from a color image to a grayscale image, and the captured image 462B obtained thereby is set as a processing target.

  Next, the extraction unit 471 extracts a medal area 473 in which the medal 410 appears from the captured image 462B that is the processing target. Thereafter, the specifying unit 465 specifies a local region in the medal region 473 extracted by the extracting unit 471. Next, in the fitting unit 466, an ellipse is fitted to the local region specified by the specifying unit 465.

  Next, the determination unit 467 uses the ellipse information regarding the ellipse obtained by the fitting unit 466 as a feature amount. Then, the determination unit 467 compares the feature quantity with the standard feature quantity 467A, and determines whether or not the medal 410 of the captured image 462B is genuine based on the comparison result. Then, the determination unit 467 sends the determination result 469 to the main control circuit (corresponding to the main control circuit 91 in the gaming machine of the first embodiment) via the input / output unit 468 (corresponding to the GPIO 250 of the first embodiment). Output. In this way, when the medal 410 shown in the captured image 462A is not a regular one, the main control circuit forcibly interrupts the game in the same manner as the gaming machine of the first embodiment, and the sub control circuit (first Via the sub-control circuit 101 in the gaming machine of the embodiment, it can be notified that there has been an illegal act. For example, it is possible to issue a warning to the outside by outputting a warning sound from a speaker or displaying warning information on a display which is a liquid crystal display device.

  Thereafter, when a new captured image 462A is input, the determination unit 467 executes the above-described regular medal determination process using the captured image 462B obtained from the captured image 462A as a new processing target. Thereafter, the determination unit 467 performs the same operation every time the captured image 462A is input.

<Detailed description of each component>
Hereinafter, operations of the extraction unit 464, the identification unit 465, the fitting unit 466, and the determination unit 467 will be described in more detail.

[Extractor]
FIG. 42 is a diagram schematically illustrating an example of the medal area 473 extracted by the extraction unit 464 from the captured image 462B. There are various methods for extracting the medal area 473 from the captured image 462B.

  For example, there is a first extraction method using the fact that the outer shape of the medal 410 is circular. In the first extraction method, first, edge detection is performed on the captured image 462B to generate an edge image. As an edge image generation method, for example, Sobel method, Laplacian method, Canny method and the like are used. Next, a circular area is extracted from the generated edge image. For example, Hough transform is used as a method for extracting a circular region. The circular area in the captured image 462B that exists at the same position as the position of the circular area in the edge image is set as the medal area 473.

  As another method, there is a second extraction method for extracting the medal area 473 from the captured image 462B using the background difference method and labeling. In the second extraction method, first, a background difference image indicating a difference between the captured image 462B and a background image (an image showing only the background of the captured image 462B) is generated, and the generated background difference image is binarized. The Then, labeling such as 4-connection is performed on the binary background difference image. Then, a partial area in the captured image 462B existing at the same position as the position of the connected area (independent area) obtained as a result of labeling in the binary background difference image is set as the medal area 473.

  In the present embodiment, the extraction unit 464 extracts the medal area 473 from the captured image 462B by a method different from the above two methods. The operation of the extraction unit 464 according to this embodiment will be described below. Note that the extraction unit 464 may extract the medal area 473 from the captured image 462B using either one of the two methods described above.

  First, the extraction unit 464 generates a background difference image indicating a difference between the captured image 462B and the background image 475 (an image showing only the background of the captured image 462B), and binarizes the generated background difference image. FIG. 43 is a diagram schematically illustrating the background image 475, and FIG. 44 is a diagram schematically illustrating the binary background difference image 476. Note that, in the binary image schematically shown in FIG. 44 and later-described drawings in the present embodiment, the region (high luminance region) where the pixel value is “1” is shown in black, and the pixel value is “0”. This region (low luminance region) is shown in white. The background image 475 can be stored in, for example, an SRAM (corresponding to the SRAM 243 of the camera unit 209 according to the first embodiment).

  Next, the extraction unit 464 performs template matching on the binary background difference image 476 using a binary outer shape template 477 indicating the outer shape of the medal 410. That is, the extraction unit 464 specifies where in the background difference image 476 a region similar to the outer shape template 477 exists. In other words, the extraction unit 464 specifies where in the background difference image 476 an area that matches the outline of the medal 410 indicated by the outline template 477 exists. FIG. 45 is a diagram schematically showing the outer shape template 477. The outline template 477 can be stored in, for example, an SRAM (corresponding to the SRAM 243 of the camera unit 209 according to the first embodiment).

  In template matching, the extraction unit 464 moves the outline template 477 little by little (for example, one pixel (pixel) at a time) in the raster scan direction on the background difference image 476 as shown in FIG. In other words, the extraction unit 464 raster scans the outline template 477 on the background difference image 476. At this time, the extraction unit 464 generates an AND image of the outline template 477 and a partial region of the background difference image 476 that overlaps the outline template 477 at each position of the outline template 477. Thereby, a plurality of binary AND images are generated. Then, the extraction unit 464 extracts the background difference image 476 of the outline template 477 used in generating the AND image having the largest number of pixels (high luminance pixels) having the pixel value “1” among the plurality of generated AND images. Identify the top position. This position is a position where an area similar to the outline template 477 exists in the background difference image 476.

  Then, as illustrated in FIG. 47, the extraction unit 464 extracts a partial area 478 in the captured image 462B existing at the same position as the identified position as a medal area 473. In other words, the extraction unit 464 extracts, as the medal area 473, the partial area 478 in the captured image 462B that overlaps the external shape template 477 when the external shape template 477 is arranged in the captured image 462B at the same position as the specified position. . At this time, in the partial area 478, a medal area 473 may be obtained by setting the pixel value of each pixel outside the circle indicated by the outer shape template 477 on the partial area 478 to zero. The medal area 473 extracted by the extraction unit 464 is a grayscale image. In the present embodiment, the outer shape of the medal area 473 is a square, but may be another shape such as a circle.

[Specific part]
The specifying unit 465 specifies a local region in the medal region 473 extracted by the extracting unit 464 using, for example, MSER (Maximally Stable Extremal Regions). The specifying unit 465 may specify the local region by a method other than MSER.

  The identification unit 465 first binarizes the medal area 473 when identifying a local area using MSER. At this time, the specifying unit 465 binarizes the medal area 473 while changing the threshold value used for binarization. Thereby, a plurality of binarized images binarized using different threshold values are obtained. Next, the specifying unit 465 specifies a partial region (a plurality of pixel clusters) in which the pixel value does not change between the plurality of binarized images in the plurality of binarized images obtained. In other words, the specifying unit 465 specifies a partial region in which pixel values are stable among the plurality of binarized images in the plurality of binarized images obtained. Then, the specifying unit 465 sets a partial area in the medal area 473 existing at the same position as the position of the specified partial area in the binarized image as a local area. As a result, the specifying unit 465 specifies a partial area having a uniform pixel value in the medal area 473 as a meaningful area.

  In the present embodiment, in the medal area 473 including the medal 410, an area where the pattern attached to the medal 410 appears is specified as a local area. FIG. 48 is a diagram schematically showing local regions 473a and 473b specified in the medal region 473 in which the medal 410 is included. The local area 473 a is an area in which the “A” pattern attached to the regular medal 410 is reflected in the medal area 473. The local region 473b is a region where the pattern “B” attached to the regular medal 410 is reflected in the medal region 473. In the medal area 473 where the regular medal 410 is shown, the area where the “A” pattern attached to the regular medal 410 is reflected and the area where the “B” pattern attached to the regular medal 410 is separately displayed. Identified as a local region.

  Thus, in the medal area 473, when there are a plurality of characteristic parts independent from each other, the plurality of characteristic parts are specified as different local areas.

[Fitting part]
The fitting unit 466 fits an ellipse to the local area specified by the specifying unit 465. When a plurality of local regions are specified by the specifying unit 465, the fitting unit 466 fits a plurality of ellipses to the plurality of local regions, respectively. FIG. 49 is a diagram showing a state in which ellipses 481a and 481b are fitted to the local regions 473a and 473b shown in FIG. 48, respectively. Below, an example of the method of fitting an ellipse with respect to a local region is demonstrated.

  The fitting unit 466 generates position information and shape information of an ellipse to be fitted to the local area based on the positions of a plurality of pixels constituting the local area included in the medal area 473. In the present embodiment, the fitting unit 466 obtains the center position of the ellipse that is fitted to the local region as the position information of the ellipse. The fitting unit 466 obtains the lengths of the major axis and the minor axis of the ellipse as the shape information of the ellipse.

  The fitting unit 466 calculates an average value of the positions of a plurality of pixels constituting the local area, and sets the average value as the center position of the ellipse to be fitted to the local area. That is, the fitting unit 466 calculates the average value of the x coordinate and y coordinate of a plurality of pixels constituting the local region, and uses the average value as the x coordinate and y coordinate of the center of the ellipse that fits the local region. And In addition, the fitting unit 466 obtains a covariance matrix for the x coordinate and the y coordinate of the pixel in the local region using the x coordinate and the y coordinate of the plurality of pixels constituting the local region. Then, the fitting unit 466 obtains two eigenvalues for the obtained covariance matrix. The fitting unit 466 obtains the lengths of the major axis and the minor axis of the ellipse fitting to the local region from these two eigenvalues. As a result, the position and shape of the ellipse to be fitted to the local region are determined, and the ellipse is fitted to the local region. When the two eigenvalues obtained by the fitting unit 466 are the same value, the ellipse fitting to the local region is a perfect circle.

[Determining part]
The determination unit 467 uses the position information and shape information of the ellipse obtained by the fitting unit 466 as the feature amount, and compares the feature amount with the standard feature amount 567A. Specifically, the determination unit 467 uses the center position of the ellipse, the length of the major axis, and the length of the minor axis obtained by the fitting unit 466 as the feature quantity, and compares the feature quantity with the standard feature quantity 467A. . Then, based on the comparison result, the determination unit 467 determines whether or not the medal 410 included in the captured image 462B is genuine.

  The standard feature quantity 467A includes standard ellipse information. For generation of the standard feature amount 467A, a captured image 462B in which a regular medal 410 is captured is used. A method for generating the standard feature quantity 467A will be described below.

  When the gaming machine (pachislot 400) is not actually operating, a regular medal 410 is inserted into the gaming machine in order to obtain the standard feature quantity 467A. A captured image 462B in which the inserted regular medal 410 is captured is generated by the imaging unit 461 and the conversion unit 463 in the camera unit 409 of the gaming machine according to the present embodiment. Then, the extraction unit 464 extracts the medal region 473 from the captured image 462B in the same manner as described above, and the specifying unit 465 specifies the local region in the medal region 473. In the present embodiment, as shown in FIG. 49 described above, two local areas 473a and 473b are specified in the medal area 473 in which the regular medal 410 appears. The fitting unit 466 fits a plurality of ellipses to the plurality of local regions 473a and 473b specified by the specifying unit 465, respectively. In this manner, an ellipse obtained from the captured image 462B on which the regular medal 410 is shown is referred to as a “standard ellipse”. In the present embodiment, the ellipse information related to the standard ellipse is the standard ellipse information. The standard ellipse information includes position information and shape information of the standard ellipse. Specifically, the standard ellipse information includes the center position of the standard ellipse, the length of the major axis, and the length of the minor axis. In the present embodiment, since a plurality of standard ellipses are obtained from the captured image 462B including the captured image of the regular medal 410, the standard feature quantity 467A includes a plurality of standard ellipse information respectively corresponding to the plurality of standard ellipses. Is included. The standard feature quantity 467A generated when the gaming machine is not actually operating can be stored in, for example, an SRAM (corresponding to the SRAM 243 of the camera unit 209 according to the first embodiment).

  The acquisition of the standard feature quantity 467A by such a gaming machine can be performed when a predetermined mode is selected in the gaming machine. Further, the standard feature quantity 467A may be acquired in advance by a gaming machine or other device and stored in the SRAM or the like of each gaming machine.

  Thereafter, in order to distinguish the ellipse obtained by the fitting unit 466 when the gaming machine is actually operating (the ellipse obtained from the captured image 462B in which the medal 410 to be subjected to the discrimination process is captured) from the standard ellipse. Sometimes called “object ellipse”.

  Here, when the feature amount composed of the ellipse information related to the target ellipse and the standard feature amount 467A are similar, it can be considered that the feature of the medal 410 shown in the captured image 462B and the feature of the regular medal 410 are similar. . Therefore, in this case, it can be determined that the medal 410 related to the captured image 462B is genuine.

  On the other hand, when the feature amount composed of the ellipse information related to the target ellipse and the standard feature amount 467A are not similar, it may be considered that the feature of the medal 410 shown in the captured image 462B is not similar to the feature of the regular medal 410. Therefore, in this case, it seems that there is no problem even if it is determined that the medal 410 shown in the captured image 462B is not genuine. However, when the feature amount composed of the ellipse information related to the target ellipse is not similar to the standard feature amount 467A, if it is determined that the medal 410 shown in the captured image 462B is not a normal one only under this condition, the captured image There is a possibility that the legitimate medal 410 shown in 462B is erroneously determined as not legitimate. This point will be described below.

  In the present embodiment, the imaging unit 461 captures the rotating medal 410 and generates a captured image 462A in which the medal 410 is reflected. Therefore, the rotation angle of the medal 410 (the rotation angle of the pattern attached to the medal 410) shown in the captured image 462B generated by the conversion unit 463 is not always the same. Therefore, the ellipse information regarding the target ellipse obtained from the captured image 462B in which the regular medal 410 is reflected is not always the same. As a result, even if the regular medal 410 appears in the captured image 462B, the feature amount composed of ellipse information about the target ellipse obtained from the captured image 462B may not be similar to the standard feature amount 467A. Therefore, when the feature amount composed of the ellipse information related to the target ellipse and the standard feature amount 467A are not similar, if it is determined that the medal 410 shown in the captured image 462B is not a normal one, the regular amount shown in the captured image 462B is There is a possibility that the medal 410 is erroneously determined not to be genuine.

  Therefore, in the present embodiment, the determination unit 467 includes a plurality of rotation ellipses obtained by rotating the target ellipse fitted to the local area included in the medal area 473 around the center of the medal area 473. Get spheroid information of. Then, the determination unit 467 uses the acquired plurality of pieces of spheroid information as a feature amount, and compares the feature amount with a standard feature amount. When a plurality of local areas are specified in the medal area 473, a plurality of pieces of spheroid information are generated for each of the plurality of local areas, and each piece of spheroid information is used as a feature amount.

  Here, it is assumed that the plurality of rotation ellipses include a target ellipse having a rotation angle of 0 °. That is, the plurality of spheroids include the ellipse itself fitted to the local region. Therefore, the plurality of rotation ellipse information includes ellipse information related to the target ellipse. It can be said that the target ellipse whose rotation angle is 0 ° is the target ellipse whose rotation angle is 360 °.

  FIG. 50 is a diagram illustrating a part of a plurality of rotation ellipses 483 obtained by rotating the target ellipse 482 around the center 473c of the medal area 473. 50 shows three spheroids 483 including the target ellipse 482 (in this example, the target ellipse 482 is also shown as one of the spheroids 483). 50 shows the center 482c of the target ellipse 482 and the center 483c of each rotation ellipse 483.

  In this way, a rotating medal is obtained by using a plurality of pieces of rotation ellipse information about a plurality of rotation ellipses including the target ellipse obtained by rotating the target ellipse around the center 473c of the medal area 473 as a feature amount. Even when 410 is captured, it is possible to appropriately determine whether or not the medal 410 shown in the captured image 462B is genuine. Hereinafter, the operation of the determination unit 467 will be described in detail. Hereinafter, the feature quantity used by the determination unit 467 when the gaming machine is actually operating may be referred to as “target feature quantity” in order to distinguish it from the standard feature quantity.

  FIG. 51 is a flowchart showing the operation of the determination unit 467. When the fitting unit 466 fits an ellipse with respect to the local region included in the medal region 473, as shown in FIG. 51, in step S21, the determination unit 467 acquires rotation ellipse information. The rotation ellipse information acquired here is the ellipse information related to the target ellipse whose rotation angle is 0 °, that is, the ellipse information of the ellipse itself acquired by the fitting unit 466. When a plurality of target ellipses are obtained in the fitting unit 466, a plurality of pieces of rotation ellipse information respectively corresponding to the plurality of target ellipses are acquired. In step S21, at least one piece of spheroid information is acquired. In this example, since two ellipses are obtained from the captured image 462B in which the regular medal 410 is shown, two pieces of rotation ellipse information are obtained in step S21.

  Next, in step S22, the determination unit 467 uses the at least one spheroid information acquired in step S21 as the target feature amount, and obtains an evaluation value indicating the degree of similarity between the target feature amount and the standard feature amount. Specifically, the determination unit 467 determines whether or not standard ellipse information similar to at least one spheroid information constituting the target feature amount is included in the standard feature amount. Then, the determination unit 467 obtains an evaluation value corresponding to the number of spheroid information determined that similar information is included in the standard feature amount. Specifically, the determination unit 467 obtains the evaluation value α using the following formula 1.

α = N1 / N2 (Formula 1)
Here, N1 indicates the number of spheroid information included in the target feature amount, which is determined that similar information is included in the standard feature amount. N2 indicates the total number of standard ellipse information included in the standard feature. In this embodiment, N2 = 2.

  In the present embodiment, the rotation ellipse information included in the target feature amount includes the center position of the rotation ellipse, the length of the major axis, and the length of the minor axis. For example, the determination unit 467 is configured such that the distance between the center position of the spheroid included in the spheroid information and the center position of the standard ellipse included in the standard ellipse information is equal to or less than a predetermined value, and the length of the major axis of the spheroid And the absolute value of the difference between the major axis of the standard ellipse is less than or equal to a predetermined value, and the absolute value of the difference between the minor axis of the rotating ellipse and the minor axis of the standard ellipse is predetermined. When the value is equal to or smaller than the value, it is determined that the rotation ellipse information and the standard ellipse information are similar. When the spheroid information and the standard ellipse information are similar, as shown in FIG. 52, the spheroid 483 corresponding to the spheroid information and the standard ellipse 484 corresponding to the standard ellipsis information are positioned and shaped. Is similar.

  When the determination unit 467 obtains the evaluation value α using Expression 1, in step S23, the rotation ellipse in the latest step S21 (the rotation ellipse corresponding to the rotation ellipse information acquired in step S21) is (360 ° − β) It is determined whether or not the target ellipse is rotated. If the determination unit 467 determines that the rotation ellipse in step S21 is not the target ellipse rotated by (360 ° −β), the determination unit 467 executes step S21 again to acquire the rotation ellipse information. Here, the determination unit 467 rotates the rotation ellipse corresponding to the rotation ellipse obtained by rotating the rotation ellipse corresponding to the rotation ellipse information acquired in the previous step S21 around the center 473c of the medal area 473 by a predetermined angle β. Get ellipse information. If the rotation ellipse in the previous step S21 is, for example, the target ellipse rotated by β, in this step S21, the target ellipse is obtained by being rotated by 2β around the center 473c of the medal area 473. Rotational ellipse information about the spheroid to be obtained is acquired. β is, for example, 1 ° or 2 °.

  When a plurality of pieces of spheroid information are acquired in the previous step S21, the determination unit 467 determines that a plurality of spheroids respectively corresponding to the plurality of pieces of spheroid information are around the center 473c of the medal area 473. A plurality of pieces of spheroid information about a plurality of spheroids obtained by being rotated by a predetermined angle β is acquired.

  When at least one piece of spheroid information is acquired in step S22, the determination unit 467 executes step S23 again to determine the degree of similarity between the target feature amount and the standard feature amount made of the at least one piece of spheroid information. An evaluation value α to be shown is obtained using Equation 1. Thereafter, step S23 is executed again.

  If it is determined in step S23 that the rotation ellipse in the latest step S21 is the target ellipse rotated by (360 ° −β) in step S23, the determination unit 467 executes step S24. In step S24, the determination unit 467 determines whether or not the maximum value among the obtained plurality of evaluation values α is greater than or equal to a threshold value. When the maximum value is equal to or greater than the threshold value, that is, when the target feature value and the standard feature value used when obtaining the maximum value are similar to each other, the determination unit 467 is reflected in the captured image 462B. It is determined that the medal 410 is genuine. On the other hand, when the maximum value is less than the threshold value, the determination unit 467, that is, all of the plurality of target feature amounts respectively used when obtaining the plurality of evaluation values α are not similar to the standard feature amount. In this case, it is determined that the medal 410 shown in the captured image 462B is not regular. The threshold value used in step S24 is set to “1”, for example.

  In the above example, the determination unit 467 determines that the medal 410 shown in the captured image 462B is genuine when the maximum value among the obtained plurality of evaluation values α is equal to or greater than the threshold value. However, when there are a predetermined number or more of the evaluation values α equal to or greater than the threshold value, the medal 410 shown in the captured image 462B may be determined to be genuine. When the evaluation value α equal to or greater than the threshold does not exist, the medal 410 shown in the captured image 462B is determined not to be normal.

  The evaluation value α may be N1. In this case, the threshold value used in step S24 is set to “2”, for example.

<Obtaining spheroid information>
For example, two methods are conceivable as the method of acquiring the spheroid information in step S21. In the first method, the determination unit 467 actually rotates the target ellipse 482 around the center 473c of the medal area 473 by a predetermined angle in the medal area 473 as shown in FIG. 483 is generated. Then, the determination unit 467 obtains the position of the center 483c, the length of the major axis, and the length of the minor axis of the generated spheroid 483, and uses them as spheroid information regarding the spheroid 483. The determination unit 467 generates a plurality of pieces of spheroid information by changing a predetermined angle.

  In the second method, the determination unit 467 acquires rotation ellipse information without actually rotating the target ellipse. Specifically, the determination unit 467 obtains rotation ellipse information of a rotation ellipse obtained by rotating the target ellipse 482 around the center 473c of the medal area 473 by a predetermined angle (β, 2β, 3β, etc.). In this case, as shown in FIG. 53, a virtual point P existing at the position of the center 482c of the target ellipse 482 included in the ellipse information related to the target ellipse 482 is placed around the center 473c of the medal area 473. Rotate only the angle. Then, the determination unit 467 sets the position of the rotated virtual point P ′ as the position of the center of the rotation ellipse included in the rotation ellipse information. The determination unit 467 obtains the positions of the centers of a plurality of rotation ellipses obtained by rotating the target ellipse around the center 473c of the medal area 473 by changing the predetermined angle.

  In the second method, the determination unit 467 can rotate the lengths of the long axis and the short axis of the target ellipse included in the ellipse information regarding the target ellipse around the center 473c of the medal area 473. The lengths of the major axis and the minor axis of each of the plurality of spheroids obtained by the above are used.

  As described above, in the second method, the virtual point P existing at the position indicated by the position information of the target ellipse 482 is rotated around the center 473 c of the medal area 473. Then, the plurality of positions of the rotated virtual point P ′ obtained thereby are set as the positions of the plurality of rotation ellipses, respectively, thereby acquiring the position information of the plurality of rotation ellipses. Further, the length information of the plurality of spheroids is acquired by setting the lengths of the major axis and the minor axis of the target ellipse as the lengths of the major axis and the minor axis of the plurality of spheroids as they are. Therefore, compared to the first method of acquiring a plurality of pieces of spheroid information by actually rotating the target ellipse, the plurality of pieces of spheroid information can be easily obtained in the second method.

  In the above example, the major axis length and minor axis length of the ellipse are adopted as the ellipse shape information included in the ellipse information as the feature quantity. The long / short axis ratio may be adopted.

  As described above, in the present embodiment, the ellipse information regarding the ellipse fitted to the characteristic local region in the medal region 473 is the feature amount indicating the feature of the medal 410 displayed in the captured image 462B. Therefore, the feature amount is easily obtained as compared with the case where the feature amount such as SIFT (Scale Invariant Feature Transformation) or SURF (Speeded Up Robust Features) is obtained from the partial image in the ellipse in the medal area 473. be able to. Therefore, it can be easily determined whether or not the medal 410 shown in the captured image 462B is genuine.

  Further, in the present embodiment, a plurality of pieces of spheroid information regarding a plurality of spheroids including the target ellipse obtained by rotating the target ellipsis 482 around the center 473c of the medal area 473 is used as the feature amount. Therefore, even when the rotating medal 410 is captured, it is possible to appropriately determine whether or not the medal 410 shown in the captured image 462B is genuine.

<Modification of Third Embodiment>
Various modifications of the present embodiment will be described below.

[Modification 1]
When only one large continuous pattern is attached to each of the regular medals 410 and the non-regular medals 410, it cannot be correctly determined whether or not the medals 410 shown in the captured image 462B are genuine. there is a possibility. Hereinafter, this point will be described.

  FIG. 54 is a diagram showing an example of a standard ellipse 482A set for the local region 491A specified in the medal region 473A obtained from the captured image 462B in which the regular medal 410 is shown. FIG. 55 is a diagram showing an example of the target ellipse 482B set for the local region 491B specified in the medal region 473B obtained from the captured image 462B showing the non-regular medal 410.

  54 and 55, only one large continuous pattern is attached to each of the regular medal 410 and the non-regular medal 410. Specifically, the regular medal 410 has a large alphabet “A” pattern, and the non-regular medal 410 has a large alphabet “S” pattern.

  As shown in FIG. 54, one standard ellipse 482A is obtained from a captured image 462B in which a correct medal 410 with only one large continuous pattern is shown. Also, as shown in FIG. 55, one target ellipse 482B is obtained from a captured image 462B on which an irregular medal 410 is shown with only one large continuous pattern.

  As shown in FIG. 54, when only one large continuous pattern is attached to the regular medal 410, the center position of the standard ellipse 482A is close to the center position of the medal area 473A. The shape of the standard ellipse 482A is close to a perfect circle. Also, as shown in FIG. 55, the center position of the target ellipse 482B acquired from the captured image 462B in which the irregular medal 410 with only one large continuous pattern is shown is the center of the medal area 473A. Close to the position, its shape is close to a perfect circle. Therefore, a plurality of spheroids related to a plurality of spheroids including the target ellipse 482B obtained by rotating the target ellipse 482B acquired from the captured image 462B showing the non-regular medal 410 around the center of the medal region 473B. There is a high possibility that the information includes information similar to the standard ellipse information related to the standard ellipse 482A. Therefore, there is a high possibility that the determination unit 467 cannot correctly determine whether or not the medal 410 shown in the captured image 462B is genuine.

  Therefore, in this modification, even if only one large continuous pattern is attached to each of the regular medal 410 and the non-regular medal 410, the accuracy of the true / false determination of the medal 410 is improved. It is possible to improve.

  The fitting unit 466 according to this modification divides the medal area 473 into concentric circles, thereby dividing the local area included in the medal area 473 into a plurality of independent divided areas. Then, the fitting unit 466 fits a plurality of ellipses to the plurality of obtained divided regions. When a plurality of local areas are specified in the medal area 473, each of the plurality of local areas is divided into a plurality of divided areas, and an ellipse is fitted to each divided area.

  FIG. 56 is a diagram showing a state where the medal area 473 is divided concentrically by the fitting unit 466. In the medal area 473 shown in FIG. 56, only the outline of the medal 410 is shown for convenience of explanation.

  In the example shown in FIG. 56, the medal area 473 is divided into concentric circles by two circles 492a and 492b that form a concentric circle 492 and have different radii. Thereby, the medal area 473 is divided into three partial areas 493a to 493c. The partial area 493a is an area inside the circle 492a in the medal area 473. The partial area 493b is an area outside the circle 492a and inside the circle 492b in the medal area 473. The partial area 493c is an area outside the circle 492b and inside the circle 492c in the medal area 473.

  Here, when the outer shape of the medal 410 shown in the medal area 473 is a circle 492c, the radii of the circles 492a, 492b, and 492c increase in this order. The ratio of the radii of the circles 492a, 492b, and 492c is 1: 2: 3. In the present embodiment, the fitting unit 466 divides the medal area 473 concentrically so that the ratio of the radii of the plurality of circles 492a, 492b, and 492c is always 1: 2: 3. That is, in the present embodiment, the fitting unit 466 includes a plurality of circles 492a including the outer shape of the medal 410 displayed in the medal region 473 between the plurality of medal regions 473 extracted by the extraction unit 464 from the plurality of captured images 462B. Each of the plurality of medal areas 473 is concentrically divided so that the ratio of the 492b and 492c radii is constant (1: 2: 3). Note that the ratio of the radii of the plurality of circles 492a, 492b, and 492c may be other than 1: 2: 3. When the medal area 473 is extracted by the first extraction method or the second extraction method described above, the outer shape of the medal area 473 is the outer shape of the medal 410 displayed in the medal area 473.

  FIG. 57 is a diagram showing how the medal area 473A shown in FIG. 54 is concentrically divided. FIG. 58 is a diagram showing how the medal area 473B shown in FIG. 55 is divided into concentric circles. As shown in FIG. 57, the medal area 473A is concentrically divided, so that the local area 491A included in the medal area 473A is divided into a plurality of independent divided areas 491A1, 491A2, 491A3, and 491A4. . As shown in FIG. 58, the medal area 473B is concentrically divided, whereby the local area 491B included in the medal area 473B is divided into a plurality of independent divided areas 491B1, 491B2, and 491B3. .

  In FIG. 57, for convenience, hatched hatching is provided in the divided areas 491A1, 491A2, 491A3, and 491A4 so that it can be easily understood that the local area 491A is divided into a plurality of divided areas 491A1, 491A2, 491A3, and 491A4. It is shown. Similarly, in FIG. 58, hatched hatching is shown in the divided regions 491B1, 491B2, and 491B3 for convenience so that it can be easily understood that the local region 491B is divided into a plurality of divided regions 491B1, 491B2, and 491B3. Yes.

  When the fitting unit 466 divides the local area included in the medal area 473 into a plurality of divided areas, the fitting unit 466 fits a plurality of ellipses to the plurality of divided areas. FIG. 59 is a diagram showing how a plurality of ellipses 494A1, 494A2, 494A3, and 494A4 are fitted to the plurality of divided regions 491A1, 491A2, 491A3, and 491A4 shown in FIG. FIG. 60 is a diagram illustrating a state in which a plurality of ellipses 494B1, 494B2, and 494B3 are fitted to the plurality of divided regions 491B1, 491B2, and 491B3 illustrated in FIG. Each of the plurality of ellipses 494A1, 494A2, 494A3, and 494A4 is a standard ellipse.

  As shown in FIGS. 59 and 60, an ellipse group composed of a plurality of ellipses 494A1 to 494A4 obtained from a medal area 473A in which a regular medal 410 is shown, and a plurality of medals area 473B obtained from a medal area 473B in which a non-regular medal 410 is shown. The number, position, and shape of the ellipse are greatly different from the ellipse group composed of the ellipses 494B1 to 494B3. Therefore, by using a plurality of pieces of ellipse information regarding a plurality of target ellipses obtained as described in the present modification from the medal area 473 extracted from the captured image 462B, the medal 410 reflected in the captured image 462B is obtained. It is possible to more accurately determine whether or not it is regular.

  When a plurality of local areas are specified in the medal area 473, each of the plurality of local areas is divided into a plurality of divided areas. Therefore, a plurality of ellipses are obtained for each of the plurality of local regions. In this modification, the fitting unit 466 obtains a plurality of ellipses regardless of the number of local regions specified in the medal region 473.

  The determination unit 467 according to the present modification determines whether or not the medal 410 shown in the captured image 462B is genuine, in the same manner as described above. Hereinafter, the operation of the determination unit 467 according to this modification will be described with reference to the flowchart of FIG. 51 again.

  When a plurality of target ellipses are obtained in the fitting unit 466, as shown in FIG. 51, in step S21, the determination unit 467 acquires a plurality of pieces of rotation ellipse information respectively corresponding to the plurality of target ellipses. The plurality of pieces of spheroid information acquired here are a plurality of pieces of ellipse information about a plurality of target ellipses having a rotation angle of 0 °, that is, a plurality of pieces of ellipse information about the plurality of target ellipses themselves acquired by the fitting unit 466. As shown in FIG. 59, four ellipses are obtained from the medal area 473 (the medal area 473A shown in FIG. 59) in which the regular medal 410 appears. In this case, four rotations are performed in step S21. Ellipse information is obtained.

  Next, in step S22, the determination unit 467 uses the plurality of pieces of spheroid information acquired in step S21 as the target feature amount, and uses the above equation 1 as the evaluation value α indicating the degree of similarity between the target feature amount and the standard feature amount. Ask for. In this modification, N2 in Equation 1 is “4”.

  When the determination unit 467 obtains the evaluation value α using Equation 1, in step S23, whether or not the plurality of rotation ellipses in the most recent step S21 is a plurality of target ellipses rotated by (360 ° −β), respectively. Determine. If the determination in step S23 is No, the determination unit 467 executes step S21 again to acquire a plurality of pieces of spheroid information. Here, the determination unit 467 is obtained by rotating a plurality of rotation ellipses corresponding to the plurality of rotation ellipse information acquired in the previous step S21 by a predetermined angle β around the center 473c of the medal area 473. A plurality of pieces of spheroid information about a plurality of spheroids are acquired. If the plurality of spheroids in the previous step S21 are, for example, a plurality of target ellipses rotated by β, in this step S21, the plurality of target ellipses are only 2β around the center 473c of the medal area 473. A plurality of pieces of spheroid information about a plurality of spheroids obtained by being rotated is acquired.

  When a plurality of pieces of spheroid information are acquired in step S22, the determination unit 467 executes step S23 again, and evaluates the degree of similarity between the target feature amount composed of the plurality of pieces of spheroid information and the standard feature amount. The value α is determined using Equation 1. Thereafter, step S23 is executed again.

  If the determination in step S23 is Yes, the determination unit 467 determines in step S24 whether the maximum value among the obtained plurality of evaluation values is greater than or equal to the threshold value. When the maximum value is equal to or greater than the threshold value, that is, when the target feature value and the standard feature value used when obtaining the maximum value are similar to each other, the determination unit 467 is reflected in the captured image 462B. It is determined that the medal 410 is genuine. On the other hand, when the maximum value is less than the threshold value, the determination unit 467, that is, all of the plurality of target feature amounts respectively used when obtaining the plurality of evaluation values α are not similar to the standard feature amount. In this case, it is determined that the medal 410 shown in the captured image 462B is not correct. In this modification, the threshold value used in step S24 is set to “0.75” or “1”, for example.

  As described above, in the present modification, the medal area 473 is divided into concentric circles, whereby the local area included in the medal area 473 is divided into a plurality of divided areas, and a plurality of divided areas are divided into a plurality of divided areas. Each ellipse is fitted. A plurality of pieces of ellipse information related to the plurality of ellipses are used as feature amounts. Therefore, as shown in FIG. 54, FIG. 55, etc., even if only one large continuous pattern is attached to each of the regular medal 410 and the non-regular medal 410, It is possible to suppress the similarity between the feature amount acquired from the captured image 462 </ b> B on which the non-medal 410 is reflected and the standard feature amount. Therefore, the accuracy of authenticity determination of the medal 410 can be improved.

  Further, when the imaging unit 461 captures the medal 410, if the distance between the medal 410 and the CMOS image sensor (corresponding to the CMOS image sensor 232 of the camera unit 209 of the first embodiment) varies, the captured image At 462B, the medal 410 appears larger or smaller, and the size of the medal 410 reflected in the captured image 462B varies. As a result, the size of the local area in the medal area 473 in which the regular medal 410 is shown varies. In such a case, if the radii of the circles 492a and 492b (see FIG. 56) set in the medal area 473 are constant regardless of the outer size of the medal 410 reflected in the medal area 473, the medal area 473 Depending on the size of the outer shape of the regular medal 410 appearing in (in accordance with the size of the local region in the medal area 473 in which the regular medal 410 appears), the division mode of the local area included in the medal area 473 varies. Therefore, the positions and shapes of a plurality of ellipses acquired from the medal area 473 in which the regular medal 410 is shown vary, and as a result, the feature amounts acquired from the medal area 473 in which the regular medal 410 is reflected vary, and the captured image 462B is displayed. The authenticity determination of the medal 410 to be reflected may not be performed correctly.

  On the other hand, in the present modification, the extraction unit 464 includes a plurality of circles 492a and 492b including the outer shape of the medal 410 indicated by the medal area 473 between the plurality of medal areas 473 extracted from the plurality of captured images 462B. , 492c, each of the plurality of medal areas 473 is divided concentrically so that the ratio of the radii is constant. Therefore, even if the size of the medal 410 included in the captured image 462B varies (even if the size of the local area in the medal area 473 where the medal 410 appears), the medal 410 appears. It is possible to suppress variations in the division mode of the local area included in the medal area 473. Therefore, it is possible to suppress variations in the positions and shapes of a plurality of ellipses acquired from the medal area 473 where the medal 410 appears. As a result, variation in the feature amount acquired from the medal area 473 in which the medal 410 is displayed is suppressed, and the accuracy of the true / false determination of the medal 410 displayed in the captured image 462B is further improved.

[Modification 2]
This modification is different from the modification 1 described above in the way of obtaining the evaluation value α. That is, in the present modification, the operation in step S22 described above is different from that in Modification 1. When determining the evaluation value α, the determination unit 467 in the present modification determines that similar standard ellipse information is included in the standard feature amount (the position of the spheroid corresponding to the spheroid information included in the target feature amount). Depending on the weighting. This modification will be described in detail below.

  In the present modification, as in Modification 1, the determination unit 467 includes standard ellipse information similar to the rotation ellipse information for each of a plurality of pieces of rotation ellipse information constituting the target feature amount in Step S22 described above. It is determined whether or not it is included in the standard feature amount. Then, the determination unit 467 gives a partial evaluation value to the spheroid information determined that similar standard ellipse information is included in the standard feature quantity (hereinafter, sometimes referred to as “similar spheroid information”). Here, the determination unit 467 weights the partial evaluation value to be given to the similar spheroid information according to the position of the spheroid corresponding to the similar spheroid information.

  How the partial evaluation value is specifically weighted according to the position of the spheroid corresponding to the similar spheroid information is determined according to the position of the characteristic part of the pattern on the regular medal 410. As shown in FIG. 54 described above, the pattern is attached to the one main surface 410a so that the center of the alphabet “A” pattern is positioned near the center of the one main surface 410a of the regular medal 410. If there is, the characteristic portion of the pattern is located near the center of the one main surface 410a. In such a case, the determination unit 467 increases the partial evaluation value given to the similar spheroid information as the position of the spheroid corresponding to the similar spheroid information is closer to the center 473c of the medal area 473. For example, when the center position of the spheroid corresponding to the similar spheroid information is present in the innermost partial region 493a (see FIG. 56) of the medal region 473, the determination unit 467 includes a part in the similar spheroid information. The evaluation value “1.5” is assigned. If the center position of the spheroid corresponding to the similar spheroid information is present in the partial area 493b of the medal area 473, the determination unit 467 assigns a partial evaluation value “1” to the similar spheroid information. . When the center position of the spheroid corresponding to the similar spheroid information is present in the outermost partial area 493c of the medal area 473, the determination unit 467 includes the partial evaluation value “0. 5 ”is given.

  When the determination unit 467 gives a partial evaluation value to each similar spheroid information included in the target feature amount, the determination unit 467 obtains a sum N11 of the given partial evaluation values. Then, the determination unit 467 obtains the evaluation value α using the following Expression 2.

α = N11 / N12 (Formula 2)
Here, N12 represents the sum of partial evaluation values when partial evaluation values are given to each of the plurality of standard ellipse information constituting the standard feature amount in the same manner as described above. For example, in the example of FIG. 59, N12 = 1.5 + 3 × 1 = 4.5.

  In addition, when the characteristic part of the pattern attached | subjected to the said one main surface 410a is located in the surrounding edge part of the one main surface 410a of the regular medal 410, the determination part 467 respond | corresponds to similar rotation ellipse information. As the position of the spheroid is farther from the center 473c of the medal area 473, the partial evaluation value given to the similar spheroid information may be increased. For example, when the center position of the spheroid corresponding to the similar spheroid information is present in the outermost partial area 493c of the medal area 473, the determination unit 467 includes the partial evaluation value “1. 5 ”is given. If the center position of the spheroid corresponding to the similar spheroid information is present in the partial area 493b of the medal area 473, the determination unit 467 assigns a partial evaluation value “1” to the similar spheroid information. . When the center position of the spheroid corresponding to the similar spheroid information is present in the innermost partial region 493a of the medal region 473, the determination unit 467 includes the partial evaluation value “0. 5 ”is given. The weighting method of the partial evaluation value is not limited to this.

  As described above, when the determination unit 467 obtains the evaluation value α, the determination unit 467 performs weighting according to the position of the rotation ellipse corresponding to the similar rotation ellipse information, whereby the accuracy of the true / false determination of the medal 410 shown in the captured image 462B. Is further improved. For example, as described above, when performing weighting according to the position of the spheroid corresponding to the similar spheroid information based on the position of the characteristic part of the pattern on the regular medal 410, in the medal area 473, When the rotation ellipse information relating to the rotation ellipse existing at the position corresponding to the position of the characteristic portion of the pattern on the regular medal 410 is similar to the standard ellipse information, the evaluation value α can be increased. That is, when the local region of the medal region 473 includes a portion similar to the characteristic portion of the pattern on the regular medal 410, the evaluation value α can be increased. If the local area of the medal area 473 includes a part similar to the characteristic part of the pattern of the regular medal 410, it is highly likely that the medal 410 shown in the captured image 462B is legitimate. Therefore, by increasing the evaluation value α in this case, it is possible to more accurately determine that the medal 410 shown in the captured image 462B is correct. Therefore, the accuracy of authenticity determination of the medal 410 shown in the captured image 462B is further improved.

  Note that the determination unit 467 may perform weighting according to the size of the spheroid corresponding to the similar spheroid information when obtaining the evaluation value α. For example, as shown in FIG. 59, among the plurality of standard ellipses 494A1 to 494A4 set in the local area 491A of the medal area 473A in which the regular medal 410 appears, the position of the characteristic part of the pattern on the regular medal 410 When the standard ellipse 494A1 existing at the position corresponding to is larger than the other standard ellipses 494A2 to 494A4, the determination unit 467 gives the similar ellipse information to the similar ellipse information as the ellipse corresponding to the similar ellipse information is larger. Increase the partial evaluation value. As an example, if the size of the spheroid corresponding to the similar spheroid information is larger than the reference size, the determination unit 467 assigns a partial evaluation value “1.5” to the similar spheroid information. If the size of the spheroid corresponding to the similar spheroid information is equal to or smaller than the reference size, the determination unit 467 assigns a partial evaluation value “0.5” to the similar spheroid information.

  Whether or not the size of the spheroid is larger than the reference size can be determined based on the major axis and minor axis length of the spheroid. For example, if the value obtained by multiplying the lengths of the major axis and minor axis of the spheroid is larger than the reference value, it is determined that the size of the spheroid is larger than the reference size. On the other hand, if the value obtained by multiplying the lengths of the major axis and minor axis of the spheroid is equal to or smaller than the reference value, it is determined that the size of the spheroid is equal to or smaller than the reference size.

  As described above, when the determination unit 467 obtains the evaluation value α, weighting is performed according to the size of the spheroid corresponding to the similar spheroid information, and the authenticity determination of the medal 410 shown in the captured image 462B is performed. The accuracy is further improved. For example, as described above, among the standard ellipses obtained from the medal area 473 in which the regular medal 410 is displayed, the standard ellipse existing at the position corresponding to the position of the characteristic portion of the pattern on the regular medal 410. When weighting is performed according to the size of the spheroid corresponding to the similar spheroid information based on the size, the local area of the medal area 473 is similar to the characteristic part of the pattern on the regular medal 410. When the portion is included, the evaluation value α can be increased. Therefore, it is possible to more accurately determine that the medal 410 shown in the captured image 462B is genuine. Therefore, the accuracy of authenticity determination of the medal 410 shown in the captured image 462B is further improved.

  In addition, how to weight the partial evaluation values specifically may be determined by learning. That is, an ellipse fitting result (ellipse fitting result for the regular medal 410) with respect to a plurality of divided areas constituting a local area of the medal area 473 in which the regular medal 410 is displayed, and a medal area 473 in which the non-regular medal 410 is projected. The weighting method may be determined based on the result of ellipse fitting to the plurality of divided regions constituting the local region (ellipse fitting result for the non-regular medal 410).

  For example, in the ellipse fitting result for the non-regular medal 410, an ellipse located at the peripheral edge of the medal area 473 is obtained, but in the elliptical fitting result for the regular medal 410, the ellipse fitting result is positioned at the peripheral edge of the medal area 473. Let us consider a case where an ellipse is not obtained. In this case, when the position of the spheroid corresponding to the similar spheroid information is present at the peripheral edge of the medal area 473, the determination unit 467 compares the spheroid with the similar spheroid as compared with the case where the spheroid exists in the other part. Reduce the partial evaluation value given to the spheroid information.

  Further, for example, a case where a large ellipse is obtained in the ellipse fitting result for the non-regular medal 410 but a large ellipse is not obtained in the ellipse fitting result for the regular medal 410 will be considered. In this case, when the size of the spheroid corresponding to the similar spheroid information is larger than the reference size, the determination unit 467 is a part to be given to the similar spheroid information as compared to the case of the reference size or less. Decrease the evaluation value.

  Thus, the accuracy of the true / false determination of the medal 410 shown in the captured image 462B is further improved by determining the weighting method by learning.

[Modification 3]
In the above example, the ellipse information (rotation ellipse information) used by the determination unit 467 includes the position information and shape information of the ellipse (rotation ellipse), but either one of the position information and shape information of the ellipse is included. May only be included. The ellipse information may include ellipse tilt information. That is, the ellipse information used by the determination unit 467 may include at least one of ellipse position information, shape information, and tilt information.

  The fitting unit 466 can generate the inclination information of the ellipse to be fitted to the local area based on the positions of a plurality of pixels constituting the local area included in the medal area 473. Specifically, the fitting unit 466 uses the x coordinate and y coordinate of a plurality of pixels constituting the local area to obtain a covariance matrix for the x coordinate and y coordinate of the pixel in the local area. . Then, the fitting unit 466 obtains two eigenvectors for the obtained covariance matrix. One of the two eigenvectors indicates the direction in which the major axis of the ellipse extends, and the other of the two eigenvectors indicates the direction in which the minor axis of the ellipse extends. Therefore, it can be said that each of the two eigenvectors indicates the inclination of the ellipse. The fitting unit 466 uses one of the two eigenvectors for the covariance matrix as inclination information of an ellipse to be fitted to the local region.

  When only the center position of the rotation ellipse is included in the rotation ellipse information, the determination unit 467 determines the center position of the rotation ellipse included in the rotation ellipse information and the standard included in the standard ellipse information in step S22 described above. When the distance from the center position of the ellipse is a predetermined value or less, it is determined that the rotation ellipse information and the standard ellipse information are similar.

  When the spheroid information includes only the major axis length and minor axis length of the spheroid information, the determination unit 467 determines the major axis of the spheroid included in the spheroid information in step S22 described above. And the absolute value of the difference between the major axis length of the standard ellipse included in the standard ellipse information is less than or equal to a predetermined value, and the minor axis length of the rotating ellipse and the minor axis length of the standard ellipse When the absolute value of the difference is less than or equal to a predetermined value, it is determined that the rotation ellipse information and the standard ellipse information are similar.

  When only the center position and eigenvector of the spheroid are included in the spheroid information, the determination unit 467 includes the center position of the spheroid included in the spheroid information and the standard ellipse information in step S22 described above. Rotation when the distance from the center position of the standard ellipse is less than a predetermined value and the angle formed by the eigenvector included in the rotation ellipse information and the eigenvector included in the standard ellipse information is less than the predetermined value. It is determined that the ellipse information and the standard ellipse information are similar.

  If the spheroid information includes only the major axis length, minor axis length, and eigenvector of the spheroid, the determination unit 467 determines the spheroid included in the spheroid information in step S22 described above. The absolute value of the difference between the length of the major axis and the major axis of the standard ellipse included in the standard ellipse information is less than or equal to the predetermined value, and the minor axis length of the rotating ellipse and the minor axis length of the standard ellipse If the absolute value of the difference from the length is less than or equal to a predetermined value and the angle formed by the eigenvector included in the spheroid information and the eigenvector included in the standard ellipse information is less than or equal to the predetermined value, the spheroid information And the standard ellipse information are determined to be similar.

  Then, when the rotation ellipse information includes the center position of the rotation ellipse, the length of the long axis, the length of the short axis, and the eigenvector, the determination unit 467 includes the rotation ellipse information in the above-described step S22. The distance between the center position of the spheroid and the center position of the standard ellipse included in the standard ellipse information is less than or equal to a predetermined value, and the major axis length of the spheroid and the major axis length of the standard ellipse The absolute value of the difference is less than or equal to a predetermined value, and the absolute value of the difference between the minor axis length of the spheroid and the minor axis length of the standard ellipse is less than or equal to a prescribed value and is included in the spheroid information When the angle formed by the eigenvector and the eigenvector included in the standard ellipse information is equal to or smaller than a predetermined value, it is determined that the rotation ellipse information and the standard ellipse information are similar.

<< Fourth Embodiment >>
Hereinafter, a pachislot machine that is a gaming machine according to a fourth embodiment of the present invention will be described with reference to FIGS. Note that the pachislot machine 500, which is a gaming machine according to the fourth embodiment of the present invention, has the functional flow, the pachislot structure, the medal selector structure, the pachislot circuit structure, and the medal selector circuit structure described above in the first embodiment. It is the same as the pachislot machine 1 that is a gaming machine according to the above. Below, the regular medal discrimination process executed by the pachislot machine 500 that is a gaming machine according to the fourth embodiment will be described.

  As described above, the pachislot machine 500 that is a gaming machine according to the fourth embodiment includes the control LSI 534 (corresponding to the control LSI 234 of the gaming machine according to the first embodiment), similarly to the gaming machine according to the first embodiment. A camera unit 509 (corresponding to the camera unit 209 of the gaming machine according to the first embodiment) is provided, and further, a medal selector 501 including the camera unit 509 (corresponding to the medal selector 201 of the gaming machine according to the first embodiment) is provided. . FIG. 61 is a functional block diagram of such a camera unit 509.

  As illustrated in FIG. 61, the camera unit 509 according to the present embodiment includes an imaging unit 561, a conversion unit 563, an extraction unit 564, an area division unit 565, a feature amount acquisition unit 566, a determination unit 567, and an input / output unit 568. It has. Note that the camera unit 509 includes a light emitting unit made of an LED or the like, but is not shown in FIG.

  The image capturing unit 561 includes a CMOS image sensor 532 (for example, corresponding to the CMOS image sensor 232 of the gaming machine according to the first embodiment), and image data captured by the CMOS image sensor 532 (predetermined if necessary) (Converted) and output as a captured image 562A.

  The conversion unit 563 (for example, corresponding to the ISP circuit 245 of the gaming machine according to the first embodiment) converts the captured image 562A input from the imaging unit 561 from a color image to a grayscale image, and converts the converted captured image to It outputs as a captured image 562B.

  The extraction unit 564 (for example, corresponding to the image recognition accelerator circuit 249 of the gaming machine according to the first embodiment) extracts a medal area (object area) 573 in which the medal 510 is captured from the captured image 562B.

  The area dividing unit 565 (for example, corresponding to the image recognition DSP circuit 242 of the gaming machine according to the first embodiment) performs area division on the medal area 573 extracted by the extracting unit 564. Here, the area division is a process of dividing the medal area 573 into a plurality of divided areas each having a uniform luminance. In other words, the area division is a process of dividing the medal area 573 into a plurality of divided areas each having a uniform feature.

  The feature amount acquisition unit 566 (for example, corresponding to the image recognition DSP circuit 242 of the gaming machine according to the first embodiment) is included in the captured image 562B based on the plurality of divided regions generated by the region dividing unit 565. A feature amount indicating the feature of the image of the medal 510 is acquired.

  The determination unit 567 (for example, corresponding to the image recognition DSP circuit 242 of the gaming machine according to the first embodiment) is based on the feature amount acquired by the feature amount acquisition unit 566, and the medal 510 shown in the captured image 562B is normal. The determination result 569 is output via the input / output unit 568 (for example, corresponding to the GPIO 250 of the gaming machine according to the first embodiment). In other words, the determination unit 567 determines whether the medal 510 shown in the captured image 562A is genuine based on the feature amount acquired by the feature amount acquisition unit 566, and outputs the determination result 569. In the present embodiment, the determination unit 567 compares the feature amount obtained from the captured image 562B with the standard feature amount (reference feature amount) 567A indicating the feature of the regular medal 510, and based on the comparison result, It is determined whether or not the medal 510 shown in the captured image 562B is genuine. The standard feature quantity 567A can be stored in, for example, an SRAM (corresponding to the SRAM 243 of the camera unit 209 according to the first embodiment).

  FIG. 62 is a diagram schematically illustrating an example of a captured image 562A obtained by the imaging unit 561. The captured image 562A illustrated in FIG. 62 includes the captured image of the medal 510. In addition, a medal rail 511 as a background is captured in the captured image 562A. The medal rail 511 corresponds to the medal rail 210 of the first embodiment described above, but here, the shape of the rail is shown in a simplified manner.

  On one main surface 510a of the medal 510, for example, a pattern of alphabet “A” is shown. This shows a pattern of a regular medal, but other patterns may be used. Moreover, a pattern may be attached | subjected to both the main surfaces of a regular medal.

  In this embodiment, the medal 510 moves on the medal rail 511 while rotating around a rotation axis along the thickness direction passing through the centers of both main surfaces. Then, the imaging unit 561 images the medal 510 from the one main surface 510a side of the medal 510. Therefore, the captured image 562A includes an image of the one main surface 510a of the medal 510. In the present embodiment, the captured image 562A generated by the imaging unit 561 is a color image, but may be a grayscale image.

<Flow of regular medal discrimination processing>
Next, a series of operations of the regular medal discrimination process performed by the camera unit 509 in the present embodiment will be described.

  First, when a captured image 562A is input from the imaging unit 561, the conversion unit 563 converts the captured image 562A from a color image to a grayscale image, and the captured image 562B obtained thereby is set as a processing target.

  Next, the extraction unit 564 extracts a medal area 573 in which the medal 510 appears from the captured image 562B that is the processing target. Thereafter, the region dividing unit 565 performs region division on the medal region 573 extracted by the extracting unit 564. Next, the feature amount acquisition unit 566 acquires a feature amount indicating the feature of the medal 510 shown in the captured image 562B based on the plurality of divided regions generated by the region dividing unit 565.

  Next, the determination unit 567 determines whether the medal 510 shown in the captured image 562B is genuine based on the feature amount acquired by the feature amount acquisition unit 566. Then, the determination unit 567 sends the determination result 569 to the main control circuit (corresponding to the main control circuit 91 in the gaming machine of the first embodiment) via the input / output unit 568 (corresponding to the GPIO 250 of the first embodiment). Output. In this way, when the medal 410 shown in the captured image 462A is not a regular one, the main control circuit forcibly interrupts the game in the same manner as the gaming machine of the first embodiment, and the sub control circuit (first Via the sub-control circuit 101 in the gaming machine of the embodiment, it can be notified that there has been an illegal act. For example, it is possible to issue a warning to the outside by outputting a warning sound from a speaker or displaying warning information on a display which is a liquid crystal display device.

  Thereafter, when a new captured image 562A is input, the determination unit 567 performs the above-described regular medal selection process using the captured image 562B obtained from the captured image 562A as a new processing target. Thereafter, the determination unit 567 performs the same operation every time the captured image 562A is input.

<Detailed description of each component>
Hereinafter, operations of the extraction unit 564, the region division unit 565, the feature amount acquisition unit 566, and the determination unit 567 will be described in more detail.

[Extractor]
FIG. 63 is a diagram schematically illustrating an example of the medal area 573 extracted by the extraction unit 564 from the captured image 562B. There are various methods for extracting the medal area 573 from the captured image 562B.

  For example, there is a first extraction method that utilizes the fact that the outer shape of the medal 510 is circular. In the first extraction method, first, edge detection is performed on the captured image 562B to generate an edge image. As an edge image generation method, for example, Sobel method, Laplacian method, Canny method and the like are used. Next, a circular area is extracted from the generated edge image. For example, Hough transform is used as a method for extracting a circular region. Then, a circular area in the captured image 562B existing at the same position as the position of the circular area in the edge image is set as a medal area 573.

  As another method, there is a second extraction method for extracting the medal region 573 from the captured image 562B using the background difference method and labeling. In the second extraction method, first, a background difference image indicating a difference between the captured image 562B and a background image (an image showing only the background of the captured image 562B) is generated, and the generated background difference image is binarized. The Then, labeling such as 4-connection is performed on the binary background difference image. In the binary background difference image, a partial area in the captured image 562B that exists at the same position as the position of the connected area (independent area) obtained as a result of labeling is set as the medal area 573.

  In the present embodiment, the extraction unit 564 extracts the medal area 573 from the captured image 562B by a method different from the above two methods. The operation of the extraction unit 564 according to this embodiment will be described below. Note that the extraction unit 564 may extract the medal region 573 from the captured image 562B using either one of the two methods described above.

  First, the extraction unit 564 generates a background difference image indicating a difference between the captured image 562B and the background image 575 (an image showing only the background of the captured image 562B), and binarizes the generated background difference image. 64 is a diagram schematically showing the background image 575, and FIG. 65 is a diagram schematically showing the binary background difference image 576. Note that in the binary image schematically shown in FIG. 65 and in the drawings described later in the present embodiment, the region having the pixel value “1” (high luminance region) is shown in black and the pixel value is “0”. This region (low luminance region) is shown in white. The background image 575 can be stored in, for example, an SRAM (corresponding to the SRAM 243 of the camera unit 209 according to the first embodiment).

  Next, the extraction unit 564 performs template matching on the binary background difference image 576 using a binary outline template 577 indicating the outline of the medal 510. That is, the extraction unit 564 identifies where in the background difference image 576 a region similar to the outline template 577 exists. In other words, the extraction unit 564 identifies where in the background difference image 576 there is an area that matches the outline of the medal 510 indicated by the outline template 577. FIG. 66 is a diagram schematically showing an outer shape template 577. The outline template 577 can be stored in, for example, an SRAM (corresponding to the SRAM 243 of the camera unit 209 according to the first embodiment). The external shape of the external shape template 577 is, for example, a square.

  In template matching, the extraction unit 564 moves the outline template 577 little by little (for example, one pixel (pixel) at a time) in the raster scan direction on the background difference image 576 as shown in FIG. In other words, the extraction unit 564 raster scans the outline template 577 on the background difference image 576. At this time, the extraction unit 564 generates an AND image of the outline template 577 and the partial region of the background difference image 576 that overlaps the outline template 577 at each position of the outline template 577. Thereby, a plurality of binary AND images are generated. The extraction unit 564 then extracts the background difference image 576 of the outer shape template 577 used in generating the AND image having the largest number of pixels (high luminance pixels) having the pixel value “1” among the plurality of generated AND images. Identify the top position. This position is a position where an area similar to the outline template 577 exists in the background difference image 576.

  Then, as illustrated in FIG. 68, the extraction unit 564 extracts a partial area 578 in the captured image 562B that exists at the same position as the identified position as a medal area 573. In other words, the extraction unit 564 extracts, as the medal area 573, the partial area 578 in the captured image 562B that overlaps the external shape template 577 when the external shape template 577 is arranged in the captured image 562B at the same position as the specified position. . At this time, in the partial area 578, a medal area 573 may be obtained by setting the pixel value of each pixel outside the circle indicated by the outer shape template 577 on the partial area 578 to zero. The medal area 573 extracted by the extraction unit 564 is a gray scale image. In this embodiment, the outer shape of the medal area 573 is a square, but may be another shape such as a circle.

[Area Division]
In the present embodiment, the area dividing unit 565 performs area division on the medal area 573 using the entropy of the luminance histogram. The area dividing unit 565 repeatedly performs a process of further dividing the divided area into a plurality of divided areas when the entropy of the luminance histogram in the divided area of the medal area 573 is equal to or greater than the threshold value.

  FIG. 69 is a flowchart showing the operation of the area dividing unit 565. As shown in FIG. 69, in step S31, the region dividing unit 565 determines a threshold value used in region division. Specifically, the area dividing unit 565 obtains a luminance histogram for the entire medal area 573. Then, the area dividing unit 565 obtains the entropy of the obtained luminance histogram. Then, the region dividing unit 565 determines a threshold value based on the obtained entropy.

  FIG. 70A is a diagram showing an example of a luminance histogram 590 in the entire medal area 573. A luminance histogram 590 shows the luminance distribution of a plurality of pixels constituting the medal area 573. The horizontal axis in FIG. 70A indicates the luminance. The vertical axis in FIG. 70A indicates the number of pixels having the luminance shown on the horizontal axis, that is, the frequency, in the medal area 573. In the present embodiment, the luminance of the pixel is expressed by 8 bits, for example, and takes a value from “0” to “255” in decimal notation.

  The area dividing unit 565 obtains the entropy EA of the luminance histogram 590 using Equation 3 shown in FIG. 70B.

Here, PAi in Expression 3 indicates the appearance probability of the luminance “i” in the medal area 573. The appearance probability PAi is expressed by the following Expression 4 using the number KAi of pixels having the luminance “i” in the medal area 573 and the total number KAtotal of the pixels in the medal area 573.
PAi = KAi / KAtotal (Formula 4)

  For example, assuming that KAtotal = 1000 and the number of pixels with luminance “255” in the medal area 573 KA255 = 10, PA255 = 10/1000.

  Entropy EA indicates the degree of variation in the distribution of luminance histogram 590. When the entropy EA is large, it can be said that the distribution of the luminance histogram 590 varies. That is, it can be said that the variation in luminance in the medal area 573 is large. On the other hand, when the entropy EA is small, it can be said that the distribution of the luminance histogram 590 is biased. That is, it can be said that the variation in luminance in the medal area 573 is small.

When obtaining the entropy EA, the area dividing unit 565 obtains a threshold value T used in the area division using the following Expression 5.
T = EA × α (Formula 5)

  Here, α in Expression 5 is an adjustment parameter for adjusting the division mode of the medal area 573, and 0 <α <1. As α decreases, the threshold value T decreases, so that the medal area 573 is easily divided in the area division. Moreover, the value of α can be stored in, for example, an SRAM (corresponding to the SRAM 243 of the camera unit 209 according to the first embodiment). In the present embodiment, the value of α is determined in advance by experiments or the like so that the authenticity of the medal 510 can be appropriately determined.

  After determining the threshold value T in step S31, the area dividing unit 565 initially divides the medal area 573 in step S32. Here, the medal area 573 is divided into four as shown in FIG. 71, for example. In the present embodiment, as shown in FIG. 71, the medal area 573 is equally divided into four square divided areas 580 in a matrix. The area dividing unit 565 does not use the entropy of the luminance histogram when initially dividing the medal area 573.

  Next, in step S <b> 33, the area dividing unit 565 determines a divided area 580 to be processed. In step S33 immediately after step S32, the respective divided areas 580 obtained in step S32 are processed.

  Next, in step S34, the area dividing unit 565 obtains entropy of the luminance histogram for each of the divided areas 580 to be processed determined in step S33. Specifically, the area dividing unit 565 first obtains a luminance histogram of the divided area 580 to be processed. The luminance histogram of the divided region 580 indicates, for example, the luminance distribution of the plurality of pixels that form the divided region 580 illustrated in FIG. 72A. Then, the region dividing unit 565 obtains the entropy EB of the luminance histogram of the processing target divided region 580 using Expression 6 shown in FIG. 72B.

Here, PBi in Expression 6 indicates the appearance probability of the luminance “i” in the divided region 580. The appearance probability PBi is expressed by the following Expression 7 using the number KBi of pixels having luminance “i” in the divided region 580 and the total number KBtotal of pixels in the divided region 580.
PBi = KBi / KBtotal (Expression 7)

  When the entropy EB for the divided region 580 is large, it can be said that the variation in luminance in the divided region 580 is large. On the other hand, when the entropy EB for the divided region 580 is small, it can be said that the variation in luminance in the divided region 580 is small.

  When step S34 is executed, in step S35, the region dividing unit 565 includes a processing target divided region 580 having an entropy EB equal to or greater than the threshold T in the processing target divided region 580 determined in step S33. It is determined whether or not. If the region dividing unit 565 determines in step S35 that there is a processing target divided region 580 having an entropy EB equal to or greater than the threshold value T, in step S36, the region dividing unit 580 having an entropy EB equal to or greater than the threshold value T is determined. Is further divided. As described above, when the entropy EB for the divided region 580 is large, it can be said that the variation in luminance in the divided region 580 is large. Therefore, the region dividing unit 565 causes the divided region to be processed to have a large variation in luminance. It can be said that 580 is further divided. In other words, the region dividing unit 565 further divides the divided region 580 to be processed whose features are not uniform. In step S36, as in step S32, the processing target divided region 580 having an entropy EB equal to or greater than the threshold value T is further equally divided into four square divided regions 581 in a matrix. FIG. 72A is a diagram showing a state in which the upper left divided region 580 among the four divided regions 580 obtained by the initial division in step S32 is further divided into four divided regions 581. FIG.

  When step S36 is executed, the area dividing unit 565 executes step S33 again to newly determine the division area 581 to be processed. In step S33 immediately after step S36, a new divided area 581 obtained in step S36, which is larger than a predetermined size, is a processing target. Thereafter, the area dividing unit 565 similarly executes step S34 and subsequent steps.

  In step S <b> 35, if the area dividing unit 565 determines that there is no divided area 581 to be processed whose entropy EB is equal to or greater than the threshold value T, the area dividing for the medal area 573 is ended.

  As described above, in the present embodiment, the region dividing unit 565 further adds a plurality of divided regions when the entropy EB of the luminance histogram in the divided regions (for example, the divided region 580 and the divided region 581) is equal to or greater than the threshold value. In order to repeatedly perform the process of dividing into divided areas, the medal area 573 is divided into a plurality of divided areas each having a small entropy EB (for example, in the example of FIG. 71, the medal area 573 is divided into four divided areas 580). In the example of FIG. 72A, the divided area 580 is divided into four divided areas 581). That is, the medal area 573 is divided into a plurality of divided areas each having a uniform luminance.

  FIG. 73 is a diagram showing an outline of a state in which the medal area 573 is divided into areas, and the medal area 573 is divided into a plurality of divided areas 582 having uniform brightness. In FIG. 73, the divided area is shown as a divided area 582 regardless of the size (that is, regardless of how many times the area has been divided). In the medal area 573, the luminance varies in the area including the outline of the pattern of the medal 510. Therefore, as shown in FIG. 73, the area around the outline of the pattern of the medal 510 is finely divided in the medal area 573. Similarly, in the medal area 573, since the luminance varies in the area including the outer shape of the medal 510, in the medal area 573, the vicinity of the outer shape of the medal 510 is finely divided as shown in FIG.

  As described above, when the entropy EB of the luminance histogram in the divided area is equal to or greater than the threshold value, the medal area 573 performs the process of further dividing the divided area into a plurality of divided areas. The outline of the pattern is finely divided. Therefore, it can be said that the plurality of divided areas 582 generated by performing the area division on the medal area 573 indicate the characteristics of the medal 510. Hereinafter, the divided area 582 may be referred to as a “uniform divided area 582”.

  In the above example, when the entropy EB of the luminance histogram in the divided area is equal to or greater than the threshold value, the divided area is further divided into a plurality of divided areas. However, the entropy EB of the luminance histogram in the divided area. Is larger than the threshold value, the divided area may be further divided into a plurality of divided areas. In the above example, the divided area is divided into four. However, the number of divided areas may be other than this.

[Feature acquisition unit]
In the present embodiment, the feature amount acquisition unit 566 includes size information indicating the size of the uniform divided region 582 and the medal region 573 for each of the plurality of uniform divided regions 582 generated by the region dividing unit 565. Distance information indicating the distance from the center to the uniform divided region 582 is acquired. Then, the feature amount acquisition unit 566 acquires medal feature amounts based on the size information and the distance information for each uniform divided region 582. In the present embodiment, the feature amount acquisition unit 566 generates a two-dimensional histogram of size information and distance information for the uniform divided region 582, and uses the two-dimensional histogram as a medal feature amount.

  As the size information of the uniform divided region 582, for example, the horizontal or vertical length of the uniform divided region 582 is employed. In the present embodiment, since the uniform divided region 582 is a square, the length of the uniform divided region 582 in the horizontal direction and the vertical direction is the same. Further, as the distance information for the uniform divided area 582, for example, the distance from the center of the medal area 573 to the center of the uniform divided area 582 is employed. As the size information of the uniform divided region 582, the length of the diagonal line of the uniform divided region 582 may be employed.

  For each uniform divided region 582, the feature quantity acquisition unit 566 uses, for example, SRAM (camera unit according to the first embodiment) as a pair of information including size information and distance information of the uniform divided region 582. 209 corresponding to SRAM 243). Then, the feature amount acquisition unit 566, based on the plurality of sets of information pairs respectively corresponding to the plurality of uniform divided regions 582 generated by the region dividing unit 565, the frequency distribution for the combination of the size information and the distance information Is generated. Hereinafter, the two-dimensional histogram may be referred to as a “two-dimensional evaluation value histogram 591”.

  FIG. 74 is a diagram showing an example of a two-dimensional evaluation value histogram 591. The first axis along the x-axis direction in FIG. 74 indicates size information, and the second axis along the y-axis direction in FIG. 74 indicates distance information. The third axis along the z-axis direction in FIG. 74 is the size information having the value indicated by the first axis and the distance information having the value indicated by the second axis in a plurality of information pairs. The frequency of combination with is shown. That is, the third axis in FIG. 74 shows how many combinations of the size information having the value shown on the first axis and the distance information having the value shown on the second axis in a plurality of information pairs. Indicates whether it exists.

  For example, if there are eight combinations of size information a1 and distance information b1 in a plurality of information pairs, the size information a1 shown on the first axis and the distance information b1 shown on the second axis The frequency in the corresponding bin is “8”. In addition, when there are three combinations of the size information a5 and the distance information b3 in a plurality of information pairs, the size information a5 shown on the first axis and the distance information b3 shown on the second axis The frequency in the corresponding bin is “3”.

  As described above, in this embodiment, the two-dimensional evaluation value histogram 591 of the size information and the distance information of the uniform divided region 582 in the medal region 573 is used as the medal feature amount.

[Determining part]
The determination unit 567 compares the medal feature amount acquired by the feature amount acquisition unit 566 with the standard feature amount indicating the feature of the regular medal 510, and based on the comparison result, the medal 510 reflected in the captured image 562B is obtained. Judge whether it is regular or not. As the standard feature amount, the two-dimensional evaluation value histogram 591 is used from the captured image 562B in which the regular medal 510 is shown in the same manner as described above. Hereinafter, the two-dimensional evaluation value histogram 591 generated from the captured image 562B showing the regular medal 510 is referred to as “standard two-dimensional evaluation value histogram 591A”.

  When the gaming machine is not in actual operation, a regular medal 510 is inserted into the gaming machine in order to obtain a standard two-dimensional evaluation value histogram 591A (standard feature value). In the conversion unit 563, a captured image 562B showing the inserted regular medal 510 is generated. This captured image 562B is referred to as a “standard captured image 562C”. The extraction unit 564 generates a medal area 573 in which the regular medal 510 is shown from the standard captured image 562C, and the area dividing unit 565 performs area division on the medal area 573. Then, the feature amount acquisition unit 566 generates a standard two-dimensional evaluation value histogram 591A (standard feature amount) based on the plurality of uniform divided regions 582 generated by the region dividing unit 565. The standard two-dimensional evaluation value histogram 591A generated in this way can be stored in, for example, an SRAM (corresponding to the SRAM 243 of the camera unit 209 according to the first embodiment).

  Note that the acquisition of the standard two-dimensional evaluation value histogram 591A by such a gaming machine can be performed when a predetermined mode is selected in the gaming machine. Further, the standard two-dimensional evaluation value histogram 591A may be acquired in advance by a gaming machine or other device and stored in the SRAM or the like of each gaming machine.

  On the other hand, in a game machine in operation, the determination unit 567 compares the two-dimensional evaluation value histogram 591 generated by the feature amount acquisition unit 566 with the standard two-dimensional evaluation value histogram 591A stored in the SRAM or the like, Based on the comparison result, it is determined whether or not the medal 510 shown in the captured image 562B is genuine. In the present embodiment, the determination unit 567 compares the two-dimensional evaluation value histogram 591 generated by the feature amount acquisition unit 566 and the standard two-dimensional evaluation value histogram 591A, thereby comparing the two. As the value indicating the similarity, for example, a Bhattacharyya distance is used. A large Bhattacharyya distance means a low similarity, and a small Bhattacharyya distance means a high similarity. Other values may be used as values indicating the degree of similarity.

  Here, when the similarity between the two-dimensional evaluation value histogram 591 generated from the captured image 562B and the standard two-dimensional evaluation value histogram 591A is high, the medal 510 shown in the captured image 562B is a regular medal. Probability is high. Therefore, like the Bhattacharyya distance, the value indicating the similarity between the two-dimensional evaluation value histogram 591 generated from the captured image 562B and the standard two-dimensional evaluation value histogram 591A is the normal value of the medal 510 shown in the captured image 562B. It can be said that it is an evaluation value indicating the certainty of being. In other words, it can be said that the value indicating the similarity is an evaluation value indicating the possibility that the medal 510 shown in the captured image 562B is genuine. Hereinafter, the evaluation value is referred to as “determination evaluation value”.

  In the present embodiment, when the similarity between the two-dimensional evaluation value histogram 591 generated by the feature amount acquisition unit 566 and the standard two-dimensional evaluation value histogram 591A is high, the determination unit 567 displays the captured image 562B. When it is determined that the medal 510 to be shown is genuine and the similarity is low, it is determined that the medal 510 shown in the captured image 562B is not legitimate. Specifically, the determination unit 567 determines that the Bhattacharyya distance between the two-dimensional evaluation value histogram 591 generated by the feature amount acquisition unit 566 and the standard two-dimensional evaluation value histogram 591A is equal to or smaller than a threshold value. Then, it is determined that the medal 510 shown in the captured image 562B is genuine, and if it is larger than the threshold, it is determined that the medal 510 shown in the captured image 562B is not regular. In other words, the determination unit 567 determines that the determination evaluation value generated based on the two-dimensional evaluation value histogram 591 obtained from the captured image 562B and the standard two-dimensional evaluation value histogram 591A is equal to or less than the threshold value. Then, it is determined that the medal 510 shown in the captured image 562B is genuine, and if it is larger than the threshold, it is determined that the medal 510 shown in the captured image 562B is not regular. Then, the determination unit 567 outputs a determination result 569.

  As described above, in the present embodiment, the threshold value T used when dividing the medal area 573 is determined based on the medal area 573. Therefore, the medal area 573 in which the medal 510 is shown can be appropriately divided into a plurality of uniform divided areas 582 according to the medal 510. Therefore, compared to the case where the threshold value T is determined in advance, a medal feature amount that appropriately indicates the feature of the medal 510 shown in the medal area 573 can be acquired. As a result, the determination accuracy when determining whether or not the medal 510 is genuine is improved.

  In this embodiment, when medal feature amounts are acquired based on a plurality of uniform divided areas 582, size information and distance information about the uniform divided areas 582 are used. Therefore, the medal feature value can be easily obtained as compared with the case where the medal feature value is obtained by using the pixel value of each pixel of the uniform divided region 582. Therefore, it is possible to easily determine whether or not the medal 510 shown in the captured image 562B is genuine.

  In the present embodiment, since the captured image 562B is a captured image obtained by capturing the rotating medal 510, the rotation posture (rotation angle) of the medal 510 reflected in the captured image 562B is always the same. Not always. Therefore, the rotation posture of the medal 510 shown in the medal area 573 is not always the same. On the other hand, the size information and the distance information of the uniform divided area 582 obtained from the medal area 573 are information that does not change even if the uniform divided area 582 rotates around the center of the medal area 573. Therefore, even if the rotation posture of the medal 510 shown in the medal area 573 varies, the size information and the distance information of the uniform divided area 582 obtained from the medal area 573 vary as long as the medal 510 is genuine. Hateful. Therefore, it can be said that each of the size information and the distance information of the uniform divided region 582 is information that is not easily influenced by the rotation posture of the medal 510 shown in the captured image 562B. In the present embodiment, since the medal feature amount is acquired based on information that is not easily influenced by the rotation posture of the medal 510 shown in the captured image 562B, the captured image 562B is obtained by capturing the rotating medal 510. Even when the captured image is a captured image, it is possible to prevent the regular medal 510 shown in the captured image 562B from being erroneously determined as not being a regular one.

<Modification of Fourth Embodiment>
Various modifications of the present embodiment will be described below.

[Modification 1 (Medal Feature Amount Acquisition Method)]
In the above example, the feature amount acquisition unit 566 has acquired the medal feature amount based on both the size information of the uniform divided region 582 and the distance information, but the size information of the uniform divided region 582, The medal feature amount may be acquired based on one of the distance information and the distance information. For example, the feature amount acquisition unit 566 may acquire the medal feature amount based on the size information of the plurality of uniform divided regions 582 generated by the region dividing unit 565. In this case, for example, the feature amount acquisition unit 566 generates a one-dimensional histogram 592 indicating the distribution of size information of the plurality of uniform divided regions 582 generated by the region dividing unit 565, and uses the one-dimensional histogram 592 as a medal. The feature value. FIG. 75 is a diagram showing an example of a one-dimensional histogram 592 showing the distribution of size information of the uniform divided region 582. As shown in FIG. The horizontal axis in FIG. 75 indicates size information. The vertical axis in FIG. 75 indicates the number of uniform divided areas 582 having the size information indicated on the horizontal axis, that is, the frequency, in the plurality of uniform divided areas 582 generated by the area dividing unit 565.

  When the one-dimensional histogram 592 indicating the distribution of the size information of the uniform divided region 582 is used as the medal feature amount, the feature amount acquisition unit 566 causes the regular medal 510 to be used when the gaming machine is not actually operating. A one-dimensional histogram (standard one-dimensional histogram 592A) of the size information of the uniform divided region 582, which is generated in the same manner from the captured image 562B in which is shown, is set as the standard feature amount. Then, as in the case where the two-dimensional evaluation value histogram 591 is used, the determination unit 567 compares the one-dimensional histogram 592 generated by the feature amount acquisition unit 566 with the standard one-dimensional histogram 592A, and the comparison result Based on the above, it is determined whether or not the medal 510 shown in the captured image 562B is genuine.

  Note that the generation of the standard one-dimensional histogram 592A by such a gaming machine can be performed when a predetermined mode is selected in the gaming machine. Further, a standard one-dimensional histogram 592A may be generated in advance by a gaming machine or other device and stored in the SRAM or the like of each gaming machine.

  In addition, when the feature amount acquisition unit 566 acquires medal feature amounts based on the distance information of the plurality of uniform division regions 582 generated by the region division unit 565, the distance between the plurality of uniform division regions 582 is obtained. A one-dimensional histogram 592 indicating the information distribution is generated, and the one-dimensional histogram 592 is used as the medal feature amount.

  As described above, even if the medal feature amount is acquired based on one of the size information and the distance information of the uniform divided region 582, the pixel value of each pixel of the uniform divided region 582 is obtained. Compared to the case where the medal feature amount is acquired based on the medals, the medal feature amount can be easily acquired. Therefore, it is possible to easily determine whether or not the medal 510 shown in the captured image 562B is genuine.

  In addition, since each of the size information and the distance information of the uniform divided region 582 is information that is not easily influenced by the rotation posture of the medal 510 shown in the captured image 562B, also in the present modified example, the captured image 562B is displayed. It is possible to suppress erroneous determination that the regular medal 510 shown is not legitimate.

[Modification 2 (Authentication determination using multiple types of standard feature)]
As described above, the size information and the distance information of the uniform divided region 582 are information that is not easily influenced by the rotation posture of the medal 510 displayed in the medal region 573, but the rotation posture of the medal 510 displayed in the medal region 573. It varies somewhat under the influence of. This point will be described in detail below.

  For example, consider four medal areas 573A to 573D in which a regular medal 510 appears as shown in FIG. In the following description, it is assumed that the medal feature value obtained from the medal area 573A is stored in the SRAM or the like as the standard feature value. Hereinafter, the plurality of uniform divided areas 582 obtained from the medal area 573A may be referred to as “a plurality of standard uniform divided areas 582A”.

  The rotation angle of the medal 510B shown in the medal area 573B is the same as the rotation angle of the medal 510A when the medal 510A shown in the medal area 573A is rotated 90 ° counterclockwise around its center. The rotation angle of the medal 510C shown in the medal area 573C is the same as the rotation angle of the medal 510A when the medal 510A shown in the medal area 573A is rotated 180 ° counterclockwise around its center. The rotation angle of the medal 510D shown in the medal area 573D is the same as the rotation angle of the medal 510A when the medal 510A shown in the medal area 573A is rotated 270 ° counterclockwise around its center.

  In the above example, when the divided area of the medal area 573 is further divided, it is equally divided into four square divided areas in a matrix. Therefore, in the plurality of uniform divided areas 582 obtained from the medal area 573B, the plurality of standard uniform divided areas 582A obtained from the medal area 573A are rotated 90 ° counterclockwise around the center of the medal area 573A. Match the one. Similarly, the plurality of uniform divided areas 582 obtained from the medal area 573C coincides with the plurality of standard uniform divided areas 582A rotated counterclockwise by 180 ° around the center of the medal area 573A. The plurality of uniform divided areas 582 obtained from the medal area 573D coincides with the plurality of standard uniform divided areas 582A rotated about 270 ° counterclockwise around the center of the medal area 573A. Accordingly, the size information and distance information of the plurality of standard uniform divided areas 582A, the size information and distance information of the plurality of uniform divided areas 582 obtained from the medal area 573B, and the plurality of pieces of information obtained from the medal area 573C. The size information and distance information of the uniform division region 582 of the same, and the size information and distance information of the plurality of uniform division regions 582 obtained from the medal region 573D coincide with each other. Therefore, the medal feature quantity obtained from the medal area 573B, the medal feature quantity obtained from the medal area 573C, and the medal feature quantity obtained from the medal area 573D are the medal feature quantity obtained from the medal area 573A, That is, it matches the standard feature amount.

  In this way, the rotation angle of the regular medal 510 reflected in a certain medal area 573X is such that the regular medal 510A reflected in the medal area 573A from which the standard feature amount is acquired is (90 × N) ° (N is (An integer greater than or equal to 0) When the rotation angle of the regular medal 510A when rotated counterclockwise is the same, the plurality of uniform division regions 582 obtained from the medal region 573X is a plurality of standard uniform divisions. The region 582A coincides with the rotation of (90 × N) ° counterclockwise around the center of the medal region 573A. Therefore, the medal feature value obtained from the medal area 573X matches the medal feature value obtained from the medal area 573A. That is, the medal feature value obtained from the medal area 573X matches the standard feature value stored in the SRAM or the like. Therefore, it is possible to appropriately determine that the medal 510 shown in the medal area 573X is genuine.

  On the other hand, the rotation angle of the regular medal 510 reflected in a certain medal area 573X is the normal angle when the regular medal 510A reflected in the medal area 573A is rotated around the center by (90 × N) ° counterclockwise. When the rotation angle of the medal 510 does not coincide with the rotation angle of the medal area 573X, the plurality of uniform division areas 582 can be obtained by rotating the plurality of standard uniform division areas 582A around the center of the medal area 573A. Even if it is rotated at, it may not coincide with the plurality of standard uniform divided areas 582A. In other words, the rotation angle of the regular medal 510A when the regular medal 510A is rotated counterclockwise around its center by γ ° (γ ≠ 90 × N, that is, γ is a value other than a multiple of “90”). Is equal to the plurality of uniform divided areas 582 obtained from the medal area 573X, no matter what rotation angle the plurality of standard uniform divided areas 582A are rotated around the center of the medal area 573A. , The plurality of standard uniform divided regions 582A may not match. Therefore, the size information and distance information of the plurality of uniform divided regions 582 obtained from the medal region 573X may not match the size information and distance information of the plurality of standard uniform divided regions 582A. Therefore, the medal feature amount obtained from the medal region 573X may not match the medal feature amount obtained from the medal region 573A. That is, the medal feature value obtained from the medal area 573X may not match the standard feature value stored in the SRAM or the like. As a result, the medal 510 shown in the medal area 573X may not be properly determined as being legitimate. In particular, the rotation angle of the regular medal 510 reflected in the medal area 573X is the regular medal 510A when the regular medal 510A reflected in the medal area 573A is rotated around the center by (90 × N + 45) ° counterclockwise. When the rotation angle coincides with the rotation angle, the medal feature value obtained from the medal area 573X may be significantly different from the standard feature value. For this reason, in this case, there is a high possibility that the medal 510 shown in the medal area 573 is not properly determined to be genuine.

  The rotation angle of the regular medal 510 reflected in a certain medal area 573X is the regular medal when the regular medal 510A reflected in the medal area 573A is rotated counterclockwise (90 × N) ° around its center. How much the medal feature value obtained from the medal area 573X deviates from the medal feature value obtained from the medal area 573A when the rotation angle does not coincide with the rotation angle of 510A in the area division for the medal area 573X. It depends on whether the medal area 573X is finely divided. When the medal area 573X is finely divided in the area division, the medal feature value obtained from the medal area 573X is greatly deviated from the medal feature value obtained from the medal area 573A.

  In this way, the rotation angle of the regular medal 510 reflected in a certain medal area 573X is the counterclockwise (90 × N) ° of the regular medal 510 reflected in the medal area 573A from which the standard feature value is acquired. If the rotation angle of the regular medal 510 does not coincide with the normal medal 510, the medal feature amount obtained from the medal area 573X may be different from the standard feature amount. Therefore, it may not be properly determined that the medal 510 shown in the medal area 573X is genuine. Therefore, in the medal determination process, not only one type of standard feature amount acquired from the medal area 573X in which the normal medal 510 is shown, but also the normal medal 510 in the medal area 573X around the center ( The standard feature amount acquired from the medal area 573 in which the regular medal 510 having a rotation angle that does not coincide with the rotation angle of the regular medal 510 when rotated counterclockwise by 90 × N) ° is also used. Is desirable.

  Further, the description so far using FIG. 76 is based on the premise that the center of the medal area 573 and the center of the regular medal 510 shown in the medal area 573 are coincident. However, depending on the extraction accuracy of the medal area 573 in the extraction unit 564, the center of the medal area 573 may not match the center of the regular medal 510 shown in the medal area 573. FIG. 77 is a diagram showing an example of a state in which the center 573c of the medal area 573 and the center 510c of the regular medal 510 shown in the medal area 573 do not match.

  When the center 573c of the medal area 573 extracted by the extraction unit 564 and the center 510c of the regular medal 510 displayed in the medal area 573 do not match, the rotation angle of the regular medal 510 displayed in a certain medal area 573X is If the rotation angle of the regular medal 510 reflected in the medal area 573X is different from the rotation angle of the regular medal 510 reflected in the medal area 573A from which the standard feature amount is acquired, the rotation angle of the regular medal 510 reflected from the medal area 573X The obtained plurality of uniform divided areas 582 are the same as the plurality of standard uniform divided areas 582A, regardless of the rotation angle of the plurality of standard uniform divided areas 582A around the center of the medal area 573A. May not match. Therefore, in this case, the rotation angle of the regular medal 510 reflected in the medal area 573X is the same as that when the regular medal 510 reflected in the medal area 573A is rotated counterclockwise by (90 × N) ° around the center. Even when the rotation angle of the regular medal 510 coincides, the plurality of uniform divided areas 582 obtained from the medal area 573X has the plurality of standard uniform divided areas 582A around the center of the medal area 573A ( 90 × N) ° There is a possibility that it does not coincide with that rotated counterclockwise. Therefore, the size information and distance information of the plurality of uniform divided regions 582 obtained from the medal region 573X may not match the size information and distance information of the plurality of standard uniform divided regions 582A. Therefore, the medal feature amount obtained from the medal region 573X may not match the medal feature amount obtained from the medal region 573A, that is, the standard feature amount.

  As described above, when the center 573c of the medal area 573 extracted by the extraction unit 564 and the center 510c of the regular medal 510 reflected in the medal area 573X do not coincide with each other, the rotation of the regular medal 510 reflected in the medal area 573X is performed. If the angle is different from the rotation angle of the regular medal 510 displayed in the medal area 573A from which the standard feature value is acquired, the medal is not limited to any rotation angle of the regular medal 510 displayed in the medal area 573X. There is a possibility that the medal feature value obtained from the region 573X is different from the standard feature value. Therefore, it may not be properly determined that the medal 510 shown in the medal area 573X is genuine. Therefore, in the medal determination process, not only one type of standard feature amount acquired from the medal area 573 in which the regular medal 510 is shown, but also a rotation angle different from the rotation angle of the regular medal 510 in the medal area 573. It is desirable to use the standard feature amount acquired from the medal area 573 in which the regular medal 510 having

  In view of the above points, in the present modification example, a plurality of medal regions 573 in which the rotation angles of the regular medals 510 shown in the medal determination process are not used, but are different from each other. A plurality of types of standard feature values respectively generated based on the above are used. The determination unit 567 compares the medal feature amount obtained from the captured image 562B with each of a plurality of types of standard feature amounts stored in the SRAM or the like, and based on the comparison result, the medal 510 reflected in the captured image 562B is determined. It is determined whether it is legitimate.

  In this modification, four types of standard feature values are used. The four types of standard feature values are generated based on the four medal areas 573R, 573α, 573β, and 573γ, respectively, in which the rotation angles of the regular medals 510 shown in them are different from each other. FIG. 78 is a diagram showing an example of the medal areas 573R, 573α, 573β, and 573γ. The rotation angle of the regular medal 510 reflected in the medal area 573α is the rotation angle of the regular medal 510 reflected in the medal area 573R when the regular medal 510 reflected in the medal area 573R rotates 45 ° counterclockwise around its center. Matches. The rotation angle of the regular medal 510 reflected in the medal area 573β is the rotation angle of the regular medal 510 reflected in the medal area 573R when the regular medal 510 reflected in the medal area 573R rotates 90 ° counterclockwise around its center. Matches. The rotation angle of the regular medal 510 reflected in the medal area 573γ is that of the regular medal 510 reflected in the medal area 573R when the regular medal 510 reflected in the medal area 573R rotates counterclockwise by 135 ° around its center. It matches the rotation angle.

  In this modification, the medal areas 573α, 573β, and 573γ are generated based on the medal area 573R. Hereinafter, the medal area 573R is referred to as a “reference medal area 573R”. The medal area 573α is an image obtained by rotating the image 584R of the normal medal 510 reflected in the reference medal area 573R by 45 ° counterclockwise around the center 573Rc of the reference medal area 573R. The medal area 573β is an image obtained by rotating the image 584R of the regular medal 510 shown in the reference medal area 573R by 90 ° counterclockwise around the center 573Rc of the reference medal area 573R. The medal area 573γ is an image obtained by rotating the image 584R of the regular medal 510 shown in the reference medal area 573R by 135 ° counterclockwise around the center 573Rc of the reference medal area 573R.

  In order to generate a plurality of types of standard feature amounts, a regular medal 510 is inserted into the gaming machine when the gaming machine is not actually operating. The conversion unit 563 generates a standard captured image 562C that shows the inserted regular medal 510. The extraction unit 564 extracts the reference medal region 573R in which the regular medal 510 is shown from the standard captured image 562C, and the region dividing unit 565 performs region division on the reference medal region 573R. Then, the feature amount acquisition unit 566 generates a standard two-dimensional evaluation value histogram 591A based on the plurality of uniform divided regions 582 generated by the region dividing unit 565. Accordingly, one type of standard feature value, that is, one type of standard two-dimensional evaluation value histogram 591A is generated based on the reference medal region 573R.

  It should be noted that the standard feature value generation by such a gaming machine can be performed when a predetermined mode is selected in the gaming machine. Further, a standard feature amount may be generated in advance by a gaming machine or other device and stored in the SRAM or the like of each gaming machine.

  In the extraction unit 564, medal areas 573α, 23β, and 23γ are generated based on the reference medal area 573R. The extraction unit 564 sets an image obtained by rotating the image 584R of the regular medal 510 around the center 573Rc of the reference medal region 573R by 45 ° counterclockwise in the reference medal region 573R as the medal region 573α. In addition, in the reference medal area 573R, the extraction unit 564 rotates the image 584R of the regular medal 510 around the center 573Rc of the reference medal area 573R by 90 ° counterclockwise, and obtains an image obtained as the medal area 573β. To do. The extraction unit 564 then obtains an image obtained by rotating the image 584R of the regular medal 510 around the center 573Rc of the reference medal region 573R counterclockwise by 135 ° in the reference medal region 573R as the medal region 573γ. To do.

  When the extracting unit 564 generates the medal areas 573α, 573β, and 573γ, the area dividing unit 565 performs area division on the medal areas 573α, 573β, and 573γ. The feature amount acquisition unit 566 generates a standard two-dimensional evaluation value histogram 591A based on the plurality of uniform divided regions 582 generated by the region division of the medal region 573α in the region dividing unit 565. The feature amount acquiring unit 566 generates a standard two-dimensional evaluation value histogram 591A based on the plurality of uniform divided regions 582 generated by the region division of the medal region 573β in the region dividing unit 565. The feature amount acquisition unit 566 generates a standard two-dimensional evaluation value histogram 591A based on the plurality of uniform divided regions 582 generated by the region division of the medal region 573γ in the region dividing unit 565. Thus, three types of standard feature values, that is, three types of standard two-dimensional evaluation value histograms 591A are generated based on the medal areas 573α, 573β, and 573γ.

  A plurality of types of standard feature values (standard two-dimensional evaluation value histogram 591A) generated as described above are stored in, for example, an SRAM (corresponding to the SRAM 243 of the camera unit 209 according to the first embodiment). Can do.

  In a game machine in actual operation, the determination unit 567 compares the two-dimensional evaluation value histogram 591 generated from the captured image 562B with each of a plurality of types of standard two-dimensional evaluation value histograms 591A stored in the SRAM or the like. . Specifically, for each of a plurality of types of standard two-dimensional evaluation value histograms 591A stored in the SRAM or the like, the determination unit 567 performs a two-dimensional evaluation generated from the standard two-dimensional evaluation value histogram 591A and the captured image 562B. The Bhattacharyya distance from the value histogram 591 is obtained. Then, the determination unit 567 sets a minimum value among the obtained Bhattacharyya distances as a determination evaluation value. Then, the determination unit 567 determines that the medal 510 shown in the captured image 562B is genuine when the determination evaluation value is equal to or smaller than the threshold value. It is determined that the medal 510 shown in the image 562B is not genuine.

  As described above, in the medal determination process according to the present modification, a plurality of types of standard feature amounts respectively generated based on a plurality of images having different rotation angles of the regular medal 510 shown in them are used. Regardless of the rotation angle of the medal 510 shown in the captured image 562B, it is possible to appropriately determine whether or not the medal 510 is genuine. Therefore, the determination accuracy is improved.

  In the above example, four types of standard feature values are used, but the number of types of standard feature values is not limited to this. Further, the rotation angle of the regular medal 510 shown in each of a plurality of images (a plurality of medal areas 573) in which a plurality of types of standard feature amounts are generated is not limited to the above rotation angle.

[Modification 3 (Authenticity determination using multiple types of determination methods)]
In the medal determination process, the determination method described above and other determination methods may be used together to determine whether or not the medal 510 shown in the captured image 562B is genuine. As another determination method for determining whether or not the medal 510 shown in the captured image 562B is genuine, for example, a template matching method using an image of a regular medal as a template image is conceivable. In this template matching method, it is determined whether or not the medal 510 shown in the captured image 562B is genuine by specifying whether or not there is an image similar to the template image in the captured image 562B. Hereinafter, a case where the above-described determination method and the template matching method are used in combination in the medal determination process will be described. Note that a matching method other than the template matching method may be used.

  Also in the template matching method, as in the above-described determination method, a determination evaluation value (also referred to as “output value”) indicating the probability that the medal 510 shown in the captured image 562B is genuine is generated. In the template matching method, an area most similar to the template image is specified in the captured image 562B in which the medal 510 is shown, and a value indicating the degree of similarity between the area and the template image is used as a determination evaluation value. Hereinafter, the determination evaluation value obtained by the processing described with reference to the functional block diagram of FIG. 61 is referred to as “first determination evaluation value EV1”, and the determination evaluation value obtained by the template matching method is referred to as “second determination evaluation value EV2. " Here, the smaller the value of the second determination evaluation value EV2, the higher the possibility that the medal 510 shown in the captured image 562B is correct.

When the first determination evaluation value EV1 is obtained for the captured image 562B and the second determination evaluation value EV2 is further obtained (using the template matching method), the determination unit 567 uses the following expression 8 to determine the comprehensive evaluation value EV0 is obtained.
EV0 = z1 × EV1 + z2 × EV2 (Expression 8)

  In formula 8, z1 and z2 are constants. As shown in Expression 8, the overall evaluation value EV0 is a small value when both the first determination evaluation value EV1 and the second determination evaluation value EV2 are small.

  When the overall evaluation value EV0 is equal to or less than the threshold th0, the determination unit 567 determines that the medal 510 shown in the captured image 562B is genuine. On the other hand, when the comprehensive evaluation value EV0 is larger than the threshold value th0, the determination unit 567 determines that the medal 510 shown in the captured image 562B is not regular. The threshold th0 and the constants z1 and z2 can be stored in, for example, an SRAM (corresponding to the SRAM 243 of the camera unit 209 according to the first embodiment).

  Here, the captured image 562B in which the regular medal 510 is shown is referred to as “positive captured image 562B1”, and the captured image 562B in which the fake medal 510 (invalid medal 510) is reflected is referred to as “negative captured image 562B2.” The threshold th0 and the constants z1 and z2 are the first determination evaluation value EV1 and the second determination evaluation value EV2 for the plurality of positive captured images 562B1, and the first determination evaluation value EV1 and the first determination value EV2 for the plurality of negative captured images 562B2. 2 can be determined based on the evaluation value EV2. Hereinafter, a method for determining the threshold th0 and the constants z1 and z2 will be described.

  FIG. 79 is a diagram illustrating the relationship between the first determination evaluation value EV1 and the second determination evaluation value EV2 obtained for each of the plurality of positive captured images 562B1 and the plurality of negative captured images 562B2. The x-axis shown in FIG. 79 indicates the second determination evaluation value EV2. The y-axis shown in FIG. 79 indicates the first determination evaluation value EV1 of the captured image 562B from which the second determination evaluation value EV2 shown on the x-axis is obtained. 79 indicates the first determination evaluation value EV1 and the second determination evaluation value EV2 for the positive captured image 562B1, and the white circle in FIG. 79 indicates the first determination evaluation value EV1 for the negative captured image 562B2. The second determination evaluation value EV2 is shown. Hereinafter, the pair of the first determination evaluation value EV1 and the second determination evaluation value EV2 obtained for the captured image 562B may be referred to as an “evaluation value pair”. FIG. 79 shows an evaluation value scatter diagram 593 showing the distribution of the evaluation value pairs of the plurality of captured images 562B.

  In this example, when the first determination evaluation value EV1 is small, there is a high possibility that the medal 510 shown in the captured image 562B is genuine. When the second determination evaluation value EV2 is small, there is a high possibility that the medal 510 shown in the captured image 562B is genuine. Therefore, in the evaluation value scatter diagram 593 shown in FIG. 79, the black triangle indicating the evaluation value pair of the positive captured image 562B1 is in an area where both the first determination evaluation value EV1 and the second determination evaluation value EV2 are small, that is, the lower left corner. concentrate.

  As in the above example, when the authenticity determination of the medal 510 is performed only by determining whether or not the first determination evaluation value EV1 is equal to or less than the threshold th1, the first determination evaluation value EV1 is small. For the negative captured image 562B2 in which the second determination evaluation value EV2 is large, it is erroneously determined that the medal 510 shown in the image is correct. In the evaluation value scatter diagram 593 shown in FIG. 79, a negative captured image in which an evaluation value pair indicated by white circles on the straight line 595 along the x axis and the lower white circle indicating the threshold th1 is obtained. It is erroneously determined that the medal 510 shown in 562B2 is genuine. In the evaluation value scatter diagram 593, on the straight line 594 along the x-axis direction, the distribution of the evaluation value pair (black triangle) of the positive captured image 562B1 and the distribution of the evaluation value pair (white circle) of the negative captured image 562B2 are appropriately displayed. Difficult to separate.

  Further, when the authenticity determination of the medal 510 is performed only by determining whether or not the second determination evaluation value EV2 is equal to or less than the threshold value th2, the first determination evaluation value although the second determination evaluation value EV2 is small. For the negative captured image 562B2 in which EV1 is large, it is erroneously determined that the medal 510 shown in the image is correct. In the evaluation value scatter diagram 593 shown in FIG. 79, a negative captured image 562B2 in which an evaluation value pair indicated by a white circle on the straight line 595 along the y axis and on the left side of the straight line 595 showing the threshold th2 is obtained. It is erroneously determined that the medal 510 shown in FIG. In the evaluation value scatter diagram 593, it is difficult to properly separate the evaluation value pair distribution of the positive captured image 562B1 and the distribution of the evaluation value pair of the negative captured image 562B2 along the straight line 595 along the y-axis direction.

In this modified example, when the gaming machine is not in actual operation, a plurality of regular medals 510 and a plurality of illegal medals 510 are inserted into the gaming machine, and a plurality of positive captured images 562B1 and a plurality of negative captured images. An evaluation value pair for each of the images 562B2 is obtained. Then, in an evaluation value scatter diagram 593 showing a plurality of evaluation value pairs, a separation straight line 596 (see FIG. 79) in which the evaluation value pair distribution of the positive captured image 562B1 and the distribution of the evaluation value pair of the negative captured image 562B2 are separated. ) Is obtained. The separation straight line 596 can be expressed by the following Equation 9. In Equation 9, A1, A2, and B are constants.
y = − (A1 / A2) x + B (formula 9)

  It should be noted that such acquisition of the evaluation value pair by the gaming machine can be performed when a predetermined mode is selected in the gaming machine. Also, an evaluation value pair may be acquired in advance by a gaming machine or other device and stored in the SRAM or the like of each gaming machine.

  In the evaluation value scatter diagram 593, the area above and below the separation straight line 596 is an area where both the first determination evaluation value EV1 and the second determination evaluation value EV2 are small. Therefore, in the case where the evaluation value pair obtained for the captured image 562B is shown in the evaluation value scatter diagram 593, when the position of the evaluation value pair is on or below the separation line 596, the image is captured. It can be considered that the medal 510 shown in the image 562B is genuine.

In the evaluation value scatter diagram 593, the area on the lower side of the separation straight line 596 and the area below it is expressed by the following Expression 10.
y ≦ − (A1 / A2) x + B (Formula 10)

Further, Expression 10 can be transformed into Expression 11 below.
A1x + A2y ≦ A2 × B (Formula 11)

  When the first determination evaluation value EV1 and the second determination evaluation value EV2 obtained for the captured image 562B are assigned to x and y in Expression 11, respectively, if Expression 11 is satisfied, the image is displayed in the captured image 562B. The medal 510 can be considered as a regular one.

  For example, the SRAM (corresponding to the SRAM 243 of the camera unit 209 according to the first embodiment) stores constants A1 and A2 of Expression 9 and constants z1 and z2 of Expression 8. The constants A1 and A2 of Expression 9 may be stored as the constants z1 and z2 of Expression 8, respectively. Further, “A2 × B” can be stored as the threshold value th0.

  The determination unit 567 uses the first determination evaluation value EV1 and the second determination evaluation value EV2 for the captured image 562B and the constants z1 and z2 stored in the SRAM or the like to obtain the overall evaluation value EV0 for the captured image 562B. Ask. Then, the determination unit 567 determines that the medal 510 shown in the captured image 562B is normal if the obtained overall evaluation value EV0 is equal to or less than the threshold th0, and if greater than the threshold th0, It is determined that the medal 510 shown in the captured image 562B is not a regular one. Thereby, authenticity determination of the medal 510 can be performed more correctly.

  Note that the expression 9 may be obtained by hand calculation by a person looking at the evaluation value scatter diagram 593, or by a predetermined computer device based on the first determination evaluation value EV1 and the second determination evaluation value EV2. You may obtain | require using machine learning functions, such as a machine. In the latter case, a gaming machine equipped with a machine learning function may obtain Equation 9.

  As described above, in this modification, it is determined whether or not the medal 510 shown in the captured image 562B is genuine based on a plurality of determination evaluation values obtained by different determination methods. Can be improved.

1,300,400,500 Pachislot 3L Left reel 3C Middle reel 3R Right reel 4 Reel display window 21 Medal slot 23 Start lever 32 Medal payout port 51 Hopper device 71 Main control board 72 Sub control board 79 Start switch 80 Stop switch board 91 Main control circuit 101 Sub control circuit 201 Medal selector 202 Medal chute 203 Slope 204 Base plate part 205 Sub plate 206 Cancel shooter 207 Select plate 208 Medal solenoid 209 Camera unit 210 Medal rail 211 Medal inlet part 212 Central hole 213 Medal pressure 217 Magnet 218 After medal pressure 227 Medal stopper 230 First substrate 231 Second substrate 232 CMOS image sensor 2 3 LED
234 Control LSI
235 Leg 241 Host controller 242 Image recognition DSP circuit 243 SRAM
244 Flash memory 245 ISP circuit 246 Medal count circuit 247 Color recognition circuit 248 Fisheye correction scaler circuit 249 Image recognition accelerator circuit 250 GPIO
251 ISI circuit 266 Input / output unit 268 Determination result 310, 410, 510 Medal 361 Imaging unit 362A, 362B Captured image 362C Feature image 363 Conversion unit 364 Feature image generation unit 365 Determination unit 366 Input / output unit 367 Template data 368 Determination result 371 Extraction Unit 372 edge image generation unit 374 first image 380 second image generation unit 461 imaging unit 462A, 462B captured image 463 conversion unit 464 extraction unit 465 identification unit 466 fitting unit 467 determination unit 467A standard feature quantity 468 input / output unit 469 determination result 561 Imaging unit 562A, 562B Captured image 563 Conversion unit 564 Extraction unit 565 Region division unit 566 Feature amount acquisition unit 567 Determination unit 567A Standard feature amount 568 Input / output unit 569 Determination result

Claims (2)

A slot for gaming media;
A game medium detecting means for detecting a game medium thrown from the slot,
The game medium detection means includes
A game medium passage section serving as a passage through which the game medium passes;
Imaging means for imaging a passing object that is an object passing through the passage;
Game medium determination means for determining whether or not the game medium is legitimate by performing image processing based on image data obtained via the imaging means,
The game medium determining means is
Counting means for converting the image data into first color space image data corresponding to a color space and counting the game media based on data relating to luminance of the first color space image data;
Color determination means for converting the image data into second color space image data corresponding to a color space, and determining the color of the game medium based on data relating to hue and saturation of the second color space image data;
Extraction means for converting the image data into grayscale image data and extracting an area in which the game medium is shown from the grayscale image data;
Area dividing means for dividing an area in which the game medium is displayed into a plurality of divided areas;
Feature quantity acquisition means for acquiring a feature quantity indicating a feature of an area in which the game medium is shown based on the plurality of divided areas;
Determination means for determining whether or not a game medium corresponding to an image of a game medium included in the grayscale image data is regular based on the feature amount;
The region dividing means includes
Based on the entropy of the luminance histogram over the entire area in which the game medium is shown, determine a threshold value used to determine whether to perform area division;
Regardless of the threshold value, the initial division is performed on the area where the game medium is shown,
For each of the divided areas where the initial division has been performed, calculate the entropy of the luminance histogram,
After the initial division, the entropy of the luminance histogram is calculated for each of the divided regions, and when the calculated entropy of the luminance histogram is equal to or greater than the threshold, the corresponding divided region is Further, it is divided into a plurality of divided areas,
The feature amount acquisition unit acquires the feature amount based on a two-dimensional histogram related to predetermined information for each of the plurality of divided regions, and the predetermined information includes information indicating a size of the corresponding divided region, and , Information indicating the distance from the center of the area where the game medium is shown to the corresponding divided area,
The determination means compares the feature amount with a standard feature amount indicating a feature of a regular game medium, and based on the comparison result, determines whether or not the game medium according to the image data is a regular one. A gaming machine characterized by judging. A game medium passage portion serving as a passage through which the game medium passes;
Imaging means for imaging a passing object that is an object passing through the passage;
Game medium determination means for determining whether or not the game medium is legitimate by performing image processing based on image data obtained via the imaging means,
The game medium determining means is
Counting means for converting the image data into first color space image data corresponding to a color space and counting the game media based on data relating to luminance of the first color space image data;
Color determination means for converting the image data into second color space image data corresponding to a color space, and determining the color of the game medium based on data relating to hue and saturation of the second color space image data;
Extraction means for converting the image data into grayscale image data and extracting an area in which the game medium is shown from the grayscale image data;
Area dividing means for dividing an area in which the game medium is displayed into a plurality of divided areas;
Feature quantity acquisition means for acquiring a feature quantity indicating a feature of an area in which the game medium is shown based on the plurality of divided areas;
Determination means for determining whether or not a game medium corresponding to an image of a game medium included in the grayscale image data is regular based on the feature amount;
The region dividing means includes
Based on the entropy of the luminance histogram over the entire area in which the game medium is shown, determine a threshold value used to determine whether to perform area division;
Regardless of the threshold value, the initial division is performed on the area where the game medium is shown,
For each of the divided areas where the initial division has been performed, calculate the entropy of the luminance histogram,
After the initial division, the entropy of the luminance histogram is calculated for each of the divided regions, and when the calculated entropy of the luminance histogram is equal to or greater than the threshold, the corresponding divided region is Further, it is divided into a plurality of divided areas,
The feature amount acquisition unit acquires the feature amount based on a two-dimensional histogram related to predetermined information for each of the plurality of divided regions, and the predetermined information includes information indicating a size of the corresponding divided region, and , Information indicating the distance from the center of the area where the game medium is shown to the corresponding divided area,
The determination means compares the feature amount with a standard feature amount indicating a feature of a regular game medium, and based on the comparison result, determines whether or not the game medium according to the image data is a regular one. A game medium discriminating apparatus characterized by determining.

Images