JP2008176653A - Monitoring device, method, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To improve a collation speed and collation accuracy until the identification of the facial image of a person to be collated. <P>SOLUTION: A remote extraction section 451a extracts a face image which is determined to be the face image of another person who is different from the person to be collated, at a position which is a predetermined distance away from a position, where the face image of the person to be collated is acquired by a face image acquisition section 221, and a difference calculating section 451b generates a partial biological information DB 403, from the difference information between a set of face images accumulated in a biological information DB 22 and a set of face images which are determined as being the facial images of other persons to be collated who are different from the person to be collated who has been extracted by the remote extraction section 451a. A similarity calculation section 461 calculates the degree of similarity between the face image of the person to be collated and the facial images in the partial biological information DB 403, and a similarity determination section 462 determines whether the face image of the person to be collated is the face image of a registered person, by comparing the degree of similarity as a result of the collation and a predetermined threshold. The present invention can be applied to a monitoring system. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a monitoring apparatus, method, and program, and more particularly, to a monitoring apparatus, method, and program that can improve the collation speed and collation accuracy of collation processing using face images.

  Authentication technology using facial images is becoming more popular.

  As a means of collecting face information of visitors and exits and managing the information, from the personal information database consisting of face images, the individual is identified based on the face information of the store visitor (store visitor) and the store exit A technique for searching and outputting a search result has been proposed (see Patent Document 1).

  In addition, a technique has been proposed in which a camera is installed for each game machine represented by a pachinko machine, a slot machine, etc., and collated with the face images of game shop members or unauthorized persons registered in advance (see Patent Document 2). .

JP 2006-107285 A JP 2001-178958 A

  However, in the above configuration, a unique specific personal information database or biometric information database is always used, and all information registered in the specific personal information database or biometric information database is always searched even when one individual is collated. Therefore, as the information in the specific personal information database is updated and the information to be searched increases, the search time may become longer.

  The present invention has been made in view of such a situation, and uses a database obtained by excluding face images that have already been searched from a database of face images in which face images of a plurality of registrants are registered in advance. Thus, the collation speed and collation accuracy until the face image of the person to be collated is specified are improved.

  The monitoring apparatus according to one aspect of the present invention includes a first storage unit that stores a pre-registered registrant face image group, an acquisition unit that acquires a face image of a verification target person, and the verification target by the acquisition unit. The face image of the registrant determined to be a face image of another collation target person different from the collation target person at a position far from the position where the face image of the person is acquired by a predetermined distance is extracted. It is determined that the face images of the collation target person different from the collation target person extracted from the extraction means, the set of registrant face images accumulated by the first accumulation means, and the collation target person extracted by the extraction means A difference calculating means for obtaining difference information from the set of registered registrant face images, a second accumulating means for accumulating the registrant face image as the difference information, and a collation target obtained by the obtaining means Stored in the second storage means The collation means for calculating and comparing the similarity with the registered registrant's face image, and comparing the similarity as the collation result of the collation means with a predetermined threshold value, the face image of the person to be collated is the registrant. A similarity determination unit that determines whether or not the face image is a face image, and the collation that is determined to be the registrant when the similarity determination unit determines that the verification target person is the registrant. Registration means for registering the face image of the subject person and the information on the position where the face image was acquired, and the extraction means is configured so that the person to be collated by the similarity determination means registered by the registration means. Based on the face image of the person to be collated determined to be the registrant and information on the position from which the face image was obtained, the position from which the face image of the person to be collated is obtained by the obtaining unit. Is a certain distance away In location, extracting the registrant's face image is determined to be different from the collation target person of the face image and the collation object person.

  Image capturing means for capturing an image, face image extracting means for extracting the face image of the person to be collated from the image captured by the image capturing means, and feature amount extraction for extracting a feature amount from the face image of the person to be collated And the collating means calculates the similarity using the feature amount of the face image of the person to be collated obtained by the obtaining means and the face image of the registrant accumulated in the accumulating means. Then, the face image of the person to be collated acquired by the acquisition unit and the face image of the registrant accumulated in the accumulation unit can be collated.

  If the face image is not acquired for a predetermined time or more by the acquisition means in the registration means, the verification target person registered corresponding to the position where the face image is not acquired for the predetermined time or more by the acquisition means The face image information can be deleted.

  When the similarity determination unit determines that the collation target person is not the registrant, it further includes an unregistered person registration unit that registers the face image of the collation target person as an unregistered person. Can do.

  The first accumulating means accumulates pre-registered registrant face images as a database, and the database includes unregistered face images registered by the unregistered person registering means a predetermined number of times, It can be registered as a face image of the registrant.

  The position from which the face image of the person to be collated is acquired belongs to one of a plurality of ranges, and the position from which the face image of the person to be collated is acquired belongs to the extraction unit. By recognizing a position outside the range as a distant position by a predetermined distance, at a position far from the position where the face image of the person to be collated is acquired by the obtaining unit, Extracts the face image of the registrant determined to be the face image of another different person to be collated.

  The monitoring method according to one aspect of the present invention includes a first accumulation step of accumulating a pre-registered registrant face image group, an acquisition step of acquiring a face image of a collation target person, and a process of the acquisition step. The face image of the registrant determined to be a face image of another collation target person different from the collation target person at a position far from the position where the face image of the collation target person is acquired by a predetermined distance. An extraction step to extract, a set of registrant face images accumulated by the process of the first accumulation step, and another collation target person different from the collation target person extracted by the extraction step process A difference calculating step for obtaining difference information with the set of face images of the registrant determined to be a face image, a second accumulation step for accumulating the face image of the registrant as the difference information, and the obtaining step Processing A matching step of calculating and comparing the similarity between the face image of the person to be collated acquired from the face image of the registrant accumulated in the process of the second accumulation step, and a process in the process of the collation step By comparing the similarity that is the collation result with a predetermined threshold value, the similarity determination step that determines whether or not the face image of the person to be collated is the face image of the registrant, and the processing of the similarity determination step When it is determined that the person to be verified is the registrant, a registration step of registering the face image of the person to be verified that has been determined to be the registrant and information on the position from which the face image was acquired And the process of the extraction step includes the face image of the person to be collated determined to be the registrant by the process of the similarity determination step registered by the process of the registration step, And, based on the information on the position where the face image was acquired, at the position far from the position where the face image of the person to be verified is acquired by the process of the acquisition step, Extracts the face image of the registrant determined to be the face image of another different person to be collated.

  The program according to one aspect of the present invention includes: a first accumulation step of accumulating a pre-registered registrant face image group; an acquisition step of acquiring a face image of a collation target person; and the collation by the processing of the acquisition step. Extract the face image of the registrant determined to be a face image of another collation target person different from the collation target person at a position far from the position where the face image of the target person is acquired by a predetermined distance. And a set of facial images of the registrant accumulated by the process of the first accumulation step, and a face of another collation target person different from the collation target person extracted by the process of the extraction step A difference calculation step for obtaining difference information from the set of face images of the registrant determined to be an image, a second accumulation step for accumulating the face image of the registrant as the difference information, and the obtaining step place Calculating the similarity between the face image of the person to be collated obtained by the above and the face image of the registrant accumulated in the process of the second accumulation step, and a collation step for collating, and a process in the process of the collation step By comparing the similarity that is the collation result with a predetermined threshold value, the similarity determination step that determines whether or not the face image of the person to be collated is the face image of the registrant, and the processing of the similarity determination step When it is determined that the person to be verified is the registrant, a registration step of registering the face image of the person to be verified that has been determined to be the registrant and information on the position from which the face image was acquired And the extraction step is performed by determining that the person to be collated is the registrant by the similarity determination step registered by the registration step. On the basis of the information on the face image of the person to be collated and the position information at which the face image is obtained, a predetermined distance from the position at which the face image of the person to be collated is obtained by the processing of the obtaining step. The face image of the registrant who is determined to be a face image of another collation target person different from the collation target person at a remote position is extracted.

  In the monitoring apparatus, method, and program according to one aspect of the present invention, a pre-registered registrant face image group is accumulated, a collation target person face image is acquired, and the collation target person face image is acquired. The registrant in which the face image of the registrant who has been determined to be a face image of another collation target person different from the collation target person is extracted and accumulated at a position far from the target position by a predetermined distance Difference information between a set of face images of the registrant determined to be a face image of another collation target person different from the extracted collation target person, and the difference information A collation unit that calculates and compares the similarity between the acquired face image of the person to be collated and the face image of the registrant composed of the accumulated difference information, The similarity and the predetermined threshold that are the matching results of the matching means It is determined whether or not the face image of the person to be collated is a registrant's face image, and if the person to be collated is determined to be the registrant, the person is determined to be the registrant. The registered face image of the person to be collated and the information on the position from which the face image was acquired are registered, and the face image of the person to be collated in which it is determined that the registered person to be collated is the registrant. Based on the information on the position where the face image is acquired, another verification different from the verification target at a position far from the position where the verification target person's face image is acquired by a predetermined distance. The face image of the registrant determined to be the face image of the subject is extracted.

  In the monitoring device according to one aspect of the present invention, the first accumulation unit that accumulates a pre-registered registrant face image group is, for example, a biometric information DB, and an acquisition unit that obtains a face image of a person to be verified Is, for example, a face image acquisition unit, and a different verification target person that is different from the verification target person at a position that is a predetermined distance away from the position at which the face image of the verification target person is acquired by the acquisition means. The extraction means for extracting the face image of the registrant determined to be a face image of the registrant is, for example, a distant extraction unit, and a set of face images of the registrant stored by the first storage means The difference calculation means for obtaining difference information from a set of face images of the registrant determined to be a face image of another collation target person different from the collation target person extracted by the extraction means is, for example, , A difference calculation unit, and the difference information The second accumulating unit that accumulates the registrant's face image is, for example, a partial biometric information DB, and is accumulated in the collation target person's face image acquired by the acquiring unit and the second accumulating unit. The matching means for calculating and matching the similarity with the registrant's face image is, for example, a similarity calculation unit, and by comparing the similarity as a matching result of the matching means with a predetermined threshold, The similarity determination unit that determines whether or not the face image of the person to be collated is a face image of the registrant is, for example, a similarity degree determination unit, and the person to be collated is the registrant by the similarity degree determination unit. The registration means for registering the face image of the person to be collated determined to be the registrant and the information on the position where the face image was acquired is, for example, a list generation unit For example, the extraction means that is a remote extraction unit is For example, the face image of the person to be collated in which the person to be collated is determined to be the registrant by the similarity determination unit registered by the registration unit that is a list generation unit, and the face image thereof are acquired. Based on the information on the position, the face image of another collation target person different from the collation target person at a position far from the position at which the face image of the collation target person is acquired by the acquisition unit. The face image of the registrant determined to be is extracted.

  That is, when it is determined that the collation target person is a registrant, the partial biometric information DB is generated by deleting the face image of the registrant determined to be the collation target person from the biometric information DB.

  For this reason, since the face image registered in the partial biometric information DB from which the face image of the registrant determined to be a collation target is deleted is collated, the registrant used for the collation process Face images are reduced.

  As a result, it is possible to improve the collation speed and collation accuracy until the face image of the person to be collated is specified.

  ADVANTAGE OF THE INVENTION According to this invention, it becomes possible to improve the collation speed and collation precision until it specifies the face image of a collation subject person.

  Embodiments of the present invention will be described below. Correspondences between the configuration requirements of the present invention and the embodiments described in the detailed description of the present invention are exemplified as follows. This description is to confirm that the embodiments supporting the present invention are described in the detailed description of the invention. Accordingly, although there are embodiments that are described in the detailed description of the invention but are not described here as embodiments corresponding to the constituent elements of the present invention, It does not mean that the embodiment does not correspond to the configuration requirements. Conversely, even if an embodiment is described here as corresponding to a configuration requirement, that means that the embodiment does not correspond to a configuration requirement other than the configuration requirement. It's not something to do.

  In other words, the monitoring device according to one aspect of the present invention acquires a first storage unit (for example, the biometric information DB 22 in FIG. 27) that stores a pre-registered registrant's face image group and a face image of the person to be verified. Acquisition means (for example, the face image acquisition unit 221 in FIG. 27) and a position far from the position where the acquisition means acquires the face image of the person to be verified by a predetermined distance, Accumulated by the first accumulating means and extracting means for extracting the face image of the registrant determined to be the face image of another different person to be collated (for example, the remote extracting unit 451a in FIG. 27). Difference information between a set of registrant face images and a set of face images of the registrant determined to be a face image of another collation target person different from the collation target person extracted by the extraction unit. Difference calculation means to be obtained (for example, FIG. A difference calculating unit 451b), a second accumulating unit (for example, the partial biometric information DB 403 in FIG. 27) that accumulates the registrant's face image as the difference information, and the face of the person to be collated acquired by the acquiring unit The collation means (for example, the similarity calculation unit 461 in FIG. 27) for calculating and collating the similarity between the image and the registrant face image accumulated in the second accumulation means, and the collation result of the collation means Similarity determination means for determining whether or not the face image of the person to be collated is a registrant's face image by comparing the similarity with a predetermined threshold (for example, the similarity determination unit 462 in FIG. 27) When the similarity determination unit determines that the collation target person is the registrant, the face image of the collation target person determined to be the registrant and the face image thereof are acquired. Registration means for registering position information (for example, 27, and the extraction means (for example, the remote extraction section 451a in FIG. 27) is configured such that the person to be collated is the registrant by the similarity determination means registered by the registration means. Based on information on the face image of the person to be collated determined to be present and the position at which the face image is obtained, a predetermined distance from the position at which the face image of the person to be collated is obtained by the obtaining unit The face image of the registrant who is determined to be the face image of another collation target person different from the collation target person at a position farther away is extracted.

  Image capturing means for capturing an image (for example, the camera 38 in FIG. 26) and face image extracting means for extracting the face image of the person to be collated from the image captured by the image capturing means (for example, face image extraction in FIG. 9). Unit 202) and a feature quantity extracting unit that extracts a feature quantity from the face image of the person to be collated, and the collating unit (for example, the similarity calculating unit 461 in FIG. 27) obtains it by the obtaining unit. The similarity is calculated using the feature amount of the face image of the collation target person and the face image of the registrant accumulated in the accumulation unit, the face image of the collation target person acquired by the acquisition unit, The face image of the registrant stored in the storage means can be collated.

  In the registration unit (for example, the list generation unit 452 in FIG. 27), when a face image is not acquired for a predetermined time or more by the acquisition unit, a position where the face image is not acquired for the predetermined time or more by the acquisition unit. The information on the face image of the person to be collated registered correspondingly can be deleted.

  When the similarity determination unit determines that the person to be verified is not the registrant, an unregistered person registration unit (for example, the unregistered game in FIG. 27) registers the face image of the person to be verified as an unregistered person. A user database registration unit 223).

  The first accumulating means accumulates face images of registrants registered in advance as a database, and the database (for example, the unregistered player DB 251 in FIG. 11) stores a predetermined number of times by the unregistered person registering means. The registered unregistered face image can be registered as the registrant face image.

  The position at which the face image of the person to be collated is acquired belongs to any of a plurality of ranges (for example, divided into ranges Z1 to Z8 as shown in FIG. 29), and the extraction means (For example, the distant extraction unit 451a in FIG. 27) recognizes a position outside the range to which the position from which the face image of the person to be collated belongs as a distant position by a predetermined distance, thereby obtaining the acquisition. The registrant's face image determined to be a face image of another collation target person different from the collation target person at a position far from the position where the face image of the collation target person is acquired by the means. Extract face images.

  The monitoring method according to one aspect of the present invention includes a first accumulation step (step S182 in FIG. 25) for accumulating a pre-registered registrant face image group, and an acquisition step (FIG. 25). 28. Step S222) and the face of another collation target person different from the collation target person at a position a predetermined distance away from the position from which the face image of the collation target person is acquired by the processing of the acquisition step An extraction step (step S223 in FIG. 28) for extracting the face image of the registrant determined to be an image, a set of registrant face images accumulated by the processing of the first accumulation step, A difference calculation step for obtaining difference information from a set of face images of the registrant determined to be a face image of another collation target person different from the collation target person extracted by the extraction step process (FIG. 2). Step S224), a second accumulation step (step S225 in FIG. 28) for accumulating the registrant face image serving as the difference information, and the collation target person face image acquired by the processing of the acquisition step, A similarity step (step S228 in FIG. 28) for calculating and collating the similarity with the face image of the registrant accumulated in the processing of the second accumulation step, and a similarity that is a collation result in the processing of the collation step A similarity determination step (step S229 in FIG. 28) for determining whether or not the face image of the person to be collated is a face image of the registrant by comparing the degree with a predetermined threshold, and the similarity determination step When it is determined by processing that the person to be collated is the registrant, the face image of the person to be collated determined to be the registrant, and information on the position from which the face image was acquired A registration step (step S233 in FIG. 28) for recording, and in the extraction step processing, the person to be collated is the registrant by the processing of the similarity determination step registered by the processing of the registration step. Based on the determined face image of the person to be collated and information on the position at which the face image is obtained, a predetermined distance from the position at which the face image of the person to be collated is obtained by the processing of the obtaining step The face image of the registrant who is determined to be the face image of another collation target person different from the collation target person at a position farther away is extracted.

  FIG. 1 is a diagram showing a configuration of an embodiment of a game shop monitoring system according to the present invention.

  The game stores 1-1 to 1-n are so-called pachinko stores, pachislot stores, or casino stores. These amusement stores 1-1 to 1-n are affiliated stores or member stores of a biometric information management center or a third party amusement store management center, and stores that need to manage a plurality of stores in an integrated manner. It is. Each of the game stores 1-1 to 1-n is connected by a biological information management bus 6 and a third party game store management bus 7, and the public communication line networks 8 and 9 represented by the bus and the Internet are used. Via each other, biological information and third party game store management information are exchanged. In the following description, when there is no particular need to distinguish each of the game stores 1-1 to 1-n, the game store 1 is simply referred to, and the other configurations are also referred to in the same manner.

  The biometric information management bus 6 mainly functions as a transmission path for distributing biometric information managed by the biometric information recognition device 21 of each game store 1. The third-party game store management bus 7 functions as a transmission path for distributing medium lending management information managed mainly by the medium lending management device 27 of each amusement store 1.

  The biometric information management center 2 is a server used by a business operator who manages and operates the biometric information management center, and is a registered player managed by a biometric information management database (hereinafter, the database is also referred to as DB) 3. The DB 252 (FIG. 11) is updated based on the unregistered player DB 251 (FIG. 11) generated by each game store 1, and the updated latest registered player DB 252 is updated with the biometric information recognition device 21 of each game store 1. Deliver against. In addition, the biometric information management center 2 acquires the information of the day collation database 19 and the biometric information database 22 from each game store 1, generates difference information thereof, and distributes the information to each game store 1.

  The third-party amusement store management center 4 is a server used by a business operator that manages and operates the third-party amusement store management center, and the medium lending management managed by the third-party amusement store management database (DB) 5 In addition to updating the information DB based on the information supplied from each game store 1, the updated latest medium lending management information is distributed to the medium lending management device 27 of each game store 1.

  The biological information recognition device 21 was imaged by the cameras 38-1 to 38-m, the entrance cameras 40-1 to 40-p, the in-store cameras 41-1 to 41-q, and the exit cameras 42-1 to 42-r. Face images pre-registered in the biometric information database 22 based on face image information extracted from the images by the image processing units 39-1 to 39- (m + p + q + r) and supplied via the biometric information bus 31. If the face image registered in the player database 20 is matched between the matching database 19 and the player database 20 generated on the day, the mobile terminal 18 is notified of the visit of the registered player, or the CRT The image is displayed on the display unit 23 such as (Cathode Ray Tube) or LCD (Liquid Crystal Display). Here, the player database 20 is extracted by the image processing units 39-1 to 39- (m + p + q + r) from the face images registered in the biological information database 22 on the same day, and is sent via the biological information bus 31. A face image that matches the supplied face image, that is, a face image that has already been collated, is registered, and that day collation database 19 is registered in the player database 20 from the face image registered in the biometric information database 22. A face image excluding the face image that has been set, that is, a face image that has not been verified, is registered. Further, when the face image registered in the biometric information database 22 is collated and does not match, the biometric information recognition device 21 accesses the biometric information management database 3 and registers it in the unregistered player DB 251 as an unregistered person. .

  The game store management device 24 is a so-called hall computer, and monitors the operations of the game machines 36-1 to 36-m via the game store management information bus 30. The game store management device 24 determines a predetermined amount according to the monitoring status such as information on the payout of the game table 36 or the payout of medals, the call information of the players on the game tables 36-1 to 36-m, or the occurrence of an error. The execution result is executed, and the execution result is displayed on the display unit 25 such as a CRT or LCD. The game store management device 24 identifies information supplied from the counter 35, the game machines 36-1 to 36-m, and the game machine peripheral terminals 37-1 to 37-m, respectively. For example, it is managed by the gaming machine management database 26 in association with the gaming machine number.

  The medium lending management device 27 manages the medium lending management information of the rented game media using the medium lending management database 29 based on the information from the payment machine 33 and the lending machine 34, and also the medium lending management database. When the medium lending management information registered in 29 is updated, the updated information is sent to the third party amusement store management center 4 via the third party amusement store management bus 7 and the public communication line network 9. Further, the medium lending management device 27 acquires the medium lending management information supplied by the third party amusement store management center 4 via the third party amusement store management bus 7 and the public communication line network 9, and manages the medium lending management. Store in the database 29.

  The lending machine 34 lends a number of game media according to the amount when the player accepts a predetermined amount by cash or a prepaid card when playing on the gaming table 36. At this time, the lending machine 34 supplies information on the number of lent gaming media to the medium lending management device 27 together with information such as the accepted cash and the remaining number of prepaid cards. Accordingly, the medium lending management device 27 registers information on the number of lent gaming media in the medium lending management database 29 together with information such as the accepted cash and the remaining number of prepaid cards.

  The checkout machine 33 sells prepaid cards with a frequency for borrowing a ball. At this time, the checkout machine 33 supplies the frequency of the prepaid card sold and the amount paid to the medium lending management device 27. Further, the settlement vending machine 33 settles and pays out cash based on the remaining number of game media lent as a frequency such as a prepaid card. At this time, the checkout machine 33 supplies the remaining number of prepaid cards and the amount of cash refunded to the medium lending management device 27.

  The counter 35 counts the number of game media acquired by the player playing on the game table 36, and outputs the counting result as a magnetic card or a receipt.

  The game machines 36-1 to 36-m execute a game when a predetermined operation is performed by the player, and pay out a game ball or a medal according to a so-called small hit or big hit.

  The game console peripheral terminals 37-1 to 37-m are so-called pedestrian machines provided corresponding to the respective game machines 36-1 to 36-m. The same as the lending machine 34) is provided. Further, the gaming machine peripheral terminal 37 acquires biological information such as a face image of the player who plays the gaming machine 36 and transmits it to the biological information recognition device 21 together with the gaming machine identification information (game machine number). FIG. 1 shows an example in which cameras 38-1 to 38-m that acquire a player's face image are provided as a function of acquiring biometric information.

  For example, as shown in FIG. 2, the cameras 38-1 to 38-m are arranged below the table display lamps 61-1 to 61-4 provided on the respective upper sides of the game tables 36-1 to 36-4. As shown in FIG. 3, a face image may be taken so that the player can take an image within the reading range δ. Can be used.

  Further, as shown in FIG. 4, the cameras 38-1 to 38-m are provided with convex portions 71-1 to 71-4 on the gaming machine peripheral terminals 37-1 to 37-4, as shown in FIG. As described above, it may be provided so that a player's face image can be captured within the reading range θ.

  Further, for example, as shown in FIG. 6, the cameras 38-1 to 38-m may be provided at the center of the game table 36 (on the board surface of the game table 36) to take an image. That is, by installing the camera 38 in the installation unit 81 of FIG. 6, the player is imaged within the reading range φ as shown in FIG.

  The entrance cameras 40-1 to 40-p, the in-store cameras 41-1 to 41-q, and the exit cameras 42-1 to 42-r are installed and taken at entrances and predetermined places in the store of the game store 1. Are supplied to the image processing units 39- (m + 1) to 39- (m + p + q + r), respectively.

  The entrance cameras 40-1 to 40-p, the in-store cameras 41-1 to 41-q, and the exit cameras 42-1 to 42-r are set as shown in FIG. 8, for example. FIG. 8 shows an installation example of entrance cameras 40-1 to 40-p, in-store cameras 41-1 to 41-q, and exit cameras 42-1 to 42-r in the game store 1.

  That is, in FIG. 8, the entrances 112-1 to 112-3 are provided, and the entrance cameras 40-1 to 40-3 capture the players entering from the respective entrances and exits, and exit cameras. 42-1 to 42-3 take an image of the player leaving the store through each of the entrances 112. Further, the in-store cameras 41-1 to 41-10 are set at positions at which both surfaces of the island facilities 111-1 to 111-5 can be imaged in a row. The island facilities 111 are provided with game machines 36 on both sides, that is, so as to sandwich the island facilities 111 in the vertical direction in the figure. Since the camera 38, the entrance camera 40, the in-store camera 41, and the exit camera 42 all have a pan / tilt / zoom function, the in-store cameras 41-1 to 41-10 are arranged as shown in FIG. As a result, all the players playing on the game table 36 can take an image with any of the in-store cameras 41-1 to 41-10.

  Furthermore, the in-store camera 41-a is provided in front of the lending machine 34, the in-store camera 41-b is provided in front of the checkout machine 33, and the in-store camera 41-c is the counter of the counter 35. It is provided in front, and a player who uses the rental machine 34, the checkout machine 33, and the counter 35 can be imaged.

  That is, as shown in FIG. 8, at the gaming store 1, the player who visits (enters) or leaves the store, the player who plays at the gaming table 36, the rental machine 34, the checkout machine 33, and the counting A camera 38, an entrance camera 40, an in-store camera 41, and an exit camera 42 so that almost all of the actions that the player is supposed to take in the game store 1, such as a player using the machine 35, can be monitored. Is installed.

  Next, a configuration example of the image processing unit 39 will be described with reference to FIG.

  The image acquisition unit 201 acquires an image captured by the camera 38 (or the entrance camera 40, the in-store camera 41, or the exit camera 42) and supplies the acquired image to the face image extraction unit 202. The face image extraction unit 202 extracts a rectangular image composed of a face image from the image supplied from the image acquisition unit 201 using a pattern such as the arrangement of the parts constituting the face, and supplies the rectangular image to the transmission unit 203. The transmission unit 203 transmits the face image to the biometric information recognition device 21.

  Next, a configuration example of the biological information recognition device 21 will be described with reference to FIG.

  The face image acquisition unit 221 acquires the face image supplied from the image processing unit 39 and supplies it to the collation unit 222. The collation unit 222 collates the face image acquired by the face image acquisition unit 221 with the registered player's face image registered in advance in the biometric information DB 22, and if there is a face image that is a candidate with a high degree of similarity. The face images up to the third candidate are displayed on the display unit 23 as the matching result. Further, the collation unit 222 supplies the supplied face image to the unregistered player database registration unit 223 when there is no face image that is a candidate with high similarity.

  More specifically, the feature amount extraction unit 231 of the matching unit 222 extracts a feature amount for identifying a face image, and supplies the feature amount together with the face image to the similarity calculation unit 232. The similarity calculation unit 232 includes a camera determination unit 232a, a player DB determination unit 232b, and a current day verification DB determination unit 232c, and controls them to the current day verification DB 19, the player DB 20, or the biological information DB 22. In addition to extracting the feature amount of the registered player's facial image, the feature amount supplied from the feature amount extraction unit 231 is used to register in the matching database 19, player DB 20, or biometric information DB 22 on the day. The similarity with all registered player's face images is obtained, and the face images supplied from the face image acquisition unit 221 and the face images with the third highest similarity are displayed in the similarity determination unit 233. Supply. More specifically, the similarity calculation unit 232, for example, based on various facial feature amounts such as the ratio between the distance between the eyes, the distance from the chin to the forehead, and the length from the chin to the nose, Each difference sum, average ratio, or ratio sum is obtained as the similarity.

  The similarity determination unit 233 includes a similarity between the similarity of the face image having the top three similarity levels supplied from the similarity calculation unit 232, and a predetermined threshold value. And the first registered face image is similar to the face image supplied from the face image acquisition unit 221 based on the comparison result (the higher the similarity, the more similar the face image is) If the similarity is higher than a predetermined threshold, or if the similarity is lower, the similarity is lower than the predetermined threshold) Information on the image and the similarity is supplied to the display unit 23 and is displayed to the communication unit 224. In addition, the similarity determination unit 233 compares the similarity between the face image ranked first and a predetermined threshold value, and the registered face image ranked first is compared with the face image acquisition unit 221 based on the comparison result. When the face image supplied is not similar, the face image supplied from the face image acquisition unit 221 is supplied to the unregistered player database registration unit 223.

  The unregistered player database registration unit 223 registers the face image, which has been supplied as being unregistered by the verification unit 222, in the unregistered player DB 251 of the biometric information management database 3.

  The operation unit 225 includes buttons, a mouse, a keyboard, and the like. The operation unit 225 is operated when any one of the face images displayed on the display unit 23 with the above-mentioned similarity ranked in the top three is selected. Is supplied to the communication unit 224. The communication unit 224 includes a modem or the like, and distributes the selected face image to the mobile terminal 18 based on an operation signal from the operation unit 225.

  Here, for example, the similarity indicates a higher value as it is closer to the face image registered as a registered player as indicated by the ratio sum, and the similarity is a value higher than a predetermined threshold value. In this case, an example will be described in which it is determined that the face image of the registered player corresponding to the similarity is. However, for example, when the similarity is expressed as a difference sum in each feature amount between the captured face image and the face image registered as the registered player, the similarity determination unit 233 determines that the similarity is a threshold value. If it is smaller than that, the captured face image is regarded as a registered player's face image, or in the case of an average ratio or the like, it is greater than or equal to a predetermined value in the range of 0 to 1 and close to 1. If it is a value, it can be considered that they are the same person.

  When a new registered player database 252 (FIG. 11) is distributed from the biometric information management center 2, the database management unit 226 updates the biometric information DB 22 based on the new registered player database 252.

  The day database management unit 227 includes a day management unit 227a, a player management unit 227b, a store visitor information reading unit 227c, and a store visitor information update unit 227d, and the face image notified of the store visit by the communication unit 224. Based on this information, the player management unit 227b is controlled to register in the player DB 20 information on the face image of the player who came to the store. Further, the current day database management unit 227 controls the same day management unit 227a to check the information obtained by deleting the facial image information registered in the player DB 20 from the facial image information registered in the biological information DB 22 on the current day. Register in DB19.

  Further, the day database management unit 227 controls the store visitor information reading unit 227c and the store visitor information updating unit 227d, and the biometric information management center information receiving unit 229 and the biometric information management center information transmitting unit 228 are used to Various information is exchanged with the information management center 2.

  Next, a configuration example of the biological information management center 2 will be described with reference to FIG.

  The biometric information management center 2 includes a DB distribution unit 241, a DB update unit 242, and a DB update determination unit 243. The registered player DB 252 stored in the biometric information management DB 3 is transferred to the unregistered player DB 251. Update based on. More specifically, the DB update determination unit 243 has a built-in RTC (Real Time Clock) 243a that generates time information. When a predetermined time elapses based on the built-in RTC 243a, the biological information management DB3 is accessed and it is determined whether or not a new unregistered player is registered in the unregistered player DB 251.

  When a new unregistered person is registered in the unregistered player DB 251, the DB update determination unit 243 notifies the DB update unit 242 to that effect. The DB update unit 242 accesses the unregistered player DB 251 to determine whether or not there is an unregistered player that has been registered a predetermined number of times or more among registered unregistered players. When there is an unregistered player registered as an unregistered player, the registered player DB 252 is read, and an unregistered player who has been registered a predetermined number of times or more is registered in the registered player DB 252 and updated. Further, when the registered player DB 252 is updated, the DB update unit 242 notifies the DB distribution unit 241 that it has been updated.

  When notified from the DB update unit 242 that the registered player DB 252 has been updated, the DB distribution unit 241 accesses the biometric information management DB 3 and reads the registered player DB 252 to recognize the biometric information of each gaming store 1. Delivered to the device 21.

  Based on the request from the amusement store entrance customer information request unit 246, the amusement store entrance customer information management unit 244 inputs the information in the matching database 19 on the day transmitted from the biometric information recognition device 21 of each amusement store 1. The store entrance information receiving unit 247 is controlled and received as store customer information. Further, the amusement store entrance customer information management unit 244 controls the difference calculation unit 244a to provide the difference information (the difference between the day verification DB 19 of the entrance customer information supplied from each amusement store 1 and the biometric information management DB 3 ( Together with information for identifying the amusement store 1, by obtaining information on a set of face images that is the difference between the set of face images registered in the matching database 19 on the day and the set of face images registered in the biometric information management DB 3. accumulate. In addition, the game store customer information management unit 244 controls the summation unit 244b to add other difference information excluding the difference information of each game store 1, and controls the game store customer information transmission unit 245. Then, the difference information is removed and transmitted to the biological information recognition device 21 of the game store 1.

  The amusement store entrance customer information request unit 246 includes an RTC (Real Time Clock) 246a, and requests the amusement store entrance information from the biometric information recognition device 21 of each amusement store 1 at predetermined time intervals.

  Next, a configuration example of the mobile terminal 18 will be described with reference to FIG.

  The communication unit 271 is configured by a modem or the like, and exchanges data with the biometric information recognition device 21 via a wireless communication network in the game store 1. In addition, the communication unit 271 acquires information indicating that a player with a facial image similar to the facial image supplied from the image processing unit 39, which is distributed from the biometric information recognition device 21, has visited the store. 272.

  The image processing unit 272 is a display constituted by an LCD or the like based on information indicating that a player with a face image similar to the face image supplied from the image processing unit 39 supplied from the communication unit 271 has visited the store. In addition to generating an image to be displayed on the unit 273, the image is displayed on the display unit 273.

  Next, the registered player visit monitoring process will be described with reference to the flowchart of FIG.

  In step S1, the camera 38, the entrance camera 40, the in-store camera 41, or the exit camera 42 determines whether or not a predetermined time has elapsed, and repeats the process until the predetermined time has elapsed. If it is determined in step S1 that the predetermined time has elapsed, in step S2, the camera 38, the entrance camera 40, the in-store camera 41, or the exit camera 42 captures an image of the installed range and captures the image. The image is supplied to the image processing unit 39. The image acquisition unit 201 of the image processing unit 39 acquires the supplied image and supplies it to the face image extraction unit 202.

  In step S <b> 3, the face image extraction unit 202 extracts a player's face image from the supplied image and supplies the extracted image to the transmission unit 203. More specifically, the face image extraction unit 202 extracts a face image from, for example, an arrangement of a characteristic part such as an eye or a nose, where the skin is exposed from the color of the captured image. To the transmission unit 203.

  In step S4, the face image extraction unit 202 determines whether or not the face image can be extracted. If the face image cannot be extracted, the process returns to step S1. That is, the processes in steps S1 to S4 are repeated until a face image is captured.

  When it is determined in step S4 that a face image has been extracted, that is, it is determined that a face image exists in the captured image, in step S5, the face image extraction unit 202 transmits the extracted face image to the transmission unit 203. To supply. The transmission unit 203 transmits the face image supplied from the face image extraction unit 202 to the biological information recognition apparatus 21. At this time, the transmission unit 203 adds a camera ID for identifying each of the camera 38, the entrance camera 40, the in-store camera 41, or the exit camera 42, transmission time information, and the like to the biometric information recognition device 21. Send.

  In step S21, the face image acquisition unit 221 of the biometric information recognition device 21 determines whether or not a face image has been transmitted, and repeats the same processing until it is transmitted. In step S21, for example, when a face image has been transmitted by the process of step S5, the process proceeds to step S22.

  In step S22, the face image acquisition unit 221 acquires the transmitted face image. In step S <b> 23, the face image acquisition unit 221 extracts any unprocessed one of the supplied face images and supplies the extracted unprocessed one to the feature amount extraction unit 231.

  In step S24, the feature amount extraction unit 231 of the collation unit 222 extracts the feature amount from the supplied face image and supplies it to the similarity calculation unit 232 together with the face image.

  In step S25, the similarity calculation unit 232 controls the camera determination unit 232a to determine whether the face image supplied from the feature amount extraction unit 231 is captured by the camera 38 or the entrance camera 40. Let it be judged.

  In step S25, for example, when the face image supplied from the feature amount extraction unit 231 is captured by the camera 38 or the entrance camera 40, a matching process is executed in step S26.

  Here, the matching process will be described with reference to the flowchart of FIG.

  In step S51, the similarity calculation unit 232 controls the player DB determination unit 232b to determine whether or not a face image registered in the player DB 20 exists. In step S51, for example, in the case of the first process, since a face image is not registered in the player DB 20, a new collation process is executed in step S55.

  Here, the new collation process will be described with reference to the flowchart of FIG.

  In step S81, the similarity calculation unit 232 controls the current day verification DB determination unit 232c to determine whether or not a face image is registered in the current day verification DB 19. In step S81, for example, in the case of the first process, since the face image is not registered in the current day verification DB 19, the process proceeds to step S82.

  In step S <b> 82, the similarity calculation unit 232, for the face image supplied from the feature amount extraction unit 231, the ratio of the eye-to-eye spacing, the length from the chin to the forehead, and the length from the chin to the nose, and the like. Using the various feature values of the face and the similar feature values in the face image registered in the biometric information DB 22 (registered in the registered player DB 252), the difference sum, average ratio, or ratio The sum or the like is calculated as the similarity, and the ranking of the similarity with the face image registered in the registered player DB 252 as the calculation result is obtained, and the top three of the face images registered in the registered player DB 252 The information on the degree of similarity with the face image up to and including the face image supplied from the feature amount extraction unit 231 is supplied to the similarity determination unit 233.

  In step S83, the similarity determination unit 233 determines whether the highest similarity is larger than a predetermined threshold based on the top three face images and similarity information supplied from the similarity calculation unit 232. Determine whether or not. That is, the similarity determination unit 233 is a registered player who is most similar (a registered game that is most similar to the facial image acquired by the facial image acquisition unit 221 among facial images registered in the biometric information DB 22). In this case, the similarity of the registered player having the highest similarity is compared with a predetermined threshold.

  Note that, as described above, the similarity between the face image of the registered player who is most similar to the captured face image is not necessarily the highest because of the definition of the similarity. And the threshold value may differ from those in this example.

  If it is determined in step S83 that the highest similarity is larger than the predetermined threshold, in step S84, the similarity determination unit 233 determines that the top third facial image supplied from the similarity calculation unit 232 is the top three. A notification screen 301 indicating that it is a candidate for a registered player's face image is displayed by controlling the display unit 23.

  At this time, for example, a notification screen 301 as shown in FIG. 16 is displayed on the display unit 23.

  In the notification screen 301 of FIG. 16, a camera image display field 311 is provided in the middle left, and the face image supplied from the image processing unit 39 is displayed. Also, on the right side, face image display fields 312-1 to 312-3 of registered players of the top three in the similarity from the first candidate to the third candidate are provided in descending order of similarity. Further, similarity level display fields 313-1 to 313-3 are provided below the face image display fields 312-1 to 312-3 of each registered player, and the level of similarity is displayed. . In FIG. 16, the horizontal length of the area shown in black indicates the magnitude of similarity.

  Further, ID display fields 314-1 to 314-3 are provided at corresponding positions below the similarity level display fields 313-1 to 313-3, and the face images in the biological information DB 22 of each face image. In FIG. 16, “00051”, “00018”, and “00022” are displayed from the left in FIG.

  Furthermore, below the ID display fields 314-1 to 314-3, confirmation buttons 318-1 to 318-3 operated by the operation unit 225 when each candidate is selected are provided at the corresponding positions. It has been.

  A camera ID display field 315 for identifying the camera that captured the face image is provided under the camera image display field 311. In FIG. 16, the camera 38 and the entrance camera 40 are identified. “Camera 02” is displayed as the camera ID. Furthermore, a time display field 316 is provided below the camera ID display field 315, and the time taken by the entrance camera 40 is displayed. In FIG. 16, “18:23:32” is displayed. It is shown that the face image in the camera image display field 311 is captured at 18:23:32.

  Furthermore, another person button 317 is provided below the time display field 316, and the face image display fields 312-1 to 312- of the registered player whose face images of the camera image are the first to third candidates. 3 is operated by the operation unit 225 when it is regarded as not similar to any of 3.

  In step S85, the communication unit 224 displays on the display unit 23 whether or not any of the candidate face images has been selected by operating the operation unit 225, for example, the notification screen 301 shown in FIG. If it has been determined, it is determined whether any of the confirmation buttons 318-1 to 318-3 has been operated by the operation unit 225.

  In step S85, for example, when the confirm button 318-1 is operated, it is considered that the face image that is the first candidate is selected, and in step S86, the communication unit 224 determines the face image that is the selected first candidate. Is transmitted to the portable terminal 18 and the database management unit 227 on the day, and the fact that the corresponding registered player has visited the store is notified.

  In step S111, the communication unit 271 determines whether or not the registered player has been notified of the store visit, and repeats the processing until the notification is received. For example, when a registered player's visit is notified in step S <b> 86 in step S <b> 86, in step S <b> 112, the communication unit 271 notifies the registered player's visit that is transmitted from the biometric information recognition device 21. , The registered player's face image and the captured camera image transmitted together with the notification are supplied to the image processing unit 272. The image processing unit 272 processes the information of the selected face image and the captured camera image into information in a format that can be displayed on the display unit 273, and displays the information on the display unit 273 in step S113.

  By the above processing, the staff in the game store 1 can recognize the visit of the registered player if the portable terminal 18 is possessed.

  In step S87, the current day database management unit 227 controls the player management unit 227b to register the registered player face of the selected candidate face image among the registered player face images registered in the biometric information DB 22. The image is registered in the player DB 20, for example, as shown in FIG.

  That is, in FIG. 17, the face images F111 to F115 are registered in the biometric information DB 22, but when the registered player's face image of the selected candidate face image is the face image F111, the process of step S87 is performed. As shown by the solid line in the figure, the face image F111 is read from the biological information DB 22, and the copy data is registered in the player DB 20 as the face image F111 ′.

  At this time, the player DB 20 is, for example, as shown in FIG. In FIG. 18, the customer ID, customer ID, registered face image, store entry time, and game points are recorded from the left. The customer ID on the day is a serial number in the player DB 20, and in FIG. 18, “0001”, “0002”, and “0003” are attached in order from the top. The customer ID is an ID in the biometric information DB 22 and is given “0001”, “0003”, and “0008” from the top in FIG. The entrance time is a time when an image including a registered face image is taken. In FIG. 18, “2006/1/1 9:05”, “2006/1/1 9:10” And “2006/1/1 10:01”. The gaming point is a point that is added every time a player plays on the gaming table 36, and is a face image captured by the camera 38, and is added when it is recognized that a game is played on the gaming table 36, In FIG. 18, “1”, “1”, and “3” are described from the top.

  In step S88, the current day database management unit 227 controls the same day management unit 227a to remove the face image registered in the player DB 20 from the registered player face images registered in the biometric information DB 22. For example, as shown in FIG. 17, the image is registered in the current day verification DB 19.

  That is, in FIG. 17, the face images F111 to F115 are registered in the biometric information DB 22, but when the registered player's face image of the selected candidate face image is the face image F111, the process of step S88 is performed. As indicated by the one-dot chain line in the figure, the face image F111 is removed from the biometric information DB 22, the face images F112 to F115 are read, and the copy data is stored in the matching database 19 on the day as the face images F112 ′ to F115 ′. Registered as

  At this time, the current day verification DB 19 is, for example, as shown in FIG. In FIG. 19, a customer ID, a registered face image, and game points are recorded from the left. The customer ID is an ID in the registered player DB 252 of the biometric information DB 22. In FIG. 19, “0002”, “0004”, “0005”, “0006”, “0007”, “0009”, and “0009” 0010 ". The game point is a face image captured by the camera 38 and is attached when it is recognized that the game is played on the game table 36, and is all described as “0” in FIG. .

  The biometric information DB 22 is registered as shown in FIG. In FIG. 20, the customer ID, registered face image, store visit point, and game point are recorded from the left. The customer ID is a serial number in the registered player DB 252 of the biometric information DB 22 and is given “0001” to “0010” from the top in FIG. The store visit point is a face image taken by the entrance camera 40, and is attached when it is recognized that the store has visited the amusement store 1. In FIG. 20, "2", "6" ”,“ 10 ”,“ 5 ”,“ 83 ”,“ 153 ”,“ 136 ”,“ 24 ”,“ 97 ”, and“ 1 ”. The game point is a face image captured by the camera 38 and is attached when it is recognized that a game is played on the game table 36. In FIG. 20, "6", "18" from the top. , “15”, “7”, “106”, “174”, “150”, “35”, “99”, and “2”.

  In this way, the biometric information DB 22 is configured as shown in FIG. 20, and the player DB 20 and the current day verification DB 19 are generated based on the information of the biometric information DB 22.

  In addition, in the matching database 19 on the day, the degree of similarity with a face image that has already been matched, that is, a face image of another player (a person to be verified) is higher than a predetermined threshold and is regarded as the same. Since the registered player's face image is omitted, the number of similarity calculation processes can be reduced by the smaller number of face images to be collated, so that the processing speed can be improved. . In addition, since the face image that has already been collated is deleted and the collation process is performed using the face image of the collation DB 19 on the day from which unnecessary face images are removed, it is possible to improve the collation accuracy of the collation process. Become.

  On the other hand, in step S85, no candidate face image is selected. For example, when the other person button 317 on the notification screen 301 in FIG. 16 is pressed, or in step S83, the similarity calculation unit 232 supplies the face image. Based on the information of the top three face images and the similarity, the highest similarity is not greater than a predetermined threshold, that is, even the face image of the most similar registered player If the similarity is less than the predetermined threshold, the similarity determination unit 233 supplies the face image supplied from the image processing unit 39 to the unregistered player database registration unit 223 in step S89. The unregistered player database registration unit 223 accesses the biometric information management database 3 through the biometric management information bus 6 and the public communication line network 8 to register the supplied face image in the unregistered player DB 251.

  On the other hand, when it is determined in step S81 that the face image is registered in the matching database 19 on the day, the similarity calculation unit 232 determines the eye and eye of the face image supplied from the feature amount extraction unit 231 in step S90. Using various facial feature quantities such as the distance between the eyes, the length from the chin to the forehead, and the ratio of the length from the chin to the nose, and similar feature quantities in the face image registered in the matching database 19 on the day Then, each difference sum, average ratio, or ratio sum is calculated as the similarity, and the ranking of the similarity with the face image registered in the current day verification DB 19 as the calculation result is obtained and registered in the current day verification DB 19 Information on the degree of similarity to the top three face images among the face images is supplied to the similarity determination unit 233 together with the face image supplied from the feature amount extraction unit 231.

  In step S91, the similarity determination unit 233 determines whether the highest similarity is greater than a predetermined threshold based on the top three face images and similarity information supplied from the similarity calculation unit 232. Determine whether or not.

  If it is determined in step S91 that the highest similarity is greater than a predetermined threshold, in step S92, the similarity determination unit 233 determines that the top third facial image supplied from the similarity calculation unit 232 is the top three. A notification screen 301 indicating that it is a candidate for a registered player's face image is displayed by controlling the display unit 23.

  In step S93, the communication unit 224 determines whether any of the candidate face images has been selected by operating the operation unit 225.

  In step S93, when the face image that is the first candidate is selected, in step S94, the communication unit 224 displays the selected face image that is the first candidate and the captured camera image on the mobile terminal 18 and the current day database management. This is transmitted to the section 227 to notify that the corresponding registered player has visited the store.

  In step S95, the current day database management unit 227 controls the player management unit 227b to register the registered player face of the selected candidate face image among the registered player face images registered in the current day verification DB 19. The image is registered in the player DB 20.

  In step S96, the current day database management unit 227 controls the current day management unit 227a, and among the registered player face images registered in the current day verification DB 19, the face image registered in the player DB 20 by the process in step S95. Is deleted.

  That is, as shown in FIG. 21, when the face image F101 ′ registered in the matching database 19 on the day is selected as a candidate face image, the face image 101 is copied to the player DB 20 by the process of step S95. The face image F101 ′ that is the selected candidate face image is deleted by the process of step S96.

  As described above, once the current day verification DB 19 is generated, the face images selected as candidate face images thereafter move sequentially from the current day verification DB 19 to the player DB 20.

  For this reason, as the number of candidate face images increases, that is, as the number of face images registered in the player DB 20 increases, the number of face images registered in the matching database 19 on the day decreases sequentially. As a result, as the number of face images registered in the current day verification DB 19 to be verified decreases, the number of similarity calculation processes can be sequentially decreased, so that the processing speed can be improved. Furthermore, since the collation process is performed using the face image of the day collation DB 19 from which unnecessary face images are removed, the collation accuracy of the collation process can be improved.

  Now, the description returns to the flowchart of FIG.

  When it is determined in step S51 that a face image is registered in the player DB 20, in step S52, the similarity calculation unit 232 determines the eye and eye for the face image supplied from the feature amount extraction unit 231. Using various face feature amounts such as the interval, the length from the chin to the forehead, and the ratio of the length from the chin to the nose, and the similar feature amounts in the face images registered in the player DB 20, Each difference sum, average ratio, or sum of ratios is calculated as a similarity, and the ranking of the similarity with the face image registered in the player DB 20 as the calculation result is obtained, and the similarity with the top face image is calculated. Is supplied to the similarity determination unit 233 together with the face image supplied from the feature amount extraction unit 231.

  In step S <b> 53, the similarity determination unit 233 determines whether the highest similarity supplied from the similarity calculation unit 232 is greater than a predetermined threshold.

  If it is determined in step S53 that the highest degree of similarity is greater than the predetermined threshold value, in step S54, the similarity degree determination unit 233 displays the highest-order face image supplied from the similarity calculation unit 232 on the day. The data is supplied to the database management unit 227. The database management unit 227 on the day controls the player management unit 227b to access the player DB 20, and adds and updates the game points corresponding to the supplied face image.

  In other words, the face image registered in the player DB 20 is registered at the time when the face image is captured by the entrance camera 40, and is subsequently captured by the camera 38 provided for each gaming table 36. So game points will be added.

  Now, the description returns to the flowchart of FIG.

  When the collation process in step S26 ends, in step S27, the face image acquisition unit 221 determines whether or not all of the supplied face images have been processed, and if there is an unprocessed face image, The process returns to step S23. That is, the processes in steps S22 to S29 are repeated until the process is performed on all face images. If it is determined that the process has been completed for all face images, the process returns to step S21.

  On the other hand, when it is determined in step S25 that the image is not captured by the entrance camera 40 or the camera 38, in step S28, the similarity calculation unit 232 controls the camera determination unit 232a to control the feature amount extraction unit. It is determined whether the face image supplied from H.231 is taken by the exit camera 42. In step S28, for example, when it is determined that the image is captured by the exit camera 42, exit camera processing is executed in step S29.

  Here, the exit camera process will be described with reference to the flowchart of FIG.

  In step S131, the similarity calculation unit 232, for the face image supplied from the feature amount extraction unit 231, a ratio between the eye-to-eye spacing, the length from the chin to the forehead, and the length from the chin to the nose, and the like. The difference sum, average ratio, ratio sum, etc. are calculated as similarities using the various face feature amounts and the similar feature amounts in the face images registered in the player DB 20, and the calculation results The ranking of the similarity with the face image registered in the player DB 20 is obtained, and information on the top face image among the face images registered in the player DB 20 is supplied to the database management unit 227 on the day. To do.

  In step S132, the current day database management unit 227 controls the same day management unit 227a, and among the registered player's face images registered in the player DB 20, the face image having the highest similarity is checked on the same day DB 19 Register with.

  In step S133, the current day database management unit 227 controls the current day management unit 227a, and among the registered player face images registered in the player DB 20, the face image registered in the current day verification DB 19 by the process in step S132. Is deleted.

  That is, as shown in FIG. 23, when the face image F121 registered in the player DB 20 is the face image having the highest similarity, the face image 121 ′ is stored in the matching database 19 on the day by the process of step S132. The face image F121 that has been copied and has the highest similarity is deleted by the process of step S133.

  As a result, the face image of the player who has left the game store 1 will not be treated as a face image that has already been collated, and therefore, when the same player re-enters the store, use it for collation. Is possible.

  Now, the description returns to the flowchart of FIG.

  In step S28, if the image is not an image captured by the exit camera 42, that is, is not an image of the camera 38, the entrance camera 40, or the exit camera 42, but is an image captured by the in-store camera 41, the process proceeds to step S27. Proceed to That is, in this process, the face image obtained from the image captured by the in-store camera 41 is not used for collation.

  Through the above processing, when a player who has entered the store leaves the store, the face image of the player moves from the player DB 20 to the matching DB 19 on the day. As a result, the face image of the player who has entered the store is registered in the player DB 20, and the face image of the player who has not entered the store is registered in the matching DB 19 on the day.

  As a result, only the minimum necessary face image in which the face image that has already been collated with the face image is always registered is registered in the day-of-day collation DB 19 used for the face image collation. This makes it possible to minimize the number of times the calculation process is performed, thereby improving the processing speed and registering only the minimum face image necessary for the collation process from which unnecessary face images are removed. In addition, since the matching process is performed using the face image in the matching database 19 on the day, it is possible to improve the matching accuracy of the matching process.

  Next, with reference to the flowchart of FIG. 24, the game store customer information collection processing will be described.

  In step S151, the game store customer information request unit 246 determines whether or not it is time to request game store customer information based on the time information generated by the RTC 246a. The process is repeated until it is time to request information.

  If it is determined in step S151 that it is time to request game store customer information, in step S152, the game store customer information request unit 246 sends the biometric information recognition device 21 of the unprocessed game store 1 to the biological information recognition device 21. In response to this, information requesting the game store visitor information is transmitted.

  In step S171, the current day database management unit 227 controls the biometric information management center information receiving unit 229 to determine whether or not game store customer information has been requested from the biometric information management center 2. In step S171, for example, when game store customer information is requested by the processing of step S152, in step S172, the database management unit 227 controls the customer information reading unit 227c on the day, and stores the customer information. Of the information, information in the current day verification database 19 is read out and transmitted to the biological information management center 2 by the biological information management center information transmission unit 228. At this time, the biometric information management center information transmitting unit 228 transmits the information on the day matching database 19 as the customer information with the information for identifying its own gaming store 1 being transmitted.

  In step S153, the amusement store entrance customer information receiving unit 247 receives the entrance customer information transmitted from the biological information recognition device 21 of the unprocessed amusement store 1, and sends it to the amusement store entrance customer information management unit 244. Supply.

  In step S154, the game store customer information management unit 244 reads the information of the registered player DB 252 of the biometric information management DB 3.

  In step S155, the amusement store entrance customer information management unit 244 controls the difference calculation unit 244a so that the facial image information registered in the registered player DB 252 of the biometric information management DB 3 and the unprocessed amusement store 1 are processed. Difference information (information consisting of a difference set of a set of mutual face images) from the face image information registered in the day-to-day verification database 19 which is store visitor information transmitted from the biometric information recognition device 21 Let That is, since the face image registered in the matching database 19 on the day is a face image in which a matching face image is not detected by the matching, the difference information obtained here is at least at each amusement shop 1. This is information about the player's face image.

  In step S156, the amusement store entrance customer information management unit 244 holds the difference information obtained by the difference calculation unit 244a in association with information for identifying the amusement store 1 that has transmitted the entry customer information.

  In step S157, the amusement store entrance customer information management unit 244 determines whether or not there is an unprocessed amusement store 1, that is, whether or not there is an amusement store 1 that does not request transmission of the entrance customer information. If there is an unprocessed game store 1, the process returns to step S152. That is, the process of steps S152 to S157 is performed until the customer information is acquired from the biometric information recognition devices 21 of all the game stores 1 and the difference information from the registered player DB 252 of the biometric information management DB3 is obtained. Will be repeated.

  In step S157, when there is no unprocessed game store 1, that is, the customer information is acquired from the biometric information recognition devices 21 of all the game stores 1, and the difference information from the registered player DB 252 of the biometric information management DB 3 is obtained. In step S158, the game store customer information management unit 244 controls the summation unit 244b to obtain all the difference information except the difference information of the unprocessed game store 1. Generate summed information. That is, the total information is information including a set of face images of the players who have visited all the game stores 1 except the unprocessed game store 1 (the game store 1 to which the total information is to be transmitted).

  In step S159, the amusement store entrance customer information management unit 244 controls the amusement store entrance customer information transmission unit 245 to transmit the total information to the unprocessed amusement store 1.

  In step S173, the current day database management unit 227 controls the biometric information management center information receiving unit 229 to determine whether or not the total information has been transmitted from the biometric information management center 2. In step S173, for example, when the sum information is transmitted by the process of step S159, in step S174, the biological information management center information receiving unit 229 receives the transmitted sum information, and the database management unit 227 on the day. To supply. The current day database management unit 227 controls the current day management unit 227a to delete the facial image information transmitted as the summation information from the facial image information currently registered in the current day verification database 19.

  In other words, the total information is information consisting of the face images of the players who have visited all the game stores 1 except for their own game store 1, in other words, already verified in all other game stores 1. This is the face image information. Therefore, the face image included in the summation information does not need to be used for matching in the own game store 1 and is deleted from the matching database 19 on the day.

  On the other hand, in step S160, the game store customer information management unit 244 determines whether or not there is an unprocessed game store 1, that is, a game store 1 that has not transmitted the summation information. If it is determined that the store 1 exists, the process returns to step S158. That is, the processes of steps S158 to S160 are repeated until there is no unprocessed game store 1. If it is determined in step S160 that the total information has been transmitted to all the game stores 1, that is, it is determined that there is no unprocessed game store 1, in step S161, the game store customer information request unit The time 246 sets the time for requesting the next game store customer information, and the process returns to step S151.

  With the above processing, the face image already verified in the other game shop 1 is deleted from the matching database 19 on the day, so that the time required for the matching process is shortened. By eliminating the matching process with the unnecessary face image, it is possible to accurately match the face image by leaving only the face image necessary for the matching process.

As a result, it is possible to improve the processing speed and collation accuracy of the collation process using face images.
Next, the update process for the registered player DB 252 will be described with reference to the flowchart of FIG.

  In step S181, the DB update determination unit 243 of the biometric information management center 2 makes an inquiry to the RTC 243a to determine whether a predetermined time has elapsed, and repeats the process until the predetermined time has elapsed. For example, when it is determined in step S181 that the predetermined time has elapsed, in step S182, the DB update determination unit 243 accesses the unregistered player DB 251 of the biometric information management DB 3, and a new unregistered player is newly registered. It is determined whether or not it is registered, and the processes of steps S181 and S182 are repeated until it is determined that a new unregistered player is registered.

  In step S182, for example, when an unregistered player is newly registered by the process of step S89, the DB update determination unit 243, in step S183, the unregistered game newly registered in the unregistered player DB 251. It is determined whether or not one of the persons has been registered a predetermined number of times or more. If not, the process returns to step S181.

  On the other hand, in step S183, for example, if it is determined that there is an unregistered player registered in the unregistered player DB 251 a predetermined number of times or more, the DB update determination unit 243 determines that the DB update unit 242 The registered player DB 252 is notified that it should be updated. In response to this, the DB update unit 242 accesses the unregistered player DB 251 and reads out all the face image information of unregistered players that have been registered a predetermined number of times or more, and accesses the registered player DB 252. Then, an ID for identifying the face image is added to the information of the face image of the unregistered player who has been registered a predetermined number of times or more, and is additionally registered in the registered player DB 252 and updated. Furthermore, the DB update unit 242 notifies the DB distribution unit 241 that the registered player DB 252 has been updated. When the update of the registered player DB 252 is completed, unregistered players that have been registered a predetermined number of times or more are deleted from the unregistered player DB 251.

  In step S185, the DB distribution unit 241 accesses and reads the newly updated registered player DB 252 of the biometric information management DB 3, and reads the registered player DB 252 read to the database management unit 226 of the biometric information recognition device 21. To deliver.

  In step S191, the database management unit 226 determines whether or not a new registered player DB 252 updated from the biometric information management center 2 has been distributed, and repeats the process until it is distributed.

  In step S191, for example, when the newly updated registered player DB 252 is distributed from the DB distribution unit 241 of the biological information management center 2 by the processing in step S185, the database management unit 226 distributes in step S192. The biometric information DB 22 is updated based on the information of the registered player DB 252 as well as the registered player DB 252 that is received. More specifically, the database management unit 226 copies and overwrites the newly distributed information of the registered player DB 252 in the biometric information DB 22.

  As a result of the above processing, when one of the gaming stores 1-1 to 1-n is registered in the unregistered player DB 251 as an unregistered player a predetermined number of times or more, it is additionally registered in the registered player DB 252. Since the database is registered in the biometric information DB 22 of any of the biometric information recognition devices 21 of the game stores 1-1 to 1-n, registration is performed when a face image is captured in a plurality of game stores 1 as well. The visit to the store will be notified as a player. In addition, since the registered player DB 252 is updated based on information from each of the game stores 1-1 to 1-n, it is possible to generate customer store records at a plurality of stores, and to integrate customer store records. Management is possible.

  By the way, in the above-described embodiment, not only face images that have already been collated in their own game store 1 but also face images that have been collated in other game stores 1 are deleted from the database used for collation. In this example, the number of face images used for collation is limited to improve collation processing speed and collation processing accuracy. However, in the above-described processing, the face image once targeted for collation processing is described. Is deleted from the database, for example, when each player tries to check how long on which game table 36 he / she has played, the face image used for the matching process at his / her own game store 1 Cannot be deleted from the database, and the face image to be processed cannot be restricted.

  Therefore, even in the same gaming store 1, collation is performed on a face image that has been collated and is considered to have been matched by collation with a face image acquired at a position far from the position where the face image is obtained. It may be deleted from the database to be used, and the face image used for collation may be limited according to the position in the game store 1.

  FIG. 26 shows the configuration of another embodiment of the monitoring system that restricts the face image used for collation according to the position in the game store 1. In the monitoring system of FIG. 26, the same components as those of the monitoring system of FIG. 1 are denoted by the same reference numerals, and description thereof will be omitted as appropriate.

  In FIG. 26, an identification information list 402, a partial biological information database 403, and a biological information recognition device 401 are provided in place of the current day verification database 19, the player database 20, and the biological information recognition device 21.

  The identification information list 402 is a list including information on the position of the gaming table 36 on which the player of the face image used for collation is playing. The partial biological information database 403 is a database in which face images used for collation are registered. The biometric information recognition device 401 has the same basic functions as the biometric information recognition device 21, but extracts only a facial image used for matching from the biometric information DB 22 based on the identification information list 402, and performs partial biometric information. A database 403 is generated, and a face image matching process is executed based on the partial biological information database 403. That is, the partial biometric information database 403 corresponds to the same day verification database 19 in FIG.

  Next, with reference to FIG. 27, the structural example of embodiment of the biometric information recognition apparatus 401 is demonstrated. In addition, about the structure similar to the structure in the biometric information recognition apparatus 21 in FIG. 10, the same code | symbol is attached | subjected and the description shall be abbreviate | omitted.

  The partial biological information DB generation unit 451 includes a remote extraction unit 451a and a difference calculation unit 451b, and controls them to generate a partial biological information DB 403 based on information in the identification status list 402 and the biological information DB 22. .

  The list generation unit 452 generates the identification status list 402 based on the matching result supplied from the matching unit 222 and the gaming machine number corresponding to the camera ID.

  The similarity calculation unit 461 extracts the feature amount of the player's face image registered in the partial biological information DB 403 and uses the partial biological information using the feature amount supplied from the feature amount extraction unit 231. The similarity with all the registered player's face images registered in the DB 403 is obtained, and the face image supplied from the face image acquisition unit 221 and the face image with the highest similarity are used as the similarity determination unit 462. To supply. More specifically, the similarity calculation unit 461, for example, based on various facial feature amounts such as the ratio between the distance between the eyes, the distance from the chin to the forehead, and the length from the chin to the nose, Each difference sum, average ratio, or ratio sum is obtained as the similarity.

  Accordingly, in FIG. 27, the similarity determination unit 462 compares the similarity with the face image having the highest similarity supplied from the similarity calculation unit 461 with a predetermined threshold value, and obtains a comparison result. Based on this, when the registered face image with the highest similarity is similar to the face image supplied from the face image acquisition unit 221 (when the similarity is greater than the threshold), the highest face Information about the image and similarity is supplied to the presence determination unit 463. Further, the similarity determination unit 462 compares the similarity between the highest-ranking face image and a predetermined threshold value, and based on the comparison result, the highest-level registered face image is received from the face-image acquiring unit 221. When it is not similar to the supplied face image (when the similarity is smaller than the threshold value), the face image supplied from the face image acquisition unit 221 is supplied to the unregistered player database registration unit 223.

  The presence determination unit 463 accesses the identification status list 402 and determines whether or not the face image supplied from the similarity determination unit 462 is registered. Only when the face image is not registered, the highest-order face image is displayed. The similarity information is supplied to the display unit 23, and is displayed to the communication unit 224.

  Next, the registered player visit monitoring process will be described with reference to the flowchart of FIG. Note that the processing of steps S201 to S205, the processing of step S237, and the processing of steps S241 to S243 in the flowchart of FIG. 28 are respectively the processing of steps S1 to S5 in FIG. 13 and the processing of step S89 in the flowchart of FIG. Since the processing is the same as the processing in steps S111 to S113, the description thereof will be omitted. In this process, for the sake of convenience of explanation, the description will be made on the case where only the face image captured by the camera 38 provided in the game stand 36 in the game store 1 is handled. It goes without saying that other cameras may be used.

  In step S221, the face image acquisition unit 221 of the biological information recognition apparatus 401 determines whether or not a face image has been transmitted, and repeats the same processing until it is transmitted. In step S221, for example, when a face image is transmitted by the process of step S205, the process proceeds to step S222.

  In step S <b> 222, the face image acquisition unit 221 acquires the transmitted face image, and supplies information on the camera ID that captured the acquired face image to the partial biological information DB generation unit 451.

  In step S223, the partial biological information DB generation unit 451 controls the remote extraction unit 451a, and based on the gaming machine number corresponding to the supplied camera ID, the gaming machine 36 located far from the identification status list 402. The ID for identifying the face image of the person who has already been verified is extracted.

  That is, for example, when the inside of the game store 1 has a layout as shown in FIG. 29, the distance and the neighborhood from the predetermined position are classified as follows. Here, FIG. 29 is a top view of the gaming store 1, and the squares indicate the positions where the gaming machines 36 of the respective gaming machine numbers are arranged, and the numbers in the squares are the gaming machines, respectively. A number (game table number) for identifying 36 is shown. Therefore, in the store shown in FIG. 29, 32 game machines 36 constitute one island facility, and a total of three island facilities. It should be noted that the numbers such as “4” or “9” are considered to be bad for the game machine number, and are not usually given at the game store 1, so the same applies to FIG. 29. The game table number is assigned without using a number such as “4” or “9”.

  That is, the game store 1 is divided into eight ranges Z1 to Z8 as shown in FIG. In FIG. 29, the range in which the gaming tables 36 having the gaming table numbers 1 to 3, 5, 6, 35 to 38, 50 to 56, 85 to 88, and 100 divided by the solid line in FIG. The range in which the gaming tables 36 with the gaming table numbers 5 to 8 and 10 to 16 divided by the dotted line are arranged is the range Z2, and the gaming table numbers 15 to 18, 20 to 23, 25 divided by the solid line. , 26, 65 to 68, 70 to 73, 75, 76, the range in which the gaming tables 36 are arranged is the range Z3, and the gaming table numbers partitioned by two-dot chain lines are 25 to 28, 30 to 33, 35, 36, 55 to 58, 60 to 63, 65, 66, the range in which the gaming machines 36 are arranged is the range Z4, and the gaming machine numbers partitioned by dotted lines are 51 to 53, 55, 56, 85 to 88, 100. To 103, 105, 106, 135 The range in which the gaming machines 36 to 138, 150 are arranged is the range Z5, and the gaming machine numbers partitioned by dotted lines are 65 to 68, 70 to 73, 75, 76, 115 to 118, 120 to 123, 125, A range in which 126 game machines 36 are arranged is a range Z6, and game machine numbers partitioned by a one-dot chain line are 75 to 78, 80 to 83, 85, 86, 105 to 108, 110 to 113, 115, 116. The range in which the gaming tables 36 are arranged is the range Z7, and the range in which the gaming tables 36 with the gaming table numbers 125 to 128, 130 to 133, 135, 136 partitioned by the two-dot chain line are arranged is the range Z8. is there.

  The identification status list 402 is, for example, as shown in FIG. 30 and includes columns of a gaming machine number, a neighboring range, an ID for identifying a face image, and a detection date and time from the left. In FIG. 30, the game machine number is a number for identifying the game machine 36 corresponding to FIG. 29, and 1, 2, 3, 5, 6, 7, 8, 10... 100, 101, 102 from the top. , 103..., And the neighboring range is a range to which each gaming table 36 belongs from above the ranges Z1 to Z8 shown in FIG. 29, and “Z1”, “Z1”, “ "Z1", "Z1, Z2", "Z1, Z2", "Z2", "Z2", "Z2", ... "Z1, Z5", "Z5", "Z5", "Z5" ... The ID is an ID for identifying the face image detected by the collation processing. From the top, “”, “”, “155”, “”, “”, “53”, “120”, “”,... “”, “11”, “33”,... Are described, and the detection date is the date when the face image was detected by the matching process. It shows the time. From the top, “”, “”, “2006/11/01 10:30:15”, “”, “”, “2006/11/01 10:30:20”, “2006/11 / 01 10:30:10 "," ", ..." "," 2006/11/01 10:30:10 "," 2006/11/01 10:30:30 "," "... is described. Note that the blanks in the ID and the detection date indicate that there is no player playing on the corresponding gaming table 36 and no face image is detected.

  In the case of FIG. 29, for example, when the camera ID from which the face image is captured corresponds to the gaming machine number 5, the neighboring range is within the range to which the gaming machine 36 with the gaming machine number 5 belongs. Therefore, in the case of FIG. 29, the gaming machine 36 with the gaming machine number 5 belongs to the ranges Z1 and Z2, and therefore it is recognized that the gaming machines 36 other than the gaming machine number 5 belonging to the ranges Z1 and Z2 exist in the vicinity. In addition, the gaming tables 36 belonging to the other ranges Z3 to Z8 are recognized as existing at a position far from the gaming table number 5 on which the face image is captured by a predetermined distance.

  For this reason, when the camera ID from which the face image is captured corresponds to the gaming machine number 5, when the identification status list 402 is as shown in FIG. IDs = 155, 53, and 120 that identify face images that have already been verified in 7 and 8 are considered to exist in the neighborhood range and are not considered to be extracted. On the other hand, IDs 11 and 33 for identifying face images that have already been verified in the game machine numbers 101 and 102 are extracted.

  In step S224, the partial biometric information DB generation unit 451 controls the difference calculation unit 451b to obtain the information of the corresponding face image based on the ID for identifying the extracted face image that has already been collated. The difference information deleted from the information DB 22 is generated.

  In step S225, the partial biological information DB generation unit 451 generates the difference information generated by the difference calculation unit 451b as the partial biological information DB 403.

  That is, every time a face image is supplied, the partial biometric information DB generation unit 451 selects a face image that has been collated at a distant position as viewed from the gaming machine number corresponding to the camera ID that captured the face image. The partial biometric information DB 403 is generated by deleting from the information DB 22.

  In step S <b> 226, the face image acquisition unit 221 extracts one of unprocessed ones of the supplied face images and supplies the extracted unprocessed one to the feature amount extraction unit 231.

  In step S227, the feature amount extraction unit 231 of the collation unit 222 extracts the feature amount from the supplied face image and supplies it to the similarity calculation unit 461 along with the face image.

  In step S228, the similarity calculation unit 461, for the face image supplied from the feature amount extraction unit 231, the ratio between the eye-to-eye spacing, the length from the chin to the forehead, the length from the chin to the nose, and the like. The difference sum, the average ratio, or the ratio sum is calculated as the degree of similarity using the various face feature amounts and the similar feature amounts in the face image registered in the partial biological information DB 403, and the calculation is performed. As a result, the similarity ranking is obtained, and information about the highest face image and similarity is supplied to the similarity determination unit 462 together with the face image supplied from the feature amount extraction unit 231.

  In step S229, the similarity determination unit 462 determines whether the highest similarity is greater than a predetermined threshold based on the highest face image and similarity information supplied from the similarity calculation unit 232. Determine.

  If it is determined in step S229 that the highest similarity is greater than the predetermined threshold value, in step S230, the similarity determination unit 462 displays the facial image information of the highest similarity in the list generation unit 452 and the presence of the face image information. This is supplied to the determination unit 463. The presence determination unit 463 accesses the identification status list 402 and searches for an ID for identifying the supplied face image.

  In step S231, the presence determination unit 463 accesses the identification situation list 402, and the ID for identifying the supplied face image is not the ID registered in the identification situation list 402, that is, whether or not the ID is searched. Determine.

  In step S231, if the ID for identifying the supplied face image in the identification status list 402 is not the ID registered in the identification status list 402, that is, if no ID is searched, the presence determination unit in step S232. In step S <b> 463, an image including the supplied face image is displayed on the display unit 23 and supplied to the communication unit 224. The communication unit 224 transmits the captured camera image including the face image having the highest similarity and the face image to the portable terminal 18 to notify that the corresponding registered player has visited the store.

  On the other hand, if an ID for identifying the supplied face image is searched in the identification status list 402 in step S231, that is, if the ID has already been collated, the process of step S232 is skipped.

  In step S233, the list generation unit 452 obtains the corresponding gaming machine number based on the face image supplied from the similarity determination unit 462 and the camera ID that captured the image including the face image, and the identification situation list 402 is updated. That is, in the case where the ID identifying the face image that is the highest collation result is 100 and the face image is detected at 10:30:40 on November 1, 2006, in FIG. “100” is described in the item of ID corresponding to the gaming machine number 5, and “2006/11/01 10:30:40” is described in the item of detection date.

  In step S234, the face image acquisition unit 221 determines whether or not all face images have been processed. If there is an unprocessed face image, the process returns to step S226. That is, the processes in steps S226 to S234 and S237 are repeated until all the face images are processed. If it is determined in step S234 that all face images have been processed, the process returns to step S221.

  On the other hand, if it is determined in step S221 that a face image has not been transmitted, in step S235, the list generation unit 452 determines whether or not a state in which no face image is detected has elapsed for a predetermined time or more. If the predetermined time has not elapsed in step S235, the process returns to step S221. If it is determined in step S235 that the predetermined time has elapsed, in step S236, the list generation unit 452 determines the ID and detection date / time of the gaming machine number corresponding to the gaming machine 36 in a state where no face image is transmitted. And the identification status list 402 is updated.

  That is, for example, in the case of the identification status list 402 of FIG. 30, if a situation where a face image has not been supplied for a predetermined time or longer for the gaming machine number 3 is registered ID = 155 and the detection date “2006 / 11/01 10:30:15 "will be deleted.

  Through the above processing, each time the face image is supplied, the partial biometric information DB 403 displays the face image that has been collated at a position far away from the game table number corresponding to the camera ID that captured the face image. It is deleted from the information DB 22 and generated.

  For this reason, for example, in the game store 1, when 500 game tables 36 are installed, one range corresponding to each of the ranges Z1 to Z8 is equal to an equal range in which 30 game tables 36 are installed. In the conventional configuration, when 400 players are operating and face images are acquired on a predetermined game stand 36, assuming that 700 people are registered in the biometric information DB 22, If there was, it had to be collated with the face images for 700 people to derive the result, but using the above method, face images for 324 (= 700- (400-24)) people The result can be obtained in about half the processing time.

  That is, since 400 of the 500 game machines 36 installed are operating, it is considered that 30 × (400/500) = 24 are operating per range. Therefore, since there are (400-24) face images that have been collated in the distance, the face images for these numbers are excluded from the biometric information DB 22 and collated with the face images registered in the partial biometric information DB 403. Processing will be performed.

  As a result, since the matching process is performed by the face image registered in the database from which the face image that has been verified has been deleted, unnecessary matching process is omitted and the similarity degree calculated unnecessarily. Therefore, the processing speed can be improved and the processing accuracy can be improved.

  In addition, an example in which the face image that has already been collated at the above-mentioned distant position described above with reference to FIG. 26 is deleted and collation processing is performed using the face image database, and FIG. 1 to FIG. 25 are referred to. Needless to say, it may be implemented in combination with the example in which the collation processing is performed using the database from which the face images that have been collated including the other game stores 1 described above are deleted.

  That is, in the monitoring system of FIG. 1, it is possible to reduce the number of face images registered in the verification database 19 on the day more efficiently by using the customer information from a plurality of game stores 1, as shown in FIG. In the monitoring system, the face image registered in the partial biological information DB 403 can be reduced by the game store 1 alone. Therefore, by using in combination, the number of face images used for collation can be effectively reduced.

  Incidentally, the series of monitoring processes described above can be executed by hardware, but can also be executed by software. When a series of processing is executed by software, a program constituting the software may execute various functions by installing a computer incorporated in dedicated hardware or various programs. For example, it is installed from a recording medium in a general-purpose personal computer or the like.

  FIG. 31 shows a configuration example of a general-purpose personal computer. This personal computer incorporates a CPU (Central Processing Unit) 1001. An input / output interface 1005 is connected to the CPU 1001 via the bus 1004. A ROM (Read Only Memory) 1002 and a RAM (Random Access Memory) 1003 are connected to the bus 1004.

  The input / output interface 1005 includes an input unit 1006 including an input device such as a keyboard and a mouse for a user to input an operation command, an output unit 1007 for outputting a processing operation screen and an image of a processing result to a display device, a program and various data. A storage unit 1008 including a hard disk drive for storing data, a LAN (Local Area Network) adapter, and the like, and a communication unit 1009 for performing communication processing via a network represented by the Internet are connected. Also, a magnetic disk (including a flexible disk), an optical disk (including a CD-ROM (Compact Disc-Read Only Memory), a DVD (Digital Versatile Disc)), a magneto-optical disk (including an MD (Mini Disc)), or a semiconductor A drive 1010 for reading / writing data from / to a removable medium 1011 such as a memory is connected.

  The CPU 1001 is read from a program stored in the ROM 1002 or a removable medium 1011 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, installed in the storage unit 1008, and loaded from the storage unit 1008 to the RAM 1003. Various processes are executed according to the program. The RAM 1003 also appropriately stores data necessary for the CPU 1001 to execute various processes.

  In this specification, the step of describing the program recorded on the recording medium is not limited to the processing performed in time series in the order described, but of course, it is not necessarily performed in time series. Or the process performed separately is included.

  Further, in this specification, the system represents the entire apparatus constituted by a plurality of apparatuses.

It is a figure which shows the structure of one Embodiment of the monitoring system to which this invention is applied. It is a figure which shows the example of installation of the camera of FIG. It is a figure which shows the example of installation of the camera of FIG. It is a figure which shows the example of installation of the camera of FIG. It is a figure which shows the example of installation of the camera of FIG. It is a figure which shows the example of installation of the camera of FIG. It is a figure which shows the example of installation of the camera of FIG. It is a figure which shows the example of installation of the entrance camera and shop camera of FIG. It is a figure explaining the structural example of the image processing unit of FIG. It is a figure explaining the structural example of the biometric information recognition apparatus of FIG. It is a figure explaining the structural example of the biometric information management center and biometric information management DB of FIG. It is a figure explaining the structural example of the portable terminal of FIG. It is a flowchart explaining the registration player visit monitoring process by the monitoring system of FIG. It is a flowchart explaining collation processing. It is a flowchart explaining a new collation process. It is a figure explaining the example of a display of an alerting | reporting image. It is a figure explaining a new collation process. It is a figure explaining player DB. It is a figure explaining the collation DB on the day. It is a figure explaining registration player DB. It is a figure explaining a new collation process. It is a flowchart explaining an exit camera process. It is a figure explaining an exit camera process. It is a flowchart explaining a game store customer information collection process. It is a flowchart explaining a registration player DB update process. It is a figure which shows the structure of other embodiment of the monitoring system to which this invention is applied. It is a figure explaining the structural example of the biometric information recognition apparatus of FIG. It is a flowchart explaining the registration player visit monitoring process by the monitoring system of FIG. It is a figure explaining the division of the range in an amusement shop. It is a figure explaining an identification situation list. It is a figure explaining a general purpose personal computer.

Explanation of symbols

1, 1-1 to 1-n amusement store 2 biometric information management center 3 biometric information management database 4 third party amusement store management center 5 third party amusement store management database 6 biometric information management bus 7 third party amusement store management bus 8, 9 Public communication network 21 Biometric information recognition device 22 Biometric information database 24 Game store management device 26 Game table management database 27 Medium lending management device 29 Medium lending management database 30 Amusement store management information bus 31 Biometric information bus 33 Settling machine 34 Lending machine 35 Counter 36,36-1 thru 36-m Game stand 37,37-1 thru 37-m Game stand peripheral terminal 38,38-1 thru 38-m Camera 39,39-1 thru 39- (m + p + q) Image processing unit 40, 40-1 to 40-p Entrance camera 41, 41-1 to 41-q In-store camera 42, 42- To 42-q exit Camera

Claims (8)

First accumulating means for accumulating face image groups of registrants registered in advance;
Acquisition means for acquiring a face image of the person to be verified;
The registration that is determined to be a face image of another collation target person different from the collation target person at a position far by a predetermined distance from the position from which the collation target person's face image is acquired by the acquisition means. Extracting means for extracting a person's face image;
The set of registrant face images accumulated by the first accumulating means and the registration determined to be a face image of another collation target person different from the collation target person extracted by the extraction means Difference calculation means for obtaining difference information with a set of person's face images;
Second accumulating means for accumulating a registrant's face image as the difference information;
Collation means for calculating and collating the similarity between the face image of the person to be collated acquired by the acquisition means and the face image of the registrant accumulated in the second accumulation means;
A similarity determination unit that determines whether or not the face image of the person to be collated is a face image of the registrant by comparing the similarity that is the collation result of the collation unit and a predetermined threshold;
When the similarity determination unit determines that the collation target person is the registrant, the face image of the collation target person determined to be the registrant and the position where the face image was acquired Registration means for registering information,
The extraction means includes the face image of the person to be collated determined by the similarity determination means registered by the registration means as the registrant and the position from which the face image was acquired. Is a face image of another collation target person different from the collation target person at a position that is a predetermined distance away from the position where the face image of the collation target person is acquired by the acquisition means. A monitoring device that extracts a face image of the registrant determined to be. An imaging means for capturing an image;
A face image extracting means for extracting the face image of the person to be collated from the image captured by the image capturing means;
Further comprising a feature amount extraction means for extracting a feature amount from the face image of the person to be collated,
The collating unit calculates a similarity using a feature amount between the face image of the person to be collated acquired by the acquiring unit and the face image of the registrant stored in the accumulating unit, and acquires the similarity by the acquiring unit. The monitoring device according to claim 1, wherein the face image of the person to be collated is collated with the face image of the registrant stored in the storage unit. In the case where a face image is not acquired for a predetermined time or more by the acquisition unit, the registration unit is configured to store the verification target person registered corresponding to a position where the face image is not acquired for the predetermined time or more by the acquisition unit. The monitoring device according to claim 1, wherein information on a face image is deleted. The unregistered person registration means for registering the face image of the verification target person as an unregistered person when the similarity determination means determines that the verification target person is not the registrant. Monitoring device. The first accumulating unit accumulates face images of registrants registered in advance as a database,
The monitoring apparatus according to claim 4, wherein a face image of an unregistered person who has been registered a predetermined number of times or more by the unregistered person registration unit is registered in the database as the face image of the registrant. The position from which the face image of the person to be collated is acquired belongs to one of a plurality of ranges,
The extraction means includes
The position where the face image of the person to be collated is acquired by the acquisition means by recognizing a position outside the range to which the position from which the face image of the person to be collated belongs belongs as a distant position by a predetermined distance The monitoring apparatus according to claim 1, wherein a face image of the registrant that is determined to be a face image of another collation target person different from the collation target person at a position farther than a predetermined distance is extracted. A first accumulation step for accumulating a pre-registered registrant's face image group;
An acquisition step of acquiring a face image of the person to be verified;
It is determined that the face image of the other person to be collated is different from the person to be collated at a position far from the position from which the face image of the person to be collated is acquired by the process of the obtaining step. An extraction step of extracting the registrant's face image;
It is determined that the set of facial images of the registrant accumulated by the process of the first accumulation step is a face image of another collation target person different from the collation target person extracted by the process of the extraction step. A difference calculating step for obtaining difference information with the set of registered registrant face images;
A second accumulation step for accumulating a registrant's face image as the difference information;
A collation step of calculating and collating the similarity between the face image of the person to be collated acquired by the process of the acquisition step and the face image of the registrant accumulated by the process of the second accumulation step;
A similarity determination step of determining whether or not the face image of the person to be verified is a registrant's face image by comparing the similarity that is the result of the verification in the process of the verification step with a predetermined threshold;
When it is determined by the similarity determination step that the person to be collated is the registrant, the face image of the person to be collated determined to be the registrant and the face image thereof are acquired. A registration step of registering location information,
The process of the extraction step includes the face image of the person to be collated determined to be the registrant by the process of the similarity determination step registered by the process of the registration step, and the face Based on the information on the position at which the image was acquired, another position different from the verification target person at a position that is a predetermined distance away from the position at which the face image of the verification target person is acquired by the processing of the acquisition step. A monitoring method for extracting a face image of the registrant determined to be a face image of a person to be collated. A first accumulation step for accumulating a pre-registered registrant's face image group;
An acquisition step of acquiring a face image of the person to be verified;
It is determined that the face image of the other person to be collated is different from the person to be collated at a position far from the position from which the face image of the person to be collated is acquired by the process of the obtaining step. An extraction step of extracting the registrant's face image;
It is determined that the set of facial images of the registrant accumulated by the process of the first accumulation step is a face image of another collation target person different from the collation target person extracted by the process of the extraction step. A difference calculating step for obtaining difference information with the set of registered registrant face images;
A second accumulation step for accumulating a registrant's face image as the difference information;
A collation step of calculating and collating the similarity between the face image of the person to be collated acquired by the process of the acquisition step and the face image of the registrant accumulated by the process of the second accumulation step;
A similarity determination step of determining whether or not the face image of the person to be verified is a registrant's face image by comparing the similarity that is the result of the verification in the process of the verification step with a predetermined threshold;
When it is determined by the similarity determination step that the person to be collated is the registrant, the face image of the person to be collated determined to be the registrant and the face image thereof are acquired. Causing a computer to execute a process including a registration step of registering position information;
The process of the extraction step includes the face image of the person to be collated determined to be the registrant by the process of the similarity determination step registered by the process of the registration step, and the face Based on the information on the position at which the image was acquired, another position different from the verification target person at a position that is a predetermined distance away from the position at which the face image of the verification target person is acquired by the processing of the acquisition step. A program for extracting a face image of the registrant determined to be a face image of a person to be collated.

Images