JP2024079976A - Authenticity determination device and program - Google Patents

Abstract

[Problem] To provide an authenticity determination device etc. capable of suitably determining the authenticity of an identification card. [Solution] An authenticity determination device 3 determines the authenticity of an ID card. The authenticity determination device 3 has an acquisition means 301 that acquires an inspection image by cutting out a predetermined area of the ID card from an infrared image of the ID card, and an authenticity determination means 302 that obtains a histogram indicating the number of pixels for each pixel value for multiple images obtained by dividing the inspection image, calculates a dissimilarity indicating the degree of difference between each histogram and a standard histogram, and determines the authenticity of the ID card to be determined from the multiple dissimilarity levels. The standard histogram indicates the number of pixels for each pixel value for multiple images obtained by dividing a predetermined area of an infrared image of a genuine ID card in the same manner as the ID card to be determined. [Selected Figure] Figure 5

Description

The present invention relates to an authenticity determination device and a program therefor.

When opening an account at a financial institution or signing a contract with a mobile carrier, identification using an ID card (identification proof) such as a driver's license is required, but there has been an increase in cases where ID cards are forged or altered in order to open an account or sign a contract with a mobile carrier while impersonating another person for criminal purposes such as special fraud.

On the other hand, for example, at a typical financial institution, the user goes to the financial institution to present their ID card, and the financial institution typically uses the submitted ID card to verify the user's identity in person, allowing the financial institution to detect counterfeit or altered ID cards by visual inspection or touch.

Patent documents 1 and 2 also describe an authenticity determination device that automatically determines the authenticity of an ID card from an image obtained by reading the face of the ID card with a scanner or the like, and it is also possible to determine the authenticity of an ID card by reading a submitted ID card with a scanner or the like.

JP 2011-34535 A JP 2019-117549 A

One of the challenges in determining the authenticity of an ID card from an image of the face of the card is that when an ID card is carried around for a long period of time, scratches and dirt can appear on the surface of the ID card, and this scratches and dirt can significantly reduce the accuracy of the authenticity determination. This can lead to problems such as the ID card becoming impossible to identify, or genuine ID cards being mistakenly detected as fake.

The present invention has been made in consideration of the above problems, and aims to provide an authenticity determination device etc. that can suitably determine the authenticity of identification cards.

The first invention for solving the above-mentioned problems is an authenticity determination device for determining the authenticity of an ID card, comprising: an acquisition means for acquiring an inspection image by cutting out a predetermined area of the ID card from a photographed image of the ID card; and an authenticity determination means for determining a feature value indicating the distribution of the number of pixels for each pixel value for a plurality of images obtained by dividing the inspection image, calculating a dissimilarity value indicating the degree of difference from a standard value for each feature value, and determining the authenticity of the ID card to be determined from the plurality of dissimilarity values, wherein the standard value indicates the distribution of the number of pixels for each pixel value for a plurality of images obtained by dividing the predetermined area of a photographed image of a genuine ID card in the same manner as the ID card to be determined.

In the present invention, a specified area of a photographed image of an ID card is cut out to create an inspection image, the inspection image is divided into multiple images, the above-mentioned feature amount is obtained for each image, and the degree of difference between each feature amount and the above-mentioned standard value is calculated. By performing an authenticity determination based on these degrees of difference, it is possible to preferably detect fake ID cards whose image features in the above-mentioned specified area differ from those of genuine ID cards. With this determination method, even if there are scratches or stains in some areas of the inspection image, the effect on the overall authenticity determination result can be reduced, and the accuracy of the authenticity determination will not be significantly reduced.

It is desirable that the feature amount and the standard value are histograms showing a distribution of the number of pixels for each pixel value, and that the dissimilarity is a Bhattacharyya distance.
In the present invention, the accuracy of authenticity determination is improved by using the Bhattacharyya distance, which is an index of similarity between histograms, as the degree of dissimilarity.

The authenticity determination means preferably performs authenticity determination by comparing a sum of the plurality of dissimilarities with a threshold value. In addition, when calculating the sum, it is preferable to weight the difference according to a position within the predetermined region of the image.
By comparing the sum of the dissimilarities with a threshold value, even if scratches or stains are present in a part of the inspection image, the effect on the authenticity determination is minimal, and it is possible to prevent a decrease in the accuracy of the authenticity determination. In addition, by weighting the images according to their positions when calculating the sum, it is possible to perform a determination that places importance on the image at the target position, thereby improving the accuracy of the authenticity determination.

It is also preferable that the captured image is an infrared image of the identification card captured under infrared illumination.
This makes it possible to determine the authenticity of an identification card based on image features of an infrared image that cannot be seen under visible light, and also makes it possible to deal with clever counterfeiting or alteration of identification cards.

The plurality of images preferably include images obtained by dividing the inspection image into different sizes.
In this way, by obtaining images of various sizes from the inspection image and using them for authenticity determination, the accuracy of authenticity determination can be improved.

A second invention is a program for causing a computer to function as an authenticity determination device that determines the authenticity of an identification card, the authenticity determination device comprising: an acquisition means for acquiring an inspection image by cutting out a specified area of the identification card from a photographed image of the identification card; and an authenticity determination means for determining a feature indicating the distribution of the number of pixels for each pixel value for a plurality of images obtained by dividing the inspection image, calculating a dissimilarity indicating the degree of difference from a standard value for each feature, and determining the authenticity of the identification card to be determined from the plurality of dissimilarity values, wherein the standard value indicates the distribution of the number of pixels for each pixel value for a plurality of images obtained by dividing the specified area of a photographed image of a genuine identification card in the same manner as the identification card to be determined.
A second invention is a program for the authenticity determining device of the first invention.

The present invention makes it possible to provide an authenticity determination device that can effectively determine the authenticity of an identification card.

FIG. 1 shows an authenticity determination system 1. 2 is a diagram showing a camera 21 and a light 22 in the scanner 2. FIG. 2 is a diagram showing the hardware configuration of an authenticity determination device 3. FIG. 1 shows an ID card 10. FIG. 2 is a diagram showing the function of the authenticity determination device 3. 1 is a flowchart showing an outline of an authenticity determining method. 4 is a flowchart showing a procedure for determining authenticity based on an infrared image of an ID card 10. 3A to 3C are diagrams for explaining division of an inspection image 100. FIG. 2 is a diagram showing a histogram of an image n obtained by dividing the inspection image 100. FIG. 4 is a diagram for explaining calculation of a standard histogram Hs _m .

The following describes in detail a preferred embodiment of the present invention with reference to the drawings.

(1. Authenticity Determination System 1)
Fig. 1 is a diagram showing an authenticity determination system 1 having an authenticity determination device 3 according to an embodiment of the present invention. As shown in Fig. 1, the authenticity determination system 1 is configured by connecting a scanner 2 and an authenticity determination device 3 so as to be able to communicate with each other by wire or wirelessly.

In the authenticity determination system 1, a photographed image of an ID card 10 is sent from a scanner 2 to an authenticity determination device 3, which then determines the authenticity of the ID card 10 from the photographed image. The purpose of authenticity determination is not particularly limited, and it can be applied to various situations such as when opening an account at a financial institution, when signing a contract with a mobile carrier, and when verifying the identity of a person during procedures at various government agencies.

The scanner 2 photographs the ID card 10. As shown in FIG. 2, a camera 21 and a light 22 are provided inside the scanner 2. The scanner 2 photographs the ID card 10 set in a predetermined position with the camera 21 provided directly above. The lights 22 are provided diagonally above both sides of the ID card 10.

The camera 21 is an area camera that is composed of an optical lens, an imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal-Oxide Semiconductor), an A/D (Analog/Digital) converter, etc. In addition, the lighting 22 in this embodiment is an infrared lighting that irradiates the ID card 10 with infrared rays.

Figure 3 is a diagram showing the hardware configuration of the authenticity determination device 3. The authenticity determination device 3 can be realized by a computer configured by connecting a control unit 31, a memory unit 32, a communication unit 33, a display unit 34, etc. via a bus or the like. However, the authenticity determination device 3 is not limited to this, and various configurations can be used as appropriate.

The control unit 31 is composed of a CPU, ROM, RAM, etc. The CPU loads programs related to the processing of the authenticity determination device 3 stored in storage media such as the memory unit 32 and ROM into a work area on the RAM and executes them. The ROM is a non-volatile memory, and permanently stores programs such as the boot program and BIOS, as well as data. The RAM is a volatile memory, and temporarily stores programs and data loaded from the memory unit 32, ROM, etc., and also has a work area used by the control unit 31 to perform various processes.

The memory unit 32 is a hard disk drive, solid state drive, flash memory, etc., and stores the programs executed by the authenticity determination device 3 during the processing described below, data necessary for program execution, the OS, etc.

The communication unit 33 is a communication interface that mediates communication with the scanner 2. The display unit 34 is an LCD display or the like, and displays various information related to the authenticity determination process of this embodiment.

(2. ID Card 10)
In this embodiment, the ID card 10 is an identity card to be subjected to the authenticity determination. Identification cards are media used for administrative procedures and identity verification by various administrative agencies, financial institutions, mobile phone carriers, etc., and in this embodiment, the ID card 10 is a My Number card.

Figure 4 is a diagram showing an outline of an ID card 10 (My Number card), and shows a schematic diagram with some of the face of the ID card 10 omitted. In the ID card 10, various face information is printed on a rectangular substrate. For example, in the case of the My Number card, text information such as the person's name, date of birth, address, and the expiration date of the My Number card are printed in predetermined positions. In addition, image information such as the My Number card mark 101, the person's facial image, and various lines are also printed in predetermined positions.

(3. Functions of Authenticity Determination Device 3)
5 is a block diagram showing the functions of the authenticity determination device 3. The authenticity determination device 3 includes an acquisition unit 301, an authenticity determination unit 302, and the like.

The acquisition means 301 is a means for the control unit 31 of the authenticity determination device 3 to receive a captured image of the ID card 10 from the scanner 2 via the communication unit 33, and to acquire an inspection image to be used for authenticity determination from the captured image. The inspection image will be described later.

The authenticity determination means 302 is a means by which the control unit 31 of the authenticity determination device 3 uses the inspection image to determine the authenticity of the ID card 10. Details of this authenticity determination will be described later.

(4. Authenticity Determination Method)
Fig. 6 is a flowchart showing an outline of the authenticity determination method executed by the authenticity determination system 1. S1 to S2 in Fig. 6 are processes executed by a control unit (not shown) of the scanner 2 by controlling each unit of the scanner 2, and S3 to S5 are processes executed by a control unit 31 of the authenticity determination device 3 by controlling each unit of the authenticity determination device 3.

In this embodiment, the user first places the ID card 10 in a predetermined position on the scanner 2, and the scanner 2 photographs the ID card 10 with the camera 21 in response to the user's operation (S1). In this embodiment, an infrared image is obtained as the photographed image of the ID card 10 by photographing the ID card 10 under infrared illumination. In this embodiment, the infrared image represents the pixel colors as pixel values of three channels: R (red), G (green), and B (blue).

The scanner 2 transmits the infrared image obtained by photographing the ID card 10 in S1 to the authenticity determination device 3 (S2). The authenticity determination device 3 receives the infrared image of the ID card 10 (S3) and determines the authenticity of the ID card 10 from the infrared image (S4). Details of the authenticity determination in S4 will be described later.

The authenticity determination device 3 displays the result of the authenticity determination of the ID card 10 on the display unit 34 (S5) and ends the process. The person in charge can take appropriate action depending on the displayed content.

(5. Authenticity Verification Using Infrared Images of ID Card 10)
In this embodiment, the authenticity of the ID card 10 is determined by utilizing the fact that a predetermined area of an infrared image of a genuine ID card 10 has a predetermined image feature. That is, due to differences in printing methods and inks used when manufacturing a genuine ID card 10 and when the ID card 10 is forged or altered, there are cases in which a predetermined area of an infrared image of a forged or altered ID card 10 does not have the above image feature. In this embodiment, such an ID card 10 can be suitably detected as a fake ID card 10. Hereinafter, a procedure for authenticity determination using an infrared image of an ID card 10 will be described with reference to FIG. 7 and the like. FIG. 7 is a flowchart showing the procedure for authenticity determination in S4 of FIG. 6.

In this embodiment, in S4, a predetermined area of the ID card 10 is first cut out from the infrared image received in S3 (see FIG. 6) and used as an inspection image (S401).

In this embodiment, the predetermined area cut out in S401 is an area including the above-mentioned mark 101 on the ID card 10. The symbol R in FIG. 4 is an example of this predetermined area, and FIG. 8(a) is an example of an inspection image 100 obtained by cutting out the predetermined area R from an infrared image.

The authenticity determination device 3 resizes the inspection image 100 to reduce it to a predetermined size, and then performs a smoothing process on the inspection image 100 (S402). There is no particular restriction on the specific method of the smoothing process, and it is possible to perform a known low-pass filter process, such as a convolution operation of a predetermined coefficient matrix. The process of S402 speeds up the processes from S403 onwards.

Next, the authenticity determination device 3 divides the inspection image 100 (S403). In this embodiment, in S403, as shown in FIG. 8(b), 16 1/16 images 110 are created by equally dividing the inspection image 100 into 4 rows and 4 columns, and 4 1/4 images 120 are created by equally dividing the inspection image 100 into 2 rows and 2 columns. 21 types of images n, including the 1/1 image 130, which is the inspection image 100 before division, are used for authenticity determination. n is a serial number assigned to each of the 1/16 images 110, 1/4 images 120, and 1/1 images 130, and the circled numbers in FIG. 8(b) indicate this serial number.

After that, the authenticity determination device 3 creates a histogram, which is a feature indicating the distribution of the number of pixels for each pixel value, for each RGB channel for each image n (S404). FIG. 9 shows an example of a histogram of the B channel created for each image n, where the horizontal axis is the histogram class (pixel value) and the vertical axis is the number of pixels for each class. Since histograms are created for each RGB channel for 21 types of images n, a total of 21 x 3 = 63 histograms are obtained in S404. Below, these histograms will be described with the symbol _Hm attached. m is a serial number attached to the 63 histograms, m = 1 to 63.

The authenticity determination device 3 calculates a degree of difference indicating the degree of difference from a standard histogram (standard value) for each of these histograms _Hm (S405). The standard histogram is a standard value that indicates the image features of a predetermined region R of the infrared image of a genuine ID card 10, and details thereof and the above-mentioned degree of difference will be described later.

The authenticity determination device 3 compares the sum of the multiple dissimilarities calculated in S405 with a threshold value, and if the sum of the dissimilarities is equal to or less than the threshold value (S406; YES), the authenticity determination device 3 determines that the ID card 10 being determined is genuine (S407) and ends the process. On the other hand, if the sum of the dissimilarities exceeds the threshold value (S406; NO), the authenticity determination device 3 determines that the ID card 10 being determined is false (S408) and ends the process. The above threshold value is set to an appropriate value in advance and is stored in advance in the memory unit 32 of the authenticity determination device 3.

6. Standard Histograms and Dissimilarity Measures
In this embodiment, in order to create the standard histogram, a number of genuine ID cards 10 are prepared in advance, and infrared images of these ID cards 10 (hereinafter referred to as "prepared ID cards") are taken with the scanner 2. Then, from each infrared image, image n is obtained in the same manner as in S401 to S404 (see FIG. 7) described above, and a histogram _Hm is created. Image n is composed of a 1/16 image 110, a 1/4 image 120, and a 1/1 image 130 obtained by dividing a predetermined region R of the infrared image of the prepared ID card in the same manner as the ID card 10 to be judged.

Fig. 10(a) is a graph showing a histogram _Hm1 of a certain serial number m=m1 for each pre-prepared ID card, with the horizontal axis representing the histogram class (pixel value) and the vertical axis representing the number of pixels for each class. The symbol k in the figure is the serial number given to the pre-prepared ID card. The authenticity determination device 3 calculates the average value of the number of pixels for each class among the pre-prepared ID cards for the histogram _Hm1 of each pre-prepared ID card, and as shown in Fig. 10(b), the average value represented for each histogram class (pixel value) is taken as the standard value of the histogram _Hm1 , i.e., the standard histogram.

Like the histogram _Hm , the standard histogram shows the distribution of the number of pixels for each pixel value in image n, and is created for each RGB channel for each of the 21 types of images n, resulting in a total of 63 standard histograms. These standard histograms will be denoted by _Hsm in the following explanation. m is a serial number assigned to the 63 standard histograms in the same order as the histogram _Hm . For example, if the value of m is the same, such as in histogram _H11 and standard histogram _Hs11 , then the image n on which these histograms were created and the channel (either RGB) of the pixel values of the histograms are the same.

The above processing can be performed by a computer serving as the authenticity determination device 3, or by another computer communicatively connected to the scanner 2 that photographs the pre-prepared ID card, and the 63 standard histograms Hs _m created as described above are stored in advance in the memory unit 32 of the authenticity determination device 3.

ここで、iはヒストグラムの各階級に付した通し番号であり、1からNまでの自然数をとる。またH_m(i)は判定対象のIDカード１０のヒストグラムH_mのi番目の階級の画素数であり、Hs_m(i)は標準ヒストグラムHs_mのi番目の階級の画素数である。式（１）で算出されるBC_mはBhattacharyya係数であり、式（２）で算出されるBhattacharyya距離D_mは、0から1までの値をとる。 Then, in S405 (see FIG. 7), the authenticity determination device 3 calculates the known Bhattacharyya distance Dm as the degree of difference between the histogram _Hm of the ID card 10 to be determined created in S404 and the standard histogram _Hsm , using the following formulas (1) to (3). _The Bhattacharyya distance _Dm is a known value that serves as an index of similarity between histograms.

Here, i is a serial number assigned to each class of the histogram and takes a natural number from 1 to N. Also, _Hm (i) is the number of pixels in the i-th class of the histogram _Hm of the ID card 10 to be judged, and _Hsm (i) is the number of pixels in the i-th class of the standard histogram _Hsm . _BCm calculated by equation (1) is a Bhattacharyya coefficient, and the Bhattacharyya distance _Dm calculated by equation (2) takes a value from 0 to 1.

ここで、MはヒストグラムH_mの総数であり、本実施形態ではM＝63である。 Then, in the above-mentioned S406 (see FIG. 7), the authenticity determination device 3 calculates the sum V of the Bhattacharyya distances _Dm obtained for each histogram _Hm by the following formula (4), and compares this with a threshold value.

Here, M is the total number of histograms _Hm , and in this embodiment, M=63.

As described above, in this embodiment, a predetermined region R of an infrared image of an ID card 10 is cut out to produce an inspection image 100, the inspection image 100 is divided into a plurality of images n, a histogram _Hm of each image n is obtained, and the degree of difference between each histogram _Hm and a standard histogram _Hsm is calculated. By performing an authenticity determination based on these degrees of difference, a fake ID card 10 whose image features of the predetermined region R are different from those of a genuine ID card 10 can be suitably detected. According to this determination method, even if scratches or stains are present in a part of the inspection image 100, the influence on the overall authenticity determination result can be reduced, and the accuracy of the authenticity determination is not significantly reduced.

In this embodiment, the accuracy of the authenticity determination is improved by using the Bhattacharyya distance _Dm as the degree of difference. Then, by comparing the sum V of the multiple Bhattacharyya distances _Dm with a threshold value, even if scratches or stains are present in a part of the inspection image 100, the effect on the authenticity determination is made small, and it is possible to prevent the accuracy of the authenticity determination from being reduced.

In addition, in this embodiment, by using an infrared image of the ID card 10 to determine authenticity, it is possible to determine the authenticity of the ID card 10 based on image features of the infrared image that cannot be seen under visible light, and it is also possible to deal with clever counterfeiting or alteration of the ID card 10.

Furthermore, in this embodiment, the image n for which the histogram _Hm is calculated includes inspection image 100 divided into different sizes, and images n of various sizes are obtained from inspection image 100 and used for authenticity determination, thereby improving the accuracy of authenticity determination.

However, the present invention is not limited to the above embodiment. For example, the position of the mark 101 and its image features may differ slightly for each manufacturer of the ID card 10. In that case, the position of the predetermined region R and the standard histogram Hs _m may be determined for each manufacturer and stored in the memory unit 32 of the authenticity determination device 3. In the processes of S401 to S405, the Bhattacharyya distance D _m , which is the degree of difference, is calculated for each manufacturer using the predetermined region R and the standard histogram Hs _m , and in S406, if the sum V calculated for any manufacturer is equal to or less than a threshold value, the ID card 10 can be determined to be authentic.

For example, the Bhattacharyya distance _Dm is calculated using a predetermined region R and a standard histogram Hs _m defined for a manufacturer a of the ID card 10, and the Bhattacharyya distance _Dm is calculated using a predetermined region R and a standard histogram Hs _m defined for another manufacturer b. Then, even if the sum V of the former Bhattacharyya distances _Dm exceeds a threshold, if the value of the sum V of the latter Bhattacharyya distances _Dm is equal to or less than a threshold, the ID card 10 to be judged is a genuine ID card 10 manufactured by the manufacturer b and can be judged to be genuine. If manufacturer identification information indicating the manufacturer of the ID card 10 is stored in an IC chip (not shown) of the ID card 10, the manufacturer identification information may be read by a reading device (not shown) provided in the scanner 2 and transmitted to the authenticity determination device 3, and the predetermined region R and the standard histogram Hs _m corresponding to the manufacturer identification information may be used to calculate the Bhattacharyya distance _Dm .

Furthermore, the method of dividing the inspection image 100 (such as the size and shape of image n) is not limited to the example in FIG. 8(b). The specified region R of the ID card 10 from which the inspection image 100 is cut out is also not limited to the example in FIG. 4, and may be any region whose image characteristics change from those of a genuine ID card 10 if the ID card 10 is counterfeited, altered, etc.

In this embodiment, the ID card 10 is photographed under infrared illumination, but the inspection image 100 may be obtained by cutting out a predetermined region R from an image of the ID card 10 photographed under visible light illumination. A light 22 (visible light light) that irradiates the ID card 10 with visible light is provided inside the scanner 2. In this case, the predetermined region R may be an area whose image characteristics change from those of a genuine ID card 10 if the ID card 10 is counterfeited or altered.

In addition, in this embodiment, the ID card 10 is a My Number card, but the ID card 10 is not limited to this and may be a driver's license, residence card, special permanent resident certificate, etc. The configuration of the printed portion on the substrate varies depending on the type of ID card 10, such as My Number card, driver's license, residence card, special permanent resident certificate, etc., but for each of these ID cards 10, if the ID card 10 is counterfeited, altered, etc., the area where the image characteristics change from the genuine ID card 10 can be defined as the specified area R.

If a predetermined region R and a standard histogram Hs _m are determined for each type of ID card 10 and stored in the memory unit 32 of the authenticity determination device 3, the authenticity determination device 3 can determine the authenticity of a plurality of types of ID cards 10. For example, the type identification information indicating the type of ID card 10 stored in the IC chip of the ID card 10 is read by the reading device of the scanner 2 and transmitted to the authenticity determination device 3, whereby the authenticity determination can be performed using the predetermined region R and the standard histogram Hs _m according to the type of ID card 10. Alternatively, a photographed image of the ID card 10 taken under visible light illumination may be transmitted to the authenticity determination device 3, and the authenticity determination device 3 may determine the type of the ID card 10 from the photographed image.

In this embodiment, the simple sum of the Bhattacharyya distances Dm is calculated as the sum V of the plurality of Bhattacharyya distances _Dm , but the weighted sum of the Bhattacharyya distances _Dm weighted according to the position of the image n in the predetermined region R may be calculated as the sum _V. For example, in the 1/16 image 110 in FIG. 8B, the Bhattacharyya distances Dm of the four images (n=6, 7, 10, 11) in the inner region where scratches and the like are relatively unlikely to occur are given a larger weighting coefficient than the Bhattacharyya distances _Dm of the 12 images (n=1-5, 8-9, 12-16) in the outer region where scratches and the _like are relatively likely to occur. By performing a judgment that places importance on the image n at the attention position in this way, the accuracy of the authenticity judgment can be improved.

The method of authenticity determination is not limited to comparing the sum V of the Bhattacharyya distances _Dm with a threshold value, and may be based on the multiple Bhattacharyya distances _Dm calculated in S405 (see FIG. 7). For example, each Bhattacharyya distance _Dm may be compared with a threshold value, and if the number of Bhattacharyya distances _Dm exceeding the threshold value is equal to or greater than a predetermined number, the ID card 10 may be determined to be fake.

In this embodiment, the Bhattacharyya distance _Dm is calculated as the dissimilarity in S405, but the dissimilarity is not limited to this and may be anything that can express the degree of difference between the histogram _Hm created in S404 and the standard histogram _Hsm . For example, the correlation value between both histograms may be used.

In this embodiment, the histogram _Hm and the standard histogram _Hsm are obtained as feature amounts and standard values indicating the distribution of the number of pixels for each pixel value of the image n, but other indices may be used as long as they indicate the distribution of the number of pixels for each pixel value.

The above describes preferred embodiments of the present invention with reference to the attached drawings, but the present invention is not limited to these examples. It is clear that a person skilled in the art can come up with various modified or revised examples within the scope of the technical ideas disclosed in this application, and it is understood that these also naturally fall within the technical scope of the present invention.

1: Authenticity determination system 2: Scanner 3: Authenticity determination device 10: ID card 21: Camera 22: Lighting 100: Inspection image 301: Acquisition means 302: Authenticity determination means

Claims (7)

An authenticity determination device for determining the authenticity of an identification card,
an acquisition means for acquiring an inspection image by cutting out a predetermined area of the identification card from a photographed image of the identification card;
an authenticity determination means for determining a feature quantity indicating a distribution of the number of pixels for each pixel value for a plurality of images obtained by dividing the inspection image, calculating a degree of difference indicating the degree of difference from a standard value of each feature quantity, and determining the authenticity of the identification card to be determined from the plurality of degrees of difference;
having
An authenticity determination device characterized in that the standard value indicates the distribution of the number of pixels for each pixel value for multiple images obtained by dividing the specified area of a photographed image of a genuine identification card in the same manner as the identification card to be judged. the feature amount and the standard value are histograms showing a distribution of the number of pixels for each pixel value,
2. The authenticity determining device according to claim 1, wherein the degree of difference is a Bhattacharyya distance. The authenticity determination device according to claim 1, characterized in that the authenticity determination means performs authenticity determination by comparing the sum of the multiple dissimilarity scores with a threshold value. The authenticity determination device according to claim 3, characterized in that the authenticity determination means performs weighting according to the position of the image within the specified area when calculating the sum. The authenticity determination device according to claim 1, characterized in that the captured image is an infrared image of the identification card captured under infrared illumination. The authenticity determination device according to claim 1, characterized in that the multiple images include images obtained by dividing the inspection image into different sizes. Computer,
An authenticity determination device for determining the authenticity of an identification card,
an acquisition means for acquiring an inspection image by cutting out a predetermined area of the identification card from a photographed image of the identification card;
an authenticity determination means for determining a feature quantity indicating a distribution of the number of pixels for each pixel value for a plurality of images obtained by dividing the inspection image, calculating a degree of difference indicating the degree of difference from a standard value of each feature quantity, and determining the authenticity of the identification card to be determined from the plurality of degrees of difference;
having
A program for functioning as an authenticity determination device, characterized in that the standard value indicates the distribution of the number of pixels for each pixel value for multiple images obtained by dividing the specified area of a photographed image of a genuine identification card in the same manner as the identification card to be determined.

Images