JP7794093B2 - Authenticity determination device and program - Google Patents

Description

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

When opening an account, for example, the user typically visits the financial institution and submits their ID card, and the financial institution then uses the ID card to verify the user's identity in person. There are also attempts to make various procedures more convenient by automatically obtaining various information from the user's ID card.

In such situations, it is important to determine whether the ID card is authentic and not counterfeit or altered. Patent Document 1 describes technology for determining the authenticity of an ID card from an image of the ID card, making it possible to automatically determine the authenticity of an ID card based on the characteristics of the image.

Japanese Patent Application Laid-Open No. 2011-34535

However, the technology in Patent Document 1 is designed to determine the authenticity of ID cards with specific characteristics, and is not designed to determine the authenticity of other types of ID cards. In situations such as those described above, multiple types of ID cards are often available, and a system that can determine the authenticity of these multiple types of ID cards is desired.

The present invention was made in consideration of the above problems, and aims to provide an authenticity determination device and the like for determining the authenticity of multiple types of cards.

The first invention for solving the above-mentioned problems is an authenticity determination device that determines the authenticity of a card from an image of an inspection area of the card, comprising: an acquisition means for acquiring a photographed image of the card and type identification information that can identify the type of the card; and an authenticity determination means that acquires an image of the inspection area at a different position depending on the type of card based on the photographed image and the type identification information, and determines the authenticity of multiple types of cards from the image of the inspection area using a common algorithm, wherein the photographed images of the card are a pair of photographed images taken by turning on light sources on both sides of the card, one side at a time; the image of the inspection area is an image in a difference image created by taking the difference in gradation values of the image of the card obtained from each of the pair of photographed images; and the common algorithm determines a determination value based on the number of bright points in the image of the inspection area and compares the determination value with a threshold value .

Although the configuration of a card's face differs depending on the type of card, this invention determines authenticity from images of inspection areas positioned differently depending on the card type, allowing a common algorithm to be effectively applied based on the card type identification information. As a result, this invention can determine the authenticity of multiple types of cards without having to switch algorithms for each card type.

In the present invention, when a card is falsified by attaching a piece of paper or the like on which false card information is printed to the card, or by scratching off the card's card information and then writing in false card information, a step is created on the card due to the attachment trace or scratching trace, and this step appears as a light area or a dark area when the card is photographed with a light source located on one side of the card turned on, and this can be used to determine the authenticity of the card. Also, by obtaining an image of the card from each of a pair of photographed images taken with the light sources on both sides of the card turned on, and then taking the difference between these images, only the area where the step has occurred can be extracted as a difference image, allowing for appropriate authentication.

The second invention is an authenticity determination device that determines the authenticity of a card from an image of an inspection area of the card, and comprises: an acquisition means that acquires a photographed image of the card and type identification information that can identify the type of the card; and an authenticity determination means that acquires an image of the inspection area at a different position depending on the type of card based on the photographed image and the type identification information, and determines the authenticity of multiple types of cards from the image of the inspection area using a common algorithm, wherein the photographed image of the card is a visible light image and an infrared image of the card, and the common algorithm calculates a discrimination value as the number of pixels in the inspection area whose shading in the visible light image and the infrared image meets a predetermined standard, and determines whether the inspection area is positive or negative based on the result of comparing the discrimination value with a threshold.
In the present invention, a genuine card is manufactured by printing each area of the card surface using a predetermined printing method, and the appearance of the shading of these areas in visible light images and infrared images differs depending on the ink used, etc., and this can be used to determine authenticity. For example, areas printed with ink containing an infrared-absorbing component, such as carbon, appear as dark areas (high-density areas) in both visible light images and infrared images, while areas printed with ink that does not absorb infrared light appear as dark areas in visible light images and light areas (low-density areas) in infrared images. This makes it possible to effectively detect cases of counterfeiting or alteration using ink with different infrared absorption characteristics from the ink used on genuine cards.

It is desirable that a plurality of inspection areas are set for each of a plurality of types of cards.
This improves the accuracy of authenticity determination.

A third invention is a program for causing a computer to function as an authenticity determination device that determines the authenticity of a card from an image of an inspection area of the card, comprising: an acquisition means for acquiring a photographed image of the card and type identification information that can identify the type of the card; and an authenticity determination means for acquiring an image of the inspection area at a different position depending on the type of card based on the photographed image and the type identification information, and determining the authenticity of multiple types of cards from the image of the inspection area using a common algorithm, wherein the photographed images of the card are a pair of photographed images taken by turning on light sources on both sides of the card, one side at a time; the image of the inspection area is an image in a difference image created by taking the difference in gradation values of the image of the card obtained from each of the pair of photographed images; and the common algorithm for determining a determination value based on the number of bright points in the image of the inspection area and comparing the determination value with a threshold value .
A third invention is a program for the authenticity determination device of the first invention.
A fourth invention is a program for causing a computer to function as an authenticity determination device that determines the authenticity of a card from an image of an inspection area of the card, comprising: an acquisition means for acquiring a photographed image of the card and type identification information that can identify the type of the card; and an authenticity determination means for acquiring an image of the inspection area at a position that varies depending on the type of card based on the photographed image and the type identification information, and determining the authenticity of multiple types of cards from the image of the inspection area using a common algorithm, wherein the photographed image of the card is a visible light image and an infrared image of the card, and the common algorithm calculates a discrimination value as the number of pixels in the inspection area whose shading in the visible light image and the infrared image meets a predetermined standard, and determines whether the inspection area is genuine or not based on the result of comparing the discrimination value with a threshold.
A fourth aspect of the present invention is a program for the authenticity determination device of the second aspect of the present invention .

This invention makes it possible to provide an authenticity determination device for determining the authenticity of multiple types of cards.

FIG. 1 is a diagram showing an authenticity determination system 1. FIG. 2 is a diagram showing a visible light camera 21 and a light source 22 in the reading device 2. FIG. 2 is a diagram showing the hardware configuration of the authenticity determination device 3. FIG. 1 is a diagram showing an example of 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 determination method. 1A and 1B are diagrams for explaining photographing of an ID card 10. 10 is a flowchart showing the procedure for determining authenticity. 1 is a diagram showing a piece of paper 101 and scraping marks 104 on an ID card 10. FIG. 10 is a flowchart showing a procedure for determining authenticity using a step detection image. 10A to 10C are diagrams illustrating the creation of a difference image 140. 3 shows an example of setting information 310 and an inspection area a. FIG. 10 is a diagram showing a histogram of the number of bright spots. 10 is a flowchart showing the procedure for determining authenticity by comparing a comparison image with an infrared image. 2A and 2B are diagrams showing binary images 200 and 300 of a spectral image and an infrared image. 10 shows an example of setting information 320 and an inspection area b. 10A and 10B are diagrams for explaining a method for determining whether an inspection area b is correct or not. 10A and 10B are diagrams for explaining a method for determining whether an inspection area b is correct or not.

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 reading device 2 and an authenticity determination device 3 so that they can communicate with each other via wired or wireless communication. In the authenticity determination system 1, a photographed image of an ID card 10 is transmitted from the reading device 2 to the authenticity determination device 3, and the authenticity determination device 3 determines the authenticity of the ID card 10 from the photographed image.

The reading device 2 has a photographing device 20 that photographs the ID card 10 and a card reader 30 that reads the IC chip on the ID card 10. In particular, in this embodiment, the photographing device 20 is provided with a visible light camera and visible light illuminator, and an infrared camera and infrared illuminator.

When photographing with a visible light camera, the visible light emitted from the visible light illuminator and reflected from the ID card 10 is received by the visible light camera. When photographing with an infrared camera, the infrared light emitted from the infrared illuminator and reflected from the ID card 10 is received by the infrared camera. Hereinafter, an image of the ID card 10 photographed with a visible light camera will be referred to as a visible light image, and an image of the ID card 10 photographed with an infrared camera will be referred to as an infrared image.

The above-mentioned visible light camera photographs the ID card 10 from directly above it, but in this embodiment, as shown in Figure 2, a pair of light sources 22 are provided diagonally above and on both sides of the ID card 10 as visible light illumination. Reference numeral 21 in the figure denotes a visible light camera that photographs the ID card 10 from directly above it.

Figure 3 shows 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, this is not limited to this, and various other 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 non-volatile memory and permanently stores programs such as the boot program and BIOS, as well as data. The RAM is 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 required for program execution, the OS, etc.

The communication unit 33 is a communication interface that mediates communication with the reader 2. The display unit 34 is an LCD display or the like, and displays various information related to authenticity determination of the ID card 10.

(2. ID Card 10)
In this embodiment, the ID card 10 is an identification card that is the subject of authentication determination. Identification cards are cards used for administrative procedures and identity verification by various government agencies, financial institutions, mobile phone carriers, etc., and include, for example, a driver's license, My Number card, residence card, special permanent resident certificate, etc. However, the ID card 10 is not limited to these.

Figures 4(a) and (b) are schematic diagrams showing examples of the faces of a driver's license and a residence card, respectively, as ID cards 10. ID cards 10 are made of a roughly rectangular card substrate with face information such as the card holder's name, date of birth, address, expiration date, and photograph printed on it. Other face information appropriate to the type of ID card 10 is also printed on it, such as the type of license in the case of a driver's license or the residence status in the case of a residence card, and the content and location of the face information on ID card 10 varies depending on the type of ID card 10.

In addition, in this embodiment, type identification information indicating the type of ID card 10 is stored in an IC chip (not shown) that the ID card 10 has, and this type identification information is read by the card reader 30.

(3. Functions of the 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 receives and acquires the captured image of the ID card 10 and the type identification information of the ID card 10 from the reading device 2 via the communication unit 33 via the control unit 31 of the authenticity determination device 3. The captured image of the ID card 10 includes the visible light image and infrared image described above.

The authenticity determination means 302 is a device in which the control unit 31 of the authenticity determination device 3 acquires images of an inspection area at a position that varies depending on the type of ID card 10 based on the captured image of the ID card 10 and the type identification information of the ID card 10, and determines the authenticity of multiple types of ID cards 10 using a common algorithm from the images of the inspection area. Details of authenticity determination will be described later.

(4. Overview of 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 S3 in Fig. 6 are processes executed by a control unit (not shown) of the reading device 2 by controlling each unit of the reading device 2, and S4 to S6 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 reader 2. The reader 2 then reads the IC chip on the ID card 10 in response to the user's operation to obtain type identification information for the ID card 10 (S1), and photographs the ID card 10 using the visible light camera 21 and infrared camera (S2).

Here, in S2, when the ID card 10 is photographed by the visible light camera 21, the reader 2 photographs the ID card 10 by turning on both light sources 22 as shown in Figure 7(a), and then photographs the ID card 10 by turning on only one light source 22 as shown in Figure 7(b), and then photographs the ID card 10 by turning on only the other light source 22 as shown in Figure 7(c).

As shown in Figure 7(a), a captured image (visible light image) taken with both light sources 22 turned on is used for comparison with the infrared image described below. Also, as shown in Figures 7(b) and 7(c), a pair of captured images (visible light images) taken with one light source 22 located on each side of the ID card 10 turned on at a time are used for detecting a step, described below. Hereinafter, the former captured image will sometimes be referred to as the "comparison image," and the latter pair of captured images will sometimes be referred to as the "step detection images."

The reading device 2 transmits the captured image obtained by photographing the ID card 10 in S2 and the type identification information of the ID card 10 obtained by reading the IC chip in S1 (hereinafter referred to as the "captured image, etc.") to the authenticity determination device 3 (S3). The authenticity determination device 3 receives the captured image, etc. (S4) and uses the captured image, etc. to determine the authenticity of the ID card 10 (S5).

It should be noted that the captured images of the ID card 10, both visible light images and infrared images, are images in which the color of each pixel is represented by the gradation values of the R (red), G (green), and B (blue) components. In infrared images, the R, G, and B gradation values of each pixel are approximately the same. However, infrared images of the ID card 10 captured with an infrared camera may be grayscale images in which the degree of brightness of each pixel is represented by gradation values. In such cases, grayscale conversion at S205 (see Figure 14) described below is not necessary.

The authenticity determination device 3 displays the authenticity determination result of the ID card 10 on the display unit 34 (S6) and ends the process. A person in charge can then take appropriate action after viewing the display unit 34. The authenticity determination device 3 may also display instructions corresponding to the determination result along with the authenticity determination result of the ID card 10 on the display unit 34, prompting the person concerned to take appropriate action.

(5. Authentication of ID card 10)
In S5, as shown in the flowchart of Fig. 8, a judgment is made based on the step detection image, which is a visible light image (S10), and a judgment is made based on a comparison between the comparison image, which is a visible light image, and the infrared image (S20). If both judgments determine that the ID card 10 is genuine (S30; YES), the ID card 10 is finally determined to be genuine (S40). On the other hand, if either judgment determines that the ID card 10 is not genuine (S30; NO), the ID card 10 is determined to be counterfeit (S50). Each judgment is explained below.

(5-1. Determination using step detection images)
In the above-mentioned S10, when the ID card 10 is falsified by pasting a piece of paper or the like on which false face information is printed, or by scratching off the face information of the ID card 10 and then writing in false face information, a step is generated on the ID card 10 due to the trace of pasting or scratching, and the step appears in the step detection image, and by utilizing this, the authenticity of the ID card 10 is determined.

For example, as shown in Figure 9(a), if a piece of paper 101 is attached to an ID card 10, when one of the light sources 22 is turned on and illumination light 221 is shone on the ID card 10 during photography, the end 102 of the piece of paper 101 closest to the light source 22 will appear bright due to the diffuse reflection of the illumination light 221 caused by the step. On the other hand, the end 103 farthest from the light source 22 will appear dark due to the shadow caused by the step. Therefore, tampering such as attaching a piece of paper 101 to the ID card 10 can be detected from such bright or dark areas.

On the other hand, as shown in Figure 9(b), if there is a scratch mark 104 on the ID card 10, when one of the light sources 22 is turned on and illumination light 221 is shone on the ID card 10 during a photograph of the ID card 10, the edge 105 of the scratch mark 104 closest to the light source 22 will appear dark due to the shadow created by the step. On the other hand, the edge 106 farthest from the light source 22 will appear bright due to the diffuse reflection of the illumination light 221 created by the step. Therefore, tampering such as scratching off the face information of the ID card 10 can be detected from such bright or dark areas.

Figure 10 is a flowchart showing the steps for authenticity determination in S10. In this embodiment, in S10, the area of the ID card 10 is first cut out from each of the pair of step detection images received in S4, and used as an image of the ID card 10 (S101).

The authenticity determination device 3 resizes and reduces the pair of ID card 10 images cut out from the pair of step detection images, and then performs grayscale conversion on both images (S102). This speeds up subsequent processing. The specific method for grayscale conversion is not particularly important.

Next, the authenticity determination device 3 calculates the difference in gradation values between the two images to create a difference image (S103). More specifically, it calculates the difference in gradation values between pixels at corresponding positions in the two images, and creates a difference image by using the absolute value as the gradation value of the pixel at that position.

Figure 11(a) shows an example of an ID card 10 that has been altered by attaching a piece of paper 101, and Figure 11(b) shows an example of a pair of images 130 of the ID card 10 obtained by processing up to S102. In S103, the difference in the gradation values of these images 130 is taken to obtain a difference image 140 as shown in Figure 11(c).

In the example of Figure 11(a), a piece of paper 101 has been pasted in the name, address, and photograph fields of the driver's license in Figure 3(a), and in the image 130 shown in Figure 11(b), light areas 131 or dark areas 132 have appeared on both sides of the piece of paper 101 as traces of the pasting. The part that appears as a light area 131 in one image 130 appears as a dark area 132 in the other image 130. As a result, as shown in Figure 11(c), in the difference image 140, the gradation values on both sides of the piece of paper 101 are higher.

Then, the authenticity determination device 3 compares the gradation value of each pixel in the difference image 140 with a predetermined threshold, and detects pixels with gradation values greater than the threshold as bright spots (S104).

The authenticity determination device 3 counts the number of bright spots, and if that number is less than or equal to a reference value (S105; YES), it determines that the ID card 10 is authentic (S106) and ends the process.

On the other hand, if the number of bright spots exceeds the reference value (S105; NO), the authenticity determination device 3 acquires setting information from the memory unit 32 (S107), and based on this setting information, cuts out a specified inspection area from the difference image 140 to acquire an image of the inspection area (S108), and creates a histogram showing the number of bright spots at each position in a specified direction within the inspection area (S109).

Figure 12(a) is a diagram showing the setting information 310 acquired in S107. In this setting information 310, position information 312 of the inspection area a in the image 130 of the ID card 10 is set for each type 311 of the ID card 10. The position of the inspection area a (position information 312) differs for each type 311 of the ID card 10, as shown in Figure 12(b), and multiple positions are set for each type of ID card 10.

In S108, this setting information 310 is referenced, and position information 312 of the inspection area a corresponding to the type 311 of the ID card 10 is obtained from the type identification information of the ID card 10 obtained in S4, and this position information 312 is used to cut out the inspection area a from the difference image 140. Note that in the setting information 310, the threshold 313 to be applied to each inspection area a in S111, described below, is also set corresponding to the position information 312 of each inspection area a.

Figure 13(a) shows an image of inspection area a of the name and date of birth of the ID card 10 in Figure 3(a) cut out from the difference image 140 in S108, and an example histogram created for inspection area a in S109, with the predetermined direction set to the long side direction of the ID card 10. The number of bright spots is higher in areas where bright spots are lined up in the short side direction of the ID card 10 (bright lines).

The authenticity determination device 3 extracts a continuous range C, which is a contiguous range of positions where bright spots exist, from the histogram of each inspection area a (S110). Figure 13(b) is an enlarged view of the continuous range C on the left side of Figure 13(a). Within this continuous range C, there is a portion between positions c1 and c2 where bright spots exist, where the number of bright spots is 0. However, even if positions c1 and c2 where bright spots exist are separated from each other, as long as the separation is less than a reference length, these positions c1 and c2 are considered to be continuous and are included in the continuous range C. The above reference length can be determined as appropriate.

The authenticity determination device 3 calculates the total number of bright spots within each continuous range C extracted from each inspection area a as a determination value. If the determination value for all continuous ranges C is equal to or less than the threshold value 313 (see Figure 12(a)) (S111; YES), the ID card 10 is determined to be authentic (S106) and the process ends.

This is because even if bright spots are present in the difference image 140, if they are not present in a relatively large group, they are likely to be noise unrelated to the authenticity of the ID card 10. For example, the continuous range C on the right side of the histogram in Figure 13(c) is caused by noise, and the total number of bright spots within continuous range C is small. Therefore, if all of continuous range C is considered to be caused by such noise, the ID card 10 is deemed to be authentic.

The threshold value 313 is calculated by multiplying the height of each inspection area a (number of pixels in the vertical direction) by a predetermined coefficient, and is set to a value that corresponds to the height of the inspection area a. The value of the coefficient can be set as appropriate, for example, 1.2. The judgment value may be based on the number of bright spots in the inspection area a, and the calculation method is not limited to the above. For example, it may simply be the total number of bright spots in the inspection area a. The threshold value 313 also differs depending on the calculation method for the judgment value.

If the judgment value exceeds the threshold value 313 in any of the continuous ranges C (S111; NO), the authenticity determination device 3 determines that the ID card 10 is not authentic (S112) and terminates processing.

In S10, the authenticity determination process for the ID card 10 can be performed as described above. Alterations by attaching pieces of paper 101 or the like are often made to specific face information such as name and address, and the location of this face information varies depending on the type of ID card 10. However, in this embodiment, by referencing the setting information 310 and cutting out a different inspection area a depending on the type of ID card 10 to perform the determination, a common algorithm corresponding to S109 to S111 in Figure 10 can be applied to face information that is expected to be altered for different types of ID cards 10.

In the above example, the ID card 10 was determined to be inauthentic based on bright spots resulting from the ID card 10's attachment marks. However, if there are scratch marks 104 on the ID card 10, bright spots will appear in the difference image 140 in the same way as above, and such an ID card 10 can be detected as inauthentic.

(5-2. Judgment by comparing the comparative image and the infrared image)
In S20, the genuine ID card 10 is manufactured by printing each area of the card face using a predetermined printing method, and the authenticity is determined by utilizing the fact that the appearance of the shading of these areas differs between the visible light image and the infrared image depending on the ink used, etc.

For example, areas printed with ink containing components that absorb infrared rays, such as carbon, appear as dark areas (high-density areas) in both visible light images and infrared images, while areas printed with ink that does not absorb infrared rays appear as dark areas in visible light images and light areas (low-density areas) in infrared images. Therefore, it is possible to effectively detect cases of counterfeiting or alteration using ink with different infrared absorption characteristics than the ink used on genuine ID cards 10.

Figure 14 is a flowchart showing the steps for authenticity determination in S20. In this embodiment, in S20, the comparison image (visible light image) and infrared image received in S4 are first resized and reduced to a predetermined size (S201). This speeds up subsequent processing. The above size is the same for the comparison image and the infrared image, and is, for example, reduced to about half the original size of the original comparison image and infrared image, but is not limited to this.

Next, the authenticity determination device 3 masks the facial photograph portion in the resized comparison image and infrared image (S202). This process is performed to prevent the gradation values of the pixels in the facial photograph from affecting the binarization process that will be performed later. The masking process is performed by replacing the gradation values of the pixels in the facial photograph with specific mask values.

Next, the authenticity determination device 3 creates a spectral image from the comparison image after masking (S203). In this process, an image is created in which the gradation values of the R, G, and B components of each pixel in the comparison image are used as the gradation values for each pixel. Hereinafter, an image based on the gradation values of the B component will be referred to as the B image, an image based on the gradation values of the G component will be referred to as the G image, and an image based on the gradation values of the R component will be referred to as the R image. The B image, G image, and R image are spectral images that show the shades of the R, G, and B components, respectively.

In addition, in S203, a spectral image is created in which the maximum gradation value of the R, G, and B components of each pixel in the comparison image is used as the gradation value for each pixel. This image shows the degree of brightness of each pixel in the comparison image as shades of gray, and is hereafter referred to as a V (brightness) image. For example, if the gradation values of the R, G, and B components of a pixel in the comparison image are (R, G, B) = (10, 20, 30), the gradation value of the corresponding pixel in the V image will be 30.

As a result, in subsequent processing, the shading of the comparison image (visible light image) will be determined by the shading of each color component of the comparison image, or by the shading indicating the degree of brightness of each pixel in the comparison image.

The authenticity determination device 3 binarizes each of the spectral images created in S203 (S204). There are no particular limitations on the binarization method, but in this embodiment, binarization is performed using Otsu's method. Otsu's method is a technique that automatically determines the threshold value for binarization from the gradation value histogram of the entire image, and is well known in the image processing field. However, binarization can also be performed using a predetermined threshold value.

Figure 15 (a) is an example of a binary image 200 of a spectral image (B image, G image, R image, V image). These binary images 200 represent high-density areas (dark areas) in the spectral image with black pixels and low-density areas (light areas) with white, with printed areas basically being black pixels (dark areas).

However, in the binary image 200 of the B, G, and R images, the parts printed in these colors (for example, the parts printed in red in the R image) do not appear as black pixels, but as white pixels (light areas). On the other hand, the parts printed in colors close to the complementary colors of these colors (for example, the parts printed in red in the B image) appear as black pixels.

The authenticity determination device 3 also performs grayscale conversion on the infrared image after masking, and then performs binarization (S205). Grayscale conversion is performed because the gradation values of the R, G, and B components of the pixels in the infrared image may differ from one another, but as mentioned above, this can be omitted if the infrared image is a grayscale image. Grayscale conversion can be performed using known methods.

Unlike the previous method, the infrared image is binarized using a predetermined threshold value. It is desirable to set an appropriate threshold value depending on the type of ID card 10. However, as before, binarization may also be performed using Otsu's method. Figure 15(b) is an example of a binary infrared image 300. In an infrared image, areas printed with ink containing components that absorb infrared rays become high-density areas (dark areas), and in the binary image 300, these areas appear as black pixels.

After creating binary images 200, 300 for the spectral image and infrared image, respectively, the authenticity determination device 3 acquires setting information from the storage unit 32 (S206), and based on this setting information, cuts out an inspection area from the binary images 200, 300 for the spectral image and infrared image, and acquires an image of the inspection area (S207).

Figure 16(a) is a diagram showing the setting information 320 acquired in S206. This setting information 320 sets position information 322 of the inspection area b within the ID card 10 according to the type 321 of the ID card 10, and the position (position information 322) of the inspection area b differs for each type of ID card 10, as shown in Figure 16(b), and multiple positions are set for each type of ID card 10. In S306, this setting information 320 is referenced, and position information 322 of the inspection area b according to the type 321 of the ID card 10 is acquired based on the type identification information of the ID card 10 acquired in S4, and this position information 322 is used to cut out the inspection area b from both the binary images 200 and 300.

In addition, in the setting information 320, the discrimination method 323 (mode A and mode B described below) to be applied to each inspection area b in S208 described below, the threshold value 324 used for discrimination, and the spectroscopic image information 325 used for discrimination are set in correspondence with the position information 322 of the inspection area b. The discrimination method 323 will be described later.

The authenticity determination device 3 determines whether inspection area b is correct (whether inspection area b is of a genuine ID card 10) based on the pixel values of the binary images 200 and 300 (S208).

In S208, based on the pixel values of the binary images 200 and 300, the number of pixels in the inspection area b whose shading in the spectral image and the infrared image meets a predetermined standard is calculated as a discrimination value, and the inspection area b is judged to be correct or incorrect based on the comparison result between the discrimination value and threshold 324. In particular, in this embodiment, the above-mentioned predetermined standard, etc. differs for each inspection area b. More specifically, it differs depending on whether the inspection area b is a part printed with ink containing a component that absorbs infrared rays or a part printed with ink that does not. Below, the differences in the methods (called modes) for determining the correctness of the inspection area b are explained.

<Mode A. When inspection area b is a portion printed with ink containing a component that absorbs infrared rays>
If the inspection area b is a portion of a genuine ID card 10 that is printed with ink containing a component that absorbs infrared rays, that printed portion will appear as a dark area in both the spectral image and the infrared image, as shown in Figure 17(a), and will appear as black pixels in these binary images 200 and 300.

On the other hand, Figure 17(b) shows that writing 12 has been made in the inspection area b of the ID card 10 using ink that does not absorb infrared light. In this case, the area where writing 12 has been made appears as a dark area in the spectral image and a light area in the infrared image, and appears as a black pixel in the binary image 200 of the spectral image, but as a white pixel in the binary image 300 of the infrared image.

Figure 17(c) shows pixels that are black in the binary spectroscopic image 200 and white in the binary infrared image 300 as white pixels, and all other pixels as black pixels. In order to detect falsification caused by writing 12 in ink with different infrared absorption characteristics as described above, the authenticity determination device 3 counts the number of pixels that are black in the binary spectroscopic image 200 and white in the binary infrared image 300 (white pixels in Figure 17(c)) for inspection area b cut out from the binary spectroscopic image 200 and the binary infrared image 300, and uses this count as the discrimination value.

Then, the discrimination value is compared with threshold 324, and if the discrimination value is equal to or less than threshold 324, inspection area b is determined to be positive, and if the discrimination value is greater than threshold 324, inspection area b is determined to be negative. In this case, the above-mentioned predetermined criterion is "a dark area in the spectral image and a light area in the infrared image (a black pixel in binary image 200 and a white pixel in binary image 300)."

<Mode B. When inspection area b is a portion printed with ink that does not absorb infrared rays>
If the inspection area b is a portion of a genuine ID card 10 that is printed with ink that does not absorb infrared rays, that printed portion will appear as a dark area in the spectral image and a light area in the infrared image, as shown in Figure 18 (a), and will appear as black pixels in the binary image 200 of the spectral image and as white pixels in the binary image 300 of the infrared image.

On the other hand, Figure 18(b) shows that the portion of the above-mentioned inspection area b of the ID card 10 that would normally be printed with ink that does not absorb infrared light has been printed with ink that contains a component that absorbs infrared light. In this case, the printed portion 14 appears as a dark area in both the spectral image and the infrared image, and appears as a black pixel in both the binary image 200 of the spectral image and the binary image 300 of the infrared image.

Figure 18(c) shows pixels that are black in both the binary spectroscopic image 200 and the binary infrared image 300 as white pixels, and all other pixels as black pixels. In order to detect counterfeiting or alteration caused by printing with inks that have different infrared absorption characteristics as described above, the authenticity determination device 3 counts the number of black pixels (white pixels in Figure 18(c)) in both binary images 200, 300 for inspection area b cut out from the binary spectroscopic image 200 and the binary infrared image 300, and uses this count as the discrimination value.

Then, the discrimination value is compared with threshold 324, and if the discrimination value is equal to or less than threshold 324, inspection area b is determined to be positive, and if the discrimination value is greater than threshold 324, inspection area b is determined to be negative. In this case, the aforementioned predetermined criterion is "a dark area in the spectral image and infrared image (a black pixel in the binary images 200, 300)."

In this way, in S208, by referencing the setting information 320, a discrimination method 323 defined for each inspection area b according to differences in the ink used, etc., is implemented to determine whether the inspection area b extracted in S206 is correct. Figure 16(b) also shows the discrimination method 323 (mode A, mode B) applied to some inspection areas b for the inspection area b. As shown in Figure 16(b), due to differences in the ink used when printing each area of the ID card 10, the position of the inspection area b to which mode A is applied differs between multiple types of ID cards 10, and similarly, the position of the inspection area b to which mode B is applied also differs between multiple types of ID cards 10.

Furthermore, the spectral image used for discrimination in Mode A and Mode B should basically be a V image because inspection area b is set mainly to the text portion. However, as an exception, for areas printed in color, it is desirable to use a color close to the complementary color of the printed color so that these areas appear as dark areas in the spectral image. In this way, information 325 (see Figure 16(a)) regarding which spectral image to use for discrimination for each inspection area b is also set in the setting information 320, and is referenced in S208 along with the threshold value 324.

The authenticity determination device 3 repeats the processes of S207 to S208 until the above determination has been made for all inspection areas b (S209; NO), and after determining whether the result is positive for all inspection areas b (S209; YES), it determines the authenticity of the ID card 10 based on the determination results for each inspection area b.

In this embodiment, if all inspection areas b are determined to be positive (S210; YES), the ID card 10 is determined to be genuine (S211); otherwise (S210; NO), the ID card 10 is determined to be inauthentic (S212), but this is not limited to this. For example, the ID card 10 can also be determined to be genuine if the number of inspection areas b determined to be positive is equal to or greater than a predetermined number.

In S20, the authenticity determination process for the ID card 10 can be performed as described above. As mentioned above, the position of each piece of face information, such as name and address, differs depending on the type of ID card 10, and the ink used when printing each piece of face information also differs depending on the type of ID card 10. In this embodiment, by referencing the setting information 320 and cutting out an inspection area b at a different position depending on the type of ID card 10 and performing the determination, a common algorithm corresponding to S208 in Figure 14 can be applied to each of the different types of ID cards 10.

As explained above, the configuration of the face of the ID card 10 (such as the position of face information) differs depending on the type of ID card 10. However, in this embodiment, authenticity is determined from images of inspection areas a and b, which are positioned differently depending on the type of ID card 10, and a common algorithm can be effectively applied based on the type identification information of the ID card 10. As a result, in this embodiment, authenticity determination of multiple types of ID cards 10 can be performed appropriately without having to switch algorithms for each type of ID card 10.

An example of a common algorithm is the flow of S109 to S111 in Figure 10. In this embodiment, if the ID card 10 is falsified by attaching a piece of paper or the like with false face information printed on it, or by scratching off the face information from the ID card 10 and then writing back false face information, a step will appear on the ID card 10 due to the attachment or scratching marks. This step will appear as a light or dark area when the light source 22 located on one side of the ID card 10 is turned on and an image of the ID card 10 is taken. This can be used to determine the authenticity of the ID card 10. In addition, a pair of step detection images are obtained by turning on the light sources 22 on both sides of the ID card 10, and by taking the difference between these images, only the area where the step occurs can be extracted as the difference image 140, allowing for optimal authentication.

Another example of a common algorithm is S208 in Figure 14. In this embodiment, a genuine ID card 10 is manufactured by printing each area of the card face using a predetermined printing method. Authenticity can be determined by utilizing the fact that the shading of these areas differs between the comparison image (visible light image) and the infrared image depending on the ink used, etc. For example, areas printed with ink containing an infrared-absorbing component, such as carbon, appear as dark areas (high-density areas) in both the comparison image and the infrared image, while areas printed with ink that does not absorb infrared light appear as dark areas in the comparison image and light areas (low-density areas) in the infrared image. This makes it possible to effectively detect cases of counterfeiting or alteration using ink with different infrared absorption characteristics than the ink used on the genuine ID card 10.

In addition, in this embodiment, multiple inspection areas a and b are set for each of multiple types of ID cards 10, thereby improving the accuracy of authenticity determination using each algorithm. Furthermore, by using the above two algorithms in combination, it is possible to respond to a wide range of methods for counterfeiting and altering ID cards 10.

However, the present invention is not limited to the above embodiments. For example, the present invention can also determine the authenticity of the ID card 10 based on the presence or absence of an IC chip. In this case, if the reading device 2 is unable to read the IC chip in S1, it transmits information to the authenticity determination device 3 in S3 that the IC chip could not be read, and upon receiving this information, the authenticity determination device 3 determines that the ID card 10 is counterfeit.

The authenticity determination device 3 may also display on the display unit 34 the inspection areas a and b that caused the ID card 10 to be determined to be inauthentic, i.e., the inspection area a having the continuous range C where the determination value exceeds the threshold value 313 in S111, or the inspection area b determined to be inauthentic in S208. This allows the person in charge to check the area and visually detect any erroneous determinations due to dust or the like, or to show the area to the holder of the ID card 10 and explain the determination results. The inspection areas a and b may be displayed together with the card image, or only the inspection areas a and b may be enlarged and displayed.

Furthermore, the common algorithm is not limited to the above, and may also be a method described in paragraphs [0043]-[0045] of JP 2019-209603 A to determine whether there are any inconsistencies in the text information obtained by performing OCR on an image of the inspection area of an ID card, such as a date of birth.

Furthermore, the purpose of authenticity determination is not particularly limited, and it can be applied not only when opening an account at a financial institution, but also when signing a contract for a mobile device, when verifying identity during procedures at various government agencies, and when creating documents using the ID card 10, and the cards to which the present invention is applicable are not limited to the ID card 10. The present invention can also be applied to identity verification when making various applications or issuing media using an ID photo machine.

In this embodiment, the type identification information of the ID card 10 is obtained from the IC chip of the ID card 10, but as mentioned above, the configuration of the face of the ID card 10 differs depending on the type of ID card 10, so it is also possible to obtain the type identification information of the ID card 10 from a photographed image of the ID card 10. Alternatively, the user may input the type identification information of the ID card 10 into the authenticity determination device 3, and the authenticity determination device 3 may obtain the type identification information input by the user. These methods make it possible to apply the present invention to cards without IC chips.

Preferred embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to these examples. It is clear that those skilled in the art will be able to conceive of various modifications and alterations 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: Reading device 3: Authenticity determination device 10: ID card 301: Acquisition means 302: Authenticity determination means

Claims (5)

An authenticity determination device that determines the authenticity of a card from an image of an inspection area of the card,
an acquisition means for acquiring a photographed image of the card and type identification information that can identify the type of the card;
an authenticity determination means for obtaining images of an inspection area at different positions depending on the type of card based on the photographed image and the type identification information, and determining the authenticity of the cards of the plurality of types from the images of the inspection area using a common algorithm;
Equipped with
The photographed images of the card are a pair of photographed images taken by lighting up light sources provided on both sides of the card, one on each side,
the image of the inspection area is an image in a difference image created by taking a difference in gradation values of the image of the card obtained from each of the pair of captured images,
The authenticity determination device is characterized in that the common algorithm determines a judgment value based on the number of bright points in the image of the inspection area and compares the judgment value with a threshold value . An authenticity determination device that determines the authenticity of a card from an image of an inspection area of the card,
an acquisition means for acquiring a photographed image of the card and type identification information that can identify the type of the card;
an authenticity determination means for obtaining images of an inspection area at different positions depending on the type of card based on the photographed image and the type identification information, and determining the authenticity of the cards of the plurality of types from the images of the inspection area using a common algorithm;
Equipped with
the captured image of the card is a visible light image and an infrared image of the card;
The common algorithm is:
An authenticity determination device characterized by calculating the number of pixels within the inspection area whose shading in the visible light image and the infrared image meets a predetermined standard as a discrimination value, and determining whether the inspection area is genuine or not based on the results of comparing the discrimination value with a threshold value . 3. The authenticity determining device according to claim 1 , wherein a plurality of the inspection areas are set for each of a plurality of types of the card. Computer,
An authenticity determination device that determines the authenticity of a card from an image of an inspection area of the card,
an acquisition means for acquiring a photographed image of the card and type identification information that can identify the type of the card;
an authenticity determination means for obtaining images of an inspection area at different positions depending on the type of card based on the photographed image and the type identification information, and determining the authenticity of the cards of the plurality of types from the images of the inspection area using a common algorithm;
Equipped with
The photographed images of the card are a pair of photographed images taken by lighting up light sources provided on both sides of the card, one on each side,
the image of the inspection area is an image in a difference image created by taking a difference in gradation values of the image of the card obtained from each of the pair of captured images,
A program for functioning as an authenticity determination device, characterized in that the common algorithm determines a judgment value based on the number of bright points in the image of the inspection area and compares the judgment value with a threshold value. Computer,
An authenticity determination device that determines the authenticity of a card from an image of an inspection area of the card,
an acquisition means for acquiring a photographed image of the card and type identification information that can identify the type of the card;
an authenticity determination means for obtaining images of an inspection area at different positions depending on the type of card based on the photographed image and the type identification information, and determining the authenticity of the cards of the plurality of types from the images of the inspection area using a common algorithm;
Equipped with
the captured image of the card is a visible light image and an infrared image of the card;
The common algorithm is:
A program for functioning as an authenticity determination device, characterized in that it calculates a discrimination value as the number of pixels within the inspection area whose shading in the visible light image and the infrared image meets a predetermined standard, and determines whether the inspection area is genuine or not based on the comparison result between the discrimination value and a threshold value .