WO2019116542A1

WO2019116542A1 - Paper sheet contamination assessment device and paper sheet contamination assessment method

Info

Publication number: WO2019116542A1
Application number: PCT/JP2017/045123
Authority: WO
Inventors: 利彦番匠谷; 良池本; 千裕永井
Original assignee: グローリー株式会社
Priority date: 2017-12-15
Filing date: 2017-12-15
Publication date: 2019-06-20
Also published as: EP3726486A1; JPWO2019116542A1; EP3726486A4; JP6878623B2

Abstract

In order to assess the presence of color contamination with a color stain over a large area on a paper sheet, this paper sheet contamination assessment device is equipped with: an image acquisition part for acquiring an image of a paper sheet; a storage part having stored therein reference data for identifying a change in color of a paper sheet resulting from the passage of time; and an assessment part for detecting, on the basis of images of paper sheets and reference data, a paper sheet whereon the color of a region having at least a prescribed area has changed from the color immediately after the printing thereof, and assessing whether the detected paper sheet is a paper sheet whereon the color has changed due to the passage of time or a color-contaminated paper sheet having a color stain.

Description

Sheet stain determination apparatus and sheet stain determination method

The present invention relates to a sheet stain determination apparatus and a sheet stain determination method for determining the stain of a sheet, and more particularly to a sheet stain for determining the presence of color stain with color stain due to ink or dye. The present invention relates to a determination device and a sheet contamination determination method.

BACKGROUND ART Conventionally, a sheet processing apparatus has been used which identifies a denomination, authenticity, and fitness of a sheet. In the damage identification, it is possible to detect a damaged sheet. For example, Patent Document 1 discloses a sheet discrimination apparatus for discriminating the degree of contamination of a sheet. This device irradiates the bill with light of a predetermined wavelength, and detects wrinkles and dirt from the state of light reflection and transmission in a preset area. It is possible to change the angle and wavelength of the light irradiated to the bill so as to easily detect wrinkles and dirt.

JP, 2010-277252, A JP-A-7-182518

However, there are contaminations that can not be accurately detected by the above-mentioned prior art. For example, there is a possibility that this color stain can not be detected even when a sheet colored in blue with ink, dye or the like is irradiated with blue light. In addition, in the prior art for detecting local stains such as wrinkles and graffiti, there is a possibility that the stains with widely colored stains can not be detected. Furthermore, only by detecting that the color is widely different from that of ordinary paper sheets, there is a possibility that color degradation due to aging may be misdetected as color stain.

For example, at Holi Festival in India, where colored powder and colored water are mixed, a large number of red and green-colored banknotes are generated. Further, for example, in order to cope with theft or the like of a bill, there is a cash processing apparatus which sprays special ink to color a bill when an abnormality is detected. Although it is required to detect these banknotes separately as other colored banknotes as color-stained banknotes, accurate detection is difficult in the prior art.

The present invention has been made in view of the problems caused by the above-mentioned prior art, and provides a sheet contamination judgment apparatus and a sheet contamination judgment method for judging presence or absence of color contamination where a sheet is colored. The purpose is

SUMMARY OF THE INVENTION In order to solve the problems described above and achieve the object, the present invention is a paper sheet staining judgment apparatus, comprising: an image acquisition unit for acquiring an image of a paper sheet; Based on the storage unit in which reference data for specifying a change is stored and the image of the sheet and the reference data, the sheet whose color is changed from the color immediately after printing is detected in an area of a predetermined area or more And a determination unit that determines whether the detected paper sheet is a paper sheet whose color has changed due to aging or a color soiled paper sheet having a color stain. .

Further, according to the present invention, in the above-mentioned invention, the reference data is obtained by calculating feature quantities from pixel values of a plurality of colors obtained by color separation of a color image of a sheet, and substituting the feature quantities into a predetermined evaluation formula. The evaluation value is a threshold value for determining whether or not it is a value indicating that the sheet is a color-damaged paper sheet, and the judgment unit judges the evaluation value from the image of the paper sheet acquired by the image acquisition unit. Is calculated and compared with the threshold value to determine whether the sheet is a color-damaged sheet or not.

Further, according to the present invention, in the above-mentioned invention, the feature amount is a value indicating a correlation feature of pixel values of the plurality of colors.

Further, according to the present invention, in the above invention, the evaluation formula is calculated from images of a plurality of sheets having no change in color due to aging and images of a plurality of sheets changing in color due to aging. It is characterized in that it is an equation for calculating a principal component score of a predetermined principal component obtained by performing principal component analysis of the feature amount.

Further, according to the present invention, in the above-described invention, the images of a plurality of sheets of paper whose color has been changed due to the aging change the color components of the image obtained by imaging the sheets and simulate the color change due to the aging. It is characterized in that it is an image that is reproduced and generated.

The present invention is characterized in that, in the above-mentioned invention, the pixel values of the plurality of colors are a pixel value of R component, a pixel value of G component, and a pixel value of B component.

Further, the present invention is characterized in that, in the above-mentioned invention, the determination section determines whether or not color stains attached to a plurality of colored stains are the same color based on the evaluation value. Do.

Further, according to the present invention, in the above-mentioned invention, the determination unit calculates the evaluation value from pixel values of pixels forming the block, targeting a partial area previously set as a block on the paper sheet. It is characterized in that it is determined whether or not the sheet is a color-stained sheet.

Further, according to the present invention, in the above-mentioned invention, the block is set by dividing the entire surface of the sheet into a plurality of parts, and the determination unit determines a color-damaged sheet based on the evaluation value calculated for each block. It is characterized in that it is determined whether the kind is a paper sheet with color stains on the entire surface or a paper sheet with color stains in only a part of the area.

Further, according to the present invention, in the above-described invention, a receiving unit for receiving a plurality of sheets, a transport unit for transporting the sheets received in the receiving unit one by one, and a plurality of accumulations for stacking the sheets. A plurality of sheets received in the receiving unit are classified and accumulated in a plurality of stacking units based on the determination result by the determination unit.

Further, the present invention is a sheet stain determination method for determining the presence or absence of color stains in a sheet stain determination apparatus, which includes the steps of acquiring an image of a sheet, and an image obtained by capturing the sheet, In addition, based on reference data for specifying the change in color of the sheet due to aging, the sheet whose color has changed from the color immediately after printing in the area of a predetermined area or more changes in color due to aging. And a step of determining whether it is a paper sheet or a colored soiled paper sheet with color stains.

According to the present invention, it is possible to detect that the area above the predetermined area on the paper sheet has changed to a color different from that immediately after printing. Then, using reference data prepared in advance to identify a change in color due to aging, it is determined whether the detected change in color is due to aging or color stain with ink, dye, etc. be able to. As a result, it is possible to detect paper sheets with color stains, as distinguished from paper sheets whose color has changed due to aging.

FIG. 1 is a diagram for explaining the contamination determination of a sheet performed by the banknote processing apparatus. FIG. 2 is a diagram for explaining the configuration of the bill processing apparatus. FIG. 3 is a block diagram schematically showing the functional configuration of the bill processing apparatus. FIG. 4 is a diagram for explaining a bill image used to calculate the feature amount. FIG. 5 is a diagram for explaining the method of calculating the feature amount. FIG. 6 is a diagram showing an example of a set when plotting the main component scores of the first main component, the second main component, and the third main component. FIG. 7 is a flowchart showing an example of the process of fitness identification and contamination determination.

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, preferred embodiments of a paper sheet contamination judgment apparatus and a paper sheet contamination judgment method according to the present invention will be described in detail with reference to the attached drawings. The paper sheet contamination determination method is used, for example, in a sheet processing apparatus that successively processes a plurality of sheets one by one. The type of sheet to be subjected to the stain determination is not particularly limited, but in the present embodiment, a bill will be described as an example. Specifically, taking a bill processing apparatus (paper sheet processing apparatus) that discriminates denominations, authenticity, fitness and the like of bills and classifies bills according to types based on identification results as an example, paper sheet dirt determination The apparatus and the sheet staining method will be described.

First, an outline of the paper sheet dirt determination method will be described. FIG. 1 is a diagram for explaining the contamination determination of a sheet performed by the banknote handling apparatus 1. The banknote handling apparatus 1 shown in FIG. 1 functions as a paper sheet contamination determination apparatus. The bill processing apparatus 1 receives a plurality of bills 100, takes them into the apparatus one by one, and identifies the denomination, authenticity, fitness and the like of each bill. The bill processing apparatus 1 separates and sorts banknotes by type into the reject unit, the stacking unit, and the like based on the identification result.

The banknote processing apparatus 1 performs fitness identification, and as shown in FIG. 1, classifies the banknote 100 into a genuine banknote 101 and unfit banknotes 111 to 114. For example, reusable banknotes in the market are regarded as correct banknotes, and banknotes which can not be reused are regarded as unfit banknotes. The bill processing apparatus 1 obtains a value indicating an optical feature from an image obtained by imaging a bill, and determines the presence or absence of dirt, wrinkles, tears, etc. of the bill. Moreover, the value which shows the thickness of a banknote is acquired, and the presence or absence etc. of the tape stuck on the banknote are determined. The determination is performed by comparing the value obtained from the banknote with a threshold value prepared in advance to separate the genuine and the unfit notes. By changing the threshold value used as reference data, it is possible to change what kind of bill is to be an unfit note.

Damaged bills include torn banknotes, partially lost banknotes, severely damaged banknotes such as folds and creases, scribbled banknotes, banknotes discolored by secular change, banknotes with color stains due to ink or dye, etc. , Includes various banknotes. The banknote handling apparatus 1 can classify these unfit banknotes according to types. In particular, it is one of the features of the bill processing apparatus 1 that it is possible to distinguish between a normal spoiled note such as a scribbled bill, a bill that is discolored by aging, and a colored spoiled note discolored by color stain. In order to explain this feature, in the following, the explanation will be continued on the assumption that the unfit notes 111 to 114 are either normal stain notes discolored due to aging or color stain notes with color stain.

The bill processing apparatus 1 that has classified the damage by performing the damage identification further classifies the unfit notes 111 to 114 into the normal spoiled note 111 and the color blotted notes 112 to 114. The bill processing apparatus 1 can further classify the color staining notes 112 and 113 having different colors of color stains by color. The color stain notes 112 to 114 can also be classified into color stain notes 112 and 113 with color stains on the whole, and color stain notes 114 with color stains on only a part of the area. In FIG. 1, for example, compared to the color immediately after printing, the color stain note 112 stains entirely in blue, the color stain note 113 stains in green, and the color stain note 114 stains partially in red. It shows schematically that the color stains are different.

Here, the color stain notes (color stain sheets) 112 to 114 refer to bills in which a color (color stain) with ink, dye or the like is attached to an area of a predetermined area or more set in advance. The bill processing apparatus 1 can detect a color stain note, which has been changed to a color different from that of a normal bill, by distinguishing it from other bills because the color stain due to ink, dye or the like is attached. Specifically, it is possible to detect a color contamination note by distinguishing it from a banknote that has been scribbled by characters, lines, etc. or that is locally stained. In addition, although the color changes in a wide range as compared with the state immediately after printing, it is possible to detect a color-stained note by distinguishing it from a banknote that is not a color stain but a fading due to aging.

For example, the bill processing apparatus 1 determines that a bill in which at least one whole block has a color stain among a plurality of blocks obtained by dividing a bill into a plurality of partial areas is a color stain. For example, a rectangular shape having dimensions of about 30 mm in the vertical and horizontal directions is taken as one block, and a banknote in which the whole block is stained with color stains is taken as a color stain. Depending on the number of blocks with color stains, it is possible to distinguish between the color stain notes 112 and 113 with color stains throughout the banknotes and the color stain notes 114 with colors in only some areas. The size and position of the block for determining the presence or absence of color stain can be changed by setting.

When a long period of time has passed since the bill was issued, discoloration due to aging occurs, and the color of the whole bill changes. Specifically, for example, the white background portion (paper color) of the banknote becomes yellowish. Also, for example, a pattern such as a character, a portrait, or a geometric pattern printed vividly with an ink such as red or blue becomes a dull color. The bill processing apparatus 1 can distinguish between the normally-damaged banknote 111 whose color has changed due to aging and the color-damaged banknotes 112 to 114 colored by a dye or the like.

The banknote processing apparatus 1 uses a value indicating the color tone of a block set on a banknote as a feature amount for determination of color contamination. For example, the sum of pixel values (brightness values) of R (red), G (green), and B (blue) of each pixel forming a block on the image is calculated using a color image obtained by imaging a bill. , And the feature amount of the block. Further, for example, the sum of correlation features of pixel values of color components of each pixel is set as a feature amount of the block. Specifically, for example, values of Higher-order Local AutoCorrelation (HLAC) of each pixel value of RGB are used, but the details will be described later.

A diagram shown in a frame 121 of FIG. 1 schematically shows a state in which a plurality of feature quantities indicating the color tone of a block are calculated from a color image obtained by imaging a bill and plotted on a multi-dimensional feature space. It is a thing. When plotting block data based on the feature amount, block data 131 of an unused banknote (hereinafter referred to as "publicly sealed ticket") after issuance without color staining or fading forms one set 130. . On the other hand, data 141 of blocks of banknotes (usually dirty banknotes) that are discolored due to aging change form a different set 140.

The degree of fading due to aging changes depending on the number of years after use and the usage conditions. The data of banknotes that are greatly discolored due to fading is plotted in a set 140 of discolored banknotes. Data 151 of banknotes which are not included in the set 140 of faded notes but which show fading are distributed on or near a straight line connecting the center of gravity of the set 130 of sealed tickets and the center of gravity of the set 140 of faded notes . The data of the faded banknote is plotted at a position closer to the faded note collection 140 as the degree of fading is higher. Whether a bill whose color has changed due to fading is to be an unfit note or an unfit note can be changed by setting an integrity threshold. For example, if a threshold value is set as a boundary between the set 130 of the official seal ticket and the set 140 of the fading ticket, if the data is plotted on the collecting side of the official seal ticket, the regular ticket is on the collecting ticket side If it is plotted, it can be determined as an unfit note. Although the banknote indicated by the data 151 can be classified into the regular banknote 101 or the unfit banknotes 111 to 114 depending on the setting of the threshold value, the description will be continued on the assumption that the banknote is classified into the regular banknote 101 here.

The feature value calculated from the pixel values of a plurality of colors indicating the color component of the block is such that the set 130 of the official seal note and the set 140 of the faded note are linear as the bill color gradually changes due to fading due to aging. Move the band area to be connected. Specifically, as the change in color due to color fading increases, the position near the set 130 of sealed tickets is moved toward the position near the set 140 of color faded tickets. On the other hand, the

data

161, 162 of the colored stain notes in which almost the whole of the block is colored is deviated from the set 130 of the sealed ticket, the set 140 of the faded notes, and the strip region connecting these sets linearly. It is plotted at the position.

As shown in the frame 121, the bill processing apparatus 1 has

data

131, 141, 151, 161, and 162 plotted in the feature space based on the feature quantities of the blocks, a collection 130 of government-sealed notes, and faded notes. The banknotes are classified by type based on the positional relationship with the set 140. Specifically, the banknotes indicated by the data 131 and the banknotes indicated by the data 151 are classified into the genuine banknotes 101. The banknotes indicated by the data 141 are generally classified into the contamination banknotes 111. The bills indicated by the data 161 and the bills indicated by the data 162 are classified into one of the color stain notes 112 to 114 according to the area and color of the color stain.

In the banknote handling apparatus 1, in order to detect the color contamination note with high accuracy, the contamination determination using the principal component analysis can be performed. When principal component analysis is performed using a multi-dimensional feature quantity indicating a color as a variable, as shown by an arrow in a frame 121 of FIG. 1, the change of the feature quantity due to the change in color due to aging changes the first main It is obtained as a component. Following this, the second main component and the third main component, which have high contribution rates, are used to detect a color contamination note.

The drawing in the frame 122 of FIG. 1 schematically shows a state in which the values of the second main component and the third main component calculated from the feature amount are plotted on the main component space. As shown in the frame 122, if the second main component and the third main component are used, a collection 171 including data 131 of a sealed ticket and

data

141 and 151 of faded banknotes, and data 161 of a color staining note, It can be separated from the set 172 including 162. Using this, the bill processing apparatus 1 distinguishes between a color-corrupted note and another bill.

Specifically, a formula for calculating the main component scores of the second main component and the third main component from the feature amount obtained by performing the main component analysis is used as an evaluation expression. The bill processing apparatus 1 calculates a feature amount from pixel values indicating color components of blocks and substitutes it into an evaluation formula to calculate main component scores of the second main component and the third main component. Then, using the calculated value as an evaluation value, it is evaluated whether or not there is color stain on the block.

As shown in the frame 122 of FIG. 1, when the data in which the main component scores of the second main component and the third main component are plotted on the main component space is included in the set 172 indicating color stains, this block Is determined to be a block of a color contamination note. That is, it is determined that the block has color stains. As a result, it is possible to distinguish between the color stains 112 to 114 and the regular bill 101 or the regular stains 111.

The bill processing apparatus 1 distinguishes between the colored stain notes 112 and 113 in which the whole bill is stained in color and the colored stain note 114 in which the partial stain is colored, based on the determination result of the color stain presence or absence of each block. . Further, based on the positional relationship between the two

data

161 and 162 of the color-discoloring note on the main component space, such as the distance and direction between the two pieces of data, the color-discoloring note of the color-discoloring note indicated by the

data

161 and 162 is the same color It is determined whether or not. As a result, it is possible to distinguish between the color stain note 112 in which the color of the color stain attached to the bill is different, and the color stain note 113.

Specifically, if there is a block with color stain even in one of all the blocks set in the bill, the bill processing apparatus 1 determines that the bill is the color stain notes 112 to 114. At this time, when there is color stain on some blocks among the plurality of blocks and no color stain on other blocks, the bill processing apparatus 1 converts the bill into a color stain note 114 with partial color stains. judge. On the other hand, when all the blocks have color stains, the bill processing apparatus 1 determines that the bill is the color stain notes 112 and 113 in which color stains are attached to the whole surface of the bill.

Further, the bill processing apparatus 1 determines whether the color of the color stain indicated by the data 161 is different from the color of the color stain indicated by the data 162 based on the positional relationship between the data 161 indicating the color stain and the data 162. Determine if Based on the determination result, the bill processing apparatus 1 classifies the color staining notes 112 and 113 having color stains on the entire surface of the bill according to colors. Similarly, it is also possible to distinguish the color difference and to classify by color the color contamination note in which part of the banknote has color stains.

In order to simplify the description, in FIG. 1, an example has been described in which a bill whose color has changed due to aging over time is distinguished from the color staining notes 112 to 114 as the normal staining note 111. It is not limited to For example, it is possible to set that banknotes that are discolored due to secular change can be classified as genuine banknotes, and similarly, for color-stained banknotes 112-114, color-stained banknotes 112-114 are also set as classified as genuine banknotes. it can. Further, for example, it may be set so as to determine whether the banknote stained in yellow is a non-performing note or not, based on the color of the color stain. In addition, for example, if three or more blocks have color stains as being unfit notes, it is set so as to determine whether to be an unfit note or an unfit note based on the number of blocks having color stains. You can also. It can be changed by setting about how to classify banknotes based on the result of the fitness identification performed by the banknote handling apparatus 1 and the stain determination.

Then, after demonstrating the structure of the banknote processing apparatus 1, the detail of the feature-value and main component for distinguishing a normal-damaged banknote and a color | corrugated banknote is demonstrated. FIG. 2 is a diagram for explaining the configuration of the banknote handling apparatus 1. FIG. 2A is a perspective view showing the appearance of the bill processing apparatus 1. FIG. 2 (b) is a schematic cross-sectional view showing an outline of the internal configuration of the banknote handling apparatus 1. The bill processing apparatus 1 has a receiving unit 11 for receiving a plurality of bills, and a taking-in unit 10 for taking a plurality of bills received by the receiving unit 11 into the apparatus one by one. An operation unit 51 is provided on the front of the device for inputting information on setting change, bill processing, and the like regarding an instruction command. Moreover, the display part 52 for displaying information, such as a setting content and a banknote process result, is provided in the apparatus front surface.

As shown in FIG. 2 (b), the inside of the bill processing apparatus 1 is transported by the transport unit 70 that transports the banknotes taken into the apparatus by the loading unit 10 along the transport path, and the transport unit 70 An identification unit 55 for identifying and counting banknotes is provided. The bill processing apparatus 1 includes, for example, two types for discharging a bill of a preset type, such as a bill that is not to be processed, a fake note, a suspect bill that is suspected of a fake note but can not determine authenticity. The reject unit 65 (65a, 65b) is provided. Rejected banknotes can be sorted by type and discharged to the first reject unit 65a and the second reject unit 65b.

The identification unit 55 acquires various data for identifying and counting the denomination, authenticity, fitness and the like of the banknotes transported by the transport unit 70. The data acquired by the identification unit 55 includes data for determining the presence or absence of color contamination.

The stacker 60 (60a to 60h) receives and stacks the banknotes transported by the transport unit 70. The accumulation unit 60 has an opening on the front surface. The operator using the bill processing apparatus 1 can extract the bills accumulated in the accumulation unit 60 from the opening. Further, on the front surface of the device, individual display portions 62a to 62h for displaying information on stacked bills are provided corresponding to the first to eighth stacking portions 60a to 60h.

Based on the data acquired by the identification unit 55, the denomination, authenticity, fitness and the like of the banknote are identified. Based on the identification result, the rejected banknotes are accumulated in the reject unit 65, and the other banknotes are classified and accumulated in the respective accumulation units 60a to 60h. The type of banknotes accumulated in each accumulation unit 60a to 60h can be changed by setting. The operator operates the operation unit 51 while checking the setting content displayed on the display unit 52 to change the setting related to the determination process or the setting of the bill accumulation destination based on the determination result. it can.

For example, the color contamination note may be separated from the other bills and stacked in the reject unit 65, or the color contamination note may be stacked in the stacking unit 60. At this time, it is also possible to set to classify and accumulate a color stain note having color stains on the entire bill and a color stain note having partial color stains. In addition, it is possible to distinguish the color of the color stain attached to the bill, and to set the color contamination note to be classified by color and accumulated.

As shown in FIG. 2 (b), the transport unit 70 is provided with a plurality of branch members 71 for branching banknotes transported on the transport path. Further, the transport unit 70 is provided with a plurality of sensors 72 for detecting bills transported on the transport path. When the identification result of the bill is obtained using the data acquired by the identification unit 55, the accumulation destination of the bill is determined from the stacking unit 60 and the reject unit 65 based on the identification result. By controlling the branching operation by the branching member 71 while detecting the conveyance position of the bill by the sensor 72, each bill can be conveyed and accumulated to the determined accumulation destination. Each stacking unit 60 is provided with a sensor 73 for detecting the presence or absence of a bill in the stacking unit.

FIG. 3 is a block diagram schematically showing the functional configuration of the banknote handling apparatus 1. As shown in FIG. 3, the bill processing apparatus 1 includes a control unit 50 and a storage unit 56 in addition to the above-described configuration. The control unit 50 controls each unit while referring to the data stored in the storage unit 56, so that each function and operation described in the present embodiment can be realized. The control unit 50 functions as a determination unit that performs determination processing relating to color stain.

The storage unit 56 is formed of, for example, a non-volatile semiconductor memory, and is used to store various data such as programs and settings required for the operation of the control unit 50. The storage unit 56 stores settings related to identification processing and determination processing, reference data such as threshold values and templates, and settings related to the types of bills to be accumulated in the reject unit 65 and the stacking unit 60. In addition, the storage unit 56 is used for temporarily storing an image obtained by capturing a bill, an identification result, and the like.

The identification unit 55 includes a light source 80 that emits light to the bills transported by the transport unit 70, and a line sensor 81 that images the bills. The identification unit 55 functions as an image acquisition unit that acquires an image of a bill. The identification unit 55 turns on the light source 80 to irradiate the bill with light, and the line sensor 81 acquires an image of the entire bill. The image acquisition method may be an aspect in which a bill is irradiated with white light to acquire a color image, or an aspect in which, for example, light of each color of RGB is separately irradiated to acquire an image of each color may be used. .

The identification unit 55 includes, in addition to the light source 80 and the line sensor 81, a magnetic sensor for acquiring data related to the magnetic characteristics of the banknote, a thickness detection sensor for acquiring data related to the thickness of the banknote, and the like. Although the identification process of a banknote is performed using the data acquired by each sensor, since an identification process can be performed similarly to a prior art, detailed description is abbreviate | omitted.

Next, feature amounts used for color stain determination will be described. FIG. 4 is a diagram for explaining a bill image used to calculate the feature amount. The entire surface of the bill 200 is imaged by the line sensor 81, and an R image 301, a G image 401, and a B image 501 are acquired as shown in FIG. The R image 301, the G image 401, and the B image 501 are, for example, images obtained by dividing the banknote 200 into a plurality of rectangular areas of several mm in height and width and capturing each rectangular area as one pixel.

When the bill 200 is sequentially irradiated with light of each color of RGB, the R image 301, the G image 401, and the B image 501 shown in FIG. 4 can be obtained directly. When the bill 200 is irradiated with white light, a color bill image is obtained. From this color image, it is possible to acquire an R image 301, a G image 401, and a B image 501 which are separated into three colors of RGB.

The R image 301 is an image showing the pixel values of the R component of the color image obtained by capturing the banknote 200. The R image 301 is divided into a plurality of blocks 321. For example, the R image 301 is divided into eight blocks 321 (R1, R2...) By dividing the image into two in the lateral direction (vertical direction in FIG. 4) and into four in the longitudinal direction (horizontal direction in FIG. 4).

The G image 401 is an image showing the pixel values of the G component of the color image obtained by imaging the banknote 200. Each pixel 411 of the G image 401 corresponds to each pixel 311 of the R image 301, and each block 421 of the G image 401 corresponds to each block 321 of the R image 301. The B image 501 is an image showing the pixel value of the B component of the color image obtained by imaging the banknote 200. Each pixel 511 of the B image 501 corresponds to each pixel 311 of the R image 301, and each block 521 of the B image 501 corresponds to each block 321 of the R image 301.

When the R image 301, the G image 401, and the B image 501 of the banknote 200 are obtained, the control unit 50 calculates the feature amount of each block. Since the calculation method of the feature amount in each block is the same, the calculation method will be described by taking the first block (R1, G1, B1) as an example.

FIG. 5 is a diagram for explaining the method of calculating the feature amount. The control unit 50, as shown in FIG. 5A, the respective pixels 311 corresponding between the first block R1 of the R image 301, the first block G1 of the G image 401, and the first block B1 of the B image 501. A feature amount is calculated from the pixel values 411 and 511.

For example, a high-order autocorrelation feature (HLAC) is calculated as a feature amount from the pixel value of the R component, the pixel value of the G component, and the pixel value of the B component. Specifically, for example, the product of the pixel values of the respective pixels 311 included in the first block R1 of the R image 301 is calculated by applying the mask pattern 240 shown in FIG. 5B. Then, the sum of products of pixel values calculated for all the pixels is added to obtain a sum, which is set as one of the feature quantities (Σ (R × R) in FIG. 5C). Similarly, the control unit 50 calculates the product of the pixel value of each pixel 311 included in the first block R1 of the R image 301 and the pixel value of the corresponding pixel 411 included in the first block G1 of the G image 401. calculate. Then, the sum obtained by summing the products calculated for all the pixels is calculated to be one of the feature amounts (Σ (R × G) in FIG. 5C). Thus, for each block, as shown in FIG. 5C, the feature quantity (Σ (R × R)) calculated from the pixel value of the R component, the feature calculated from the pixel value of the R component and the pixel value of the G component Amount (Σ (R × G)), feature amount calculated from pixel values of R component and B component (値 (R × B)), feature amount calculated from pixel values of G component (Σ (G ×)) G) Six-dimensional feature amount (Σ (G × B)) calculated from the pixel value of G component and pixel value of B component, and the feature amount (Σ (B × B)) calculated from pixel value of B component Feature amounts of are obtained.

Next, a method of setting determination conditions for determining the presence or absence of color stain will be described. First, a large number of actual banknotes to be judged as color stains are prepared. Specifically, a plurality of official seal ticket actuals and a plurality of faded ticket actuals which are discolored by aging are prepared. Then, each of the prepared official seal ticket and the fading ticket is imaged, and as described above, a six-dimensional feature value is calculated for each block from each image.

In order to detect a color change due to aging, it is preferable that the actual color-erasing ticket to be prepared is a banknote such as a scribbled banknote or a banknote with ink stain attached, which has no color change due to reasons other than aging. For example, in the case where a bill has just been newly issued and the actual color-fade note can not be obtained, etc., an image of the color-fade note is generated in a pseudo manner from the image of the available bill. Due to the secular change, the white background portion of the banknote becomes yellowish, and the printing portion with the ink such as red and blue fades. For this reason, for example, while reducing the pixel value of each component of RGB of the bill image of the official seal note and reproducing the color change, the pixel value of the B component is compared with the pixel value of the R component and the pixel value of the G component. The yellowing is reproduced by greatly reducing the color and the like, and the image of the color fading ticket is generated in a pseudo manner. The amount of change of each pixel value of RGB when reproducing the color fade is determined, for example, with reference to the difference in color between the official seal ticket of the other denomination and the actual color of the color faded ticket.

When the feature amount is obtained for each block of each of a large number of government-sealed tickets and fading tickets, principal component analysis is performed using the obtained feature amount as a variable for each block. Then, the first to third main components are adopted in order from the highest contribution rate. Since the principal component analysis is performed on the public seal ticket and the fading ticket, the first main component is a component that indicates a change in color when the public seal ticket is fading. On the other hand, the second main component and the third main component are components showing a change in color different from the color fading. Information such as coefficients for calculating the values of the first main component, the second main component, and the third main component of each block is stored in the storage unit 56 as a determination condition relating to color contamination of each block. That is, an evaluation formula for calculating the main component score of the second main component and the third main component to be used as the evaluation value for color stain determination from the feature amount of each block is stored in advance in storage unit 56 as a determination condition. Save it. In addition, about the partial area | region on the banknote made into each block, it is preserve | saved by the memory | storage part 56 previously. For example, a block and a determination condition are set for each type of banknote. For example, after acquiring a bill image, the kind of bill can be identified first, the feature amount can be obtained from the block set for the kind, and the process can be advanced using the determination condition corresponding to the kind of bill .

FIG. 6 is a diagram showing an example of a set when plotting the main component scores of the first main component, the second main component, and the third main component. For example, the value of the first main component is determined and plotted for the same block of a large number of banknotes in which a public seal ticket, a fading ticket (usually a contamination ticket), and a color staining ticket are mixed. As a result, as shown in FIG. 6A, the set 601 of the official seal tickets, the set 611 of the fading notes, and the set 612 of the color staining notes are separated. On the other hand, when the values of the second main component and the third main component are obtained and plotted, as shown in FIG. 6B, a set 601 of official seal notes, a set 611 of fading notes, and a set 612 of color staining notes Are separated.

If the official seal ticket actual thing and the fading certificate actual thing are prepared, for each block, as shown in Figure 6 (a), the set 601 of the official seal seal ticket and the set 611 of the color fading ticket are obtained, the official seal ticket and the genuine ticket The threshold value of the first main component is set so that it can be distinguished from the other banknotes. Then, each threshold is stored in the storage unit 56 as a determination condition of each block. When identifying a bill by the bill processing apparatus 1, the control unit 50 refers to the determination condition of the storage unit 56 to obtain the value of the first main component from each block of the bill to be determined, and is set for each block Compare with the threshold value. In this way, it is possible to distinguish between the official seal ticket and the genuine ticket and the other banknotes.

If the official seal ticket actual thing and the fading certificate actual thing are prepared, for each block, as shown in Figure 6 (b), when the set 601 of official seal ticket and the set 611 of the color fading ticket are obtained, for example, these two A threshold is set based on the value of the area outer edge including the set. Then, each threshold is stored in the storage unit 56 as a determination condition of each block. When identifying a bill by the bill processing apparatus 1, the control unit 50 refers to the determination condition of the storage unit 56 to obtain the values of the second main component and the third main component from each block of the bill to be determined. Compare with the threshold set for each block. Then, if the value obtained from the block is not included in the set 601 of public seal tickets and the set 611 of color fading notes, it can be determined that this block is a block of a color stain.

That is, a threshold is set as reference data for determining the presence or absence of color stain, and is stored in advance in the storage unit 56 as a determination condition. Then, the main component score calculated by substituting the value of the feature value into the evaluation formula prepared in advance is compared with the reference data as the evaluation value to determine the presence or absence of the color stain.

In addition, although the example which prepares the official closing ticket actual thing and the color fading ticket actual thing and sets the determination conditions for color stain determination was shown, the setting method of a determination condition is not limited to this. For example, in addition to the official seal ticket and the actual faded ticket, it is possible to use an actual color stain ticket. Prepare many copies of the official seal ticket, the fading ticket and the color stain ticket, and examine the set 612 of the color stain banknotes based on the values of the second main component and the third main component as shown in FIG. . Then, for example, the threshold may be set based on the values of the second main component and the third main component that form the outer edge of the set 612 of color contamination notes. Thereby, the values of the second main component and the third main component are obtained from the block of the bill to be judged and compared with the threshold value, and if it is included in the set 612 of colored stains, it is a block of colored stains It can be determined that Also, a threshold (boundary) may be set to divide the main component space into two so that the set of colored stain notes 612 can be distinguished from the set of government sealed notes 601 and the set of faded notes 611. Thereby, the values of the second main component and the third main component are obtained from the block of the bill to be judged, and it is judged whether or not it is the block of the color stain, based on which region it is included. be able to. In addition, when examining the set 612 of color staining notes, as in the case of the color fading notes, even if the RGB pixel values of the official seal note image are changed, the image of the color staining note may be generated and used in a pseudo manner. Good.

The determination method of color stain is not limited to the aspect of directly using the values of the second main component and the third main component calculated for each block. For example, a mode may be used in which the Mahalanobis distance is calculated and determined from the values of the second main component and the third main component. For example, from the position of the data of the determination target block defined by the values of the second main component and the third main component, the Mahalanobis distance of a set 含む including the set 601 of sealed tickets and the set 611 of discolored notes is calculated. When the Mahalanobis distance exceeds a preset threshold value, it can be determined that there is color stain. Also, for example, the Mahalanobis distance of the set 612 of color contamination notes is calculated from the position of the data of the determination target block defined by the values of the second main component and the third main component. If the Mahalanobis distance does not exceed a preset threshold value, it can be determined that the block is a color stain.

Next, the flow of processing of damage identification and contamination determination performed based on the values of the first to third main components will be described. FIG. 7 is a flowchart showing an example of the process of fitness identification and contamination determination. The bill processing apparatus 1 comprehensively determines data such as an optical feature, a magnetic feature, and a thickness of a bill to identify the denomination, authenticity, and damage of the bill, but FIG. 7 relates to the determination of color contamination. Only processing is shown.

The operator places a plurality of bills to be subjected to color stain determination on the receiving unit 11 and starts bill processing. The banknotes taken into the apparatus one by one from the receiving unit 11 by the taking-in unit 10 are conveyed by the conveying unit 70 along the conveyance path. During the conveyance, the identification unit 55 acquires a color image of the entire banknote (step S1).

The control unit 50 calculates the feature amount based on the high-order autocorrelation feature from each pixel value of the R component, the G component, and the B component of the bill image for each of the plurality of blocks previously set on the bill (Step S2 ). Subsequently, the control unit 50 performs the first main component, the second main component, and the third main component for each of the plurality of blocks based on the calculated feature amount and the determination condition stored in advance in the storage unit 56. Each principal component score of is calculated (step S3). The control unit 50 determines whether the banknote is a genuine banknote based on the value of the first main component and the information stored in advance as the determination condition in the storage unit 56 (step S4).

For example, the control unit 50 calculates the Mahalanobis distance between the value of the first main component of each block and the collection 601 of the sealed tickets shown in FIG. 6 (a). Then, if the Mahalanobis distances of all of the plurality of blocks set for the bill are equal to or less than the threshold set in advance as the reference data, the control unit 50 determines that the bill is a genuine note (step S4; Yes). If at least one of the blocks has a Mahalanobis distance exceeding the threshold, the control unit 50 determines that the banknote is not a legitimate banknote (step S4; No).

When the determination result that the banknote is a genuine banknote is obtained (step S5), the control unit 50 ends the determination process. On the other hand, when it is determined that the banknote is not a legitimate banknote, that is, an unfit banknote, the control unit 50 subsequently performs a determination process to determine whether the banknote is a color-discolored banknote. (Step S6).

For example, the control unit 50 calculates the Mahalanobis distance between the values of the second main component and the third main component of each block, and the collection 612 of color stains shown in FIG. 6B. Then, if the Mahalanobis distances of all of the plurality of blocks set for the bill exceed the value set in advance as the reference data, the control unit 50 determines that the bill is not a color stain (Step S6; No) . If the Mahalanobis distance is equal to or less than the threshold value even in one of the plurality of blocks, the control unit 50 determines that the banknote is a color-stained banknote (step S6; Yes).

If it is determined that the bill is not a color stain, that is, a normal stain such as a bill that has faded due to aging (step S8), the control unit 50 ends the determination process. In addition, also in the case where the determination result that the banknote is the color contamination note is obtained (step S7), the control unit 50 ends the determination process.

However, if it is determined that the sheet is a color stain, it may be set to continue the process. For example, based on the positional relationship between the collection 612 of color stains shown in FIG. 6B and the point at which the data of the block to be determined is plotted, the color stains are classified according to the color of stain. You can also. Also, for example, based on the number of blocks determined to have color stains, the color stain notes having color stains on the entire banknote and the color stain notes having color stains on only some blocks are classified. It can also be set to perform processing.

Further, in FIG. 7, an example of plotting the data of the determination target block in the main component space consisting of the second main component and the third main component, and determining the presence or absence of color contamination based on the Mahalanobis distance from the set of color contamination notes However, the determination method is not limited to this. For example, as described above, the Mahalanobis distance from the collection of the official seal ticket and the fading ticket may be determined, and the color contamination ticket may be determined when the distance exceeds a preset threshold. Further, it may be a mode in which the Mahalanobis distance is obtained from the set of only the fading notes to determine the presence or absence of the color stain.

In this embodiment, although the example which divides the whole surface of a bill into plurality and makes it a block was shown, the setting of a block is not limited to this. If it is not necessary to determine the color stain on the entire surface of the bill, the block may be set only in the area where the color stain is to be determined. For example, in order to cope with theft or the like of a bill, there is a device for jetting special ink to the bill to color the bill when an abnormality is detected. If the area to which the special ink adheres is limited, the block may be set in only a part of the area so that color stains in this area can be detected.

In the present embodiment, an example has been shown in which the color contamination note is detected using the feature amount indicating the color tone of the block set on the bill. In addition to this, the feature amount indicating the color of the block may be used to identify the denomination or authenticity of the bill. For example, it is assumed that similar designs are printed, but there are banknotes with different shades of designs depending on the denomination, and banknotes of denominations with different shades of design depending on the year of issue of the banknotes. In this case, as described above, the denomination and issue of the bill can be determined by discriminating the bills having different color tones by using the feature quantity obtained from each pixel value of RGB, the principal component score obtained from the feature quantity, and the like. The year can be identified. Also, for example, even when a false bill whose color tone is different from that of a true bill appears, the color is similarly distinguished using the feature amount obtained from each pixel of RGB, the main component score obtained from the feature amount, etc. Thus, the authenticity of the bill can be identified. That is, the feature amount indicating the color tone of the block can be used as a color feature of a bill for various purposes in order to specify the type of the bill.

In this embodiment, an example is shown in which the feature amount is calculated using pixel values of R component, G component, and B component of a color image obtained by imaging a bill, but the color used to calculate the feature amount is limited to RGB It is not something to be done. As long as it is possible to extract the change in color due to the color fading of the bill, the feature amount may be calculated from the pixel values of other colors. For example, the pixel value of an image obtained by capturing a bill with infrared light is IR component, the pixel value of an image obtained by capturing a bill with green light is G component, and the pixel value of an image obtained by capturing a bill with purple light is V As a component, the feature amount may be calculated from pixel values of these three color components. Also, the feature amount may be calculated from pixel values of four or more color components.

In this embodiment, an example in which six-dimensional feature quantities are calculated as high-order autocorrelation features from pixel values of R, G, and B components of each block is shown, but the feature quantities are limited to this It is not a thing. For example, a value indicating a correlation feature between a target pixel and an adjacent pixel may be used as a feature amount. Specifically, for example, the product of each pixel value of the R component, G component and B component of the target pixel and each pixel value of the R component, G component and B component of the pixel adjacent to this pixel is calculated A mode may be adopted in which the sum totaled as a result of the addition is added to the feature amount, and the value of a higher order autocorrelation feature of seven or more dimensions is used as the feature amount.

Although the example which determines the presence or absence of color stain using the image which imaged the single side | surface of the banknote was shown in this embodiment, the determination method is not limited to this. For example, the image of the front surface of the bill and the image of the back surface may be acquired, and the above-described determination of color contamination may be performed on the image of each surface. For example, if it is determined that color staining is present on one of the front and back surfaces, it is determined that the sheet is a color staining note, and if it is determined that color staining is not present on both sides, it is not a color staining note. can do. Further, for example, even if there is color contamination on either one of the front and back surfaces, it may be set so as not to be judged as a color contamination note.

As described above, according to the banknote processing apparatus 1 according to the present embodiment, it is possible to obtain pixel values of a plurality of colors from a color image obtained by imaging a banknote, and to calculate a feature amount indicating a color tone of the banknote. The calculated feature value can be substituted into a previously prepared evaluation formula to calculate an evaluation value for determining the presence or absence of color stain. By comparing the calculated evaluation value with a threshold set in advance as reference data, it is possible to determine the presence or absence of color stain. The evaluation formula and the threshold value are obtained by subjecting the feature quantities of a large number of public-sealed notes and faded notes to principal component analysis, and by using these, banknotes whose color is changed due to fading and color stains are attached It can be distinguished from the color stains. As a result, it is possible to detect a color contamination note with color stains with high accuracy.

As described above, the paper sheet stain determination apparatus and the sheet stain detection method according to the present invention are useful for determining the presence or absence of color stains that are colored widely on the sheets.

DESCRIPTION OF SYMBOLS 1 banknote processing device 10 taking-in unit 11 receiving unit 50 control unit 51 operation unit 52 display unit 55 identification unit 56 storage unit 60 (60a to 60h) stacking unit 62 (62a to 62h) individual display unit 65 (65a, 65b) Reject Part 70 Conveying part 71 Branching

members

72, 73 Banknote detection sensor 80 Light source 81 Line sensor

Claims

An image acquisition unit that acquires an image of a sheet,
A storage unit storing reference data for identifying a change in color of the paper sheet due to aging;
While detecting a sheet whose color has changed from a color immediately after printing in a region of a predetermined area or more based on the image of the sheet and the reference data, the detected sheet changes in color due to aging. What is claimed is: 1. A paper sheet contamination judgment apparatus comprising: a judgment unit that judges whether the sheet is a colored sheet or a colored soiled sheet having a color stain.
In the reference data, a feature amount is calculated from pixel values of a plurality of colors obtained by color separation of a color image of a paper sheet, and an evaluation value obtained by substituting the feature amount into a predetermined evaluation formula It is a threshold for determining whether it is a value indicating that it is
The determination unit determines whether the paper sheet is a color-damaged paper sheet by calculating the evaluation value from the image of the paper sheet acquired by the image acquisition unit and comparing the evaluation value with the threshold value. The paper sheet dirt judgment device according to claim 1.
The apparatus according to claim 2, wherein the feature amount is a value indicating a correlation feature of pixel values of the plurality of colors.
The evaluation formula is a principal component analysis of the feature amounts calculated from images of a plurality of sheets having no change in color due to aging and images of a plurality of sheets changing in color due to aging. 4. The paper sheet contamination determination apparatus according to claim 2, wherein the apparatus is a formula for calculating the obtained principal component score of the predetermined principal component.
The images of a plurality of paper sheets whose color has changed due to the aging change are images generated by artificially reproducing the change of the color due to the aging change by changing the color component of the image obtained by imaging the paper sheets. The paper sheet dirt judgment apparatus according to claim 4,
The sheet according to any one of claims 2 to 5, wherein the pixel values of the plurality of colors are a pixel value of an R component, a pixel value of a G component, and a pixel value of a B component. Pollution detection device.
7. The apparatus according to any one of claims 2 to 6, wherein the determination unit determines, based on the evaluation value, whether or not color stains attached to a plurality of colored stains are the same. The paper sheet dirt judgment device according to the paragraph.
The determination unit calculates the evaluation value from pixel values of pixels forming the block, targeting a partial area previously set as a block on the sheet, and the sheet is a color-damaged sheet The paper sheet dirt judgment apparatus according to any one of claims 2 to 6, wherein it is judged whether or not.
The block is set by dividing the entire surface of the sheet into a plurality of parts.
The determination unit determines whether the color-damaged paper sheet is a paper sheet having color stains on the entire surface or only a partial area has color stain, based on the evaluation value calculated for each block. 9. The paper sheet stain determination apparatus according to claim 8, wherein it is determined whether the sheet is a leaf.
A receiving unit for receiving a plurality of sheets,
A conveying unit that conveys the sheets received in the receiving unit one by one;
And a plurality of stacking units for stacking sheets,
The plurality of sheets received in the receiving unit are classified into a plurality of stacking units based on the determination result of the determination unit, and the plurality of stacking units are stacked. The paper sheet contamination determination apparatus described above.
A paper sheet stain determination method is a sheet sheet stain determination method that determines the presence or absence of color stains.
Obtaining an image of a sheet, and
A sheet having a color changed from a color immediately after printing in a region of a predetermined area or more based on an image obtained by imaging the sheet and reference data for specifying a change in color of the sheet due to aging. And a step of determining whether the sheet is a sheet whose color has changed due to aging or a color-stained sheet having a color stain.