JP2024034287A - Authenticity determination device and program - Google Patents

Abstract

An object of the present invention is to provide an authentication device and the like for determining the authenticity of a plurality of types of cards. SOLUTION: An authenticity determination device 3 determines the authenticity of an ID card from an image of an inspection area of the ID card. The authenticity determination device 3 includes an acquisition unit 301 that acquires a photographed image of the ID card and type identification information that can identify the type of the ID card, and an acquisition unit 301 that acquires the photographed image of the ID card and type identification information that can identify the type of the ID card, and the Authenticity determining means 302 is provided, which acquires images of inspection areas at different positions depending on the type, and determines the authenticity of a plurality of types of ID cards using a common algorithm from the images of the inspection areas. [Selection diagram] Figure 5

Description

The present invention relates to an authentication device, a program thereof, and the like.

When opening an account, it is common for a user to go to a financial institution and submit an ID card, and the financial institution uses the submitted ID card to verify the user's identity face-to-face. There are also attempts to automatically obtain various information from the user's ID card during various procedures to make the procedures more convenient.

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

Japanese Patent Application Publication No. 2011-34535

However, the technique disclosed in Patent Document 1 is for determining the authenticity of ID cards having specific characteristics, and is not for determining the authenticity of other types of ID cards. In the situations 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 has been desired.

The present invention has been made in view of the above problems, and an object of the present invention is to provide an authentication device and the like for determining the authenticity of a plurality of types of cards.

A first invention for solving the above-mentioned problems is an authenticity determination device that determines the authenticity of the card from an image of an inspection area of the card, the device being capable of identifying a photographed image of the card and the type of the card. an acquisition means for acquiring type identification information; and an acquisition means for acquiring images of inspection areas at different positions depending on the card type based on the photographed image and the type identification information, and determining the authenticity of the plurality of types of cards by the inspection. This is an authentication device characterized by comprising: an authentication device that performs authentication using a common algorithm from an image of a region.

Although the configuration of the card surface differs depending on the card type, in the present invention, a common algorithm can be effectively applied based on card type identification information, and authenticity can be determined from images of inspection areas at different positions depending on the card type. I do. As a result, in the present invention, the authenticity of multiple types of cards can be determined without switching algorithms for each type of card.

For example, the photographed image of the card is a pair of photographed images taken with light sources provided on both sides of the card turned on one side at a time, and the image of the inspection area is obtained from each of the pair of photographed images. It is an image in a difference image created by taking the difference in gradation values of the images of the card, and the common algorithm calculates a judgment value based on the number of bright spots in the image of the inspection area, and calculates the judgment value based on the number of bright spots in the image of the inspection area. is compared with a threshold value.
In the present invention, if a card is tampered with, such as by pasting a piece of paper with false face information printed on it, or by scraping off the face information of the card and then writing false face information on it, the card will not have any bumps due to pasting marks or scraping marks. The authenticity of the card can be determined by utilizing the fact that the step appears as a bright or dark area when the card is photographed with a light source located on one side of the card turned on. In addition, by obtaining an image of the card from each of a pair of images taken with the light sources on both sides of the card turned on one by one, and taking the difference between these images, only the part where the step has occurred can be imaged. It is possible to extract the image as a difference image and suitably determine the authenticity.

Further, for example, the photographed image of the card is a visible light image and an infrared image of the card, and the common algorithm is such that the pixels in the inspection area have a predetermined density in the visible light image and the infrared image. The number of pixels that meet the criteria is determined as a discriminant value, and it is determined whether or not the inspection area is positive based on the comparison result between the discriminant value and the threshold value.
In the present invention, a regular card is manufactured by printing each area of the card using a predetermined printing method, and depending on the ink used, the appearance of shading in these areas differs from the visible light image. Authenticity can also be determined using the difference between the infrared image and the infrared image. For example, areas printed with ink containing components that absorb infrared rays, such as carbon, appear as dark areas (areas of high concentration) in both visible light images and infrared images, but areas printed with ink that does not absorb infrared rays appear as dark areas (areas of high concentration) in both visible light images and infrared images. The area appears as a dark area in a visible light image, and appears as a light area (a low density area) in an infrared image. Therefore, it is possible to suitably detect cases where forgery, falsification, etc. have been carried out using ink that has different infrared absorption characteristics from the ink used in genuine cards.

Preferably, a plurality of inspection areas are set for each of a plurality of types of cards.
This improves the accuracy of authenticity determination.

A second invention is an authenticity determination device that uses a computer to determine the authenticity of the card from an image of an inspection area of the card, and acquires a photographed image of the card and type identification information that can identify the type of the card. acquisition means for acquiring images of an inspection area at different positions depending on the type of card based on the captured image and the type identification information, and determining the authenticity of a plurality of types of cards in common from the images of the inspection area. This is a program for functioning as an authenticity determination device, characterized in that it is provided with an authentication means for determining authenticity using an algorithm.
The second invention is a program for the authentication device of the first invention.

According to the present invention, it is possible to provide an authentication device and the like for determining the authenticity of a plurality of types of cards.

FIG. 1 is a diagram showing an authenticity determination system 1. FIG. FIG. 2 is a diagram showing a visible light camera 21 and a light source 22 in the reading device 2. FIG. FIG. 3 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. The figure which shows the function of the authenticity determination device 3. Flowchart showing an outline of the method for determining authenticity. FIG. 3 is a diagram illustrating photographing of the ID card 10. Flowchart showing the procedure for determining authenticity. FIG. 3 is a diagram showing a piece of paper 101 and scratch marks 104 on the ID card 10. 2 is a flowchart showing a procedure for determining authenticity using images for step detection. FIG. 3 is a diagram illustrating creation of a difference image 140. An example of setting information 310 and inspection area a. FIG. 3 is a diagram showing a histogram of the number of bright spots. A flowchart showing a procedure for determining authenticity by comparing a comparison image and an infrared image. A diagram showing binary images 200 and 300 of a spectral image and an infrared image. An example of setting information 320 and inspection area b. FIG. 7 is a diagram illustrating a method for determining whether inspection area b is correct or incorrect. FIG. 7 is a diagram illustrating a method for determining whether inspection area b is correct or incorrect.

Hereinafter, preferred embodiments of the present invention will be described in detail based on 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 as to be communicable by wire or wirelessly. In the authenticity determination system 1, a photographed image of the ID card 10, etc. 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, etc.

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

When photographing with a visible light camera, the visible light camera receives the visible light emitted from the visible light illumination and reflected from the ID card 10. Furthermore, when photographing with an infrared camera, the infrared camera receives the infrared rays emitted from the infrared illumination and reflected from the ID card 10. Hereinafter, an image of the ID card 10 taken with a visible light camera will be referred to as a visible light image, and an image of the ID card 10 taken with an infrared camera will be referred to as an infrared image.

The visible light camera described above photographs the ID card 10 from directly above the ID card 10, but in this embodiment, as visible light illumination, as shown in FIG. installed diagonally above both sides of the Reference numeral 21 in the figure is a visible light camera that photographs the ID card 10 from directly above it.

FIG. 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 section 31, a storage section 32, a communication section 33, a display section 34, etc. via a bus or the like. However, the present invention is not limited to this, and various configurations can be adopted as appropriate.

The control unit 31 is composed of a CPU, ROM, RAM, etc. The CPU calls a program related to the processing of the authenticity determination device 3 stored in the storage unit 32 or a storage medium such as a ROM into a work area on the RAM and executes it. ROM is a nonvolatile memory that permanently stores programs such as the boot program and BIOS, as well as data. The RAM is a volatile memory that temporarily holds programs and data loaded from the storage unit 32, ROM, etc., and also includes a work area used by the control unit 31 to perform various processes.

The storage unit 32 is a hard disk drive, a solid state drive, a flash memory, or the like, and stores programs to be executed by the authenticity determination device 3 during processing to be described later, data necessary for program execution, an OS, and the like.

The communication unit 33 is a communication interface that mediates communication with the reading device 2. The display unit 34 is a liquid crystal display or the like, and displays various information related to determining the authenticity of the ID card 10.

(2. ID card 10)
The ID card 10 is an identification card that is subject to authenticity determination in this embodiment. An identity verification card is a card used for administrative procedures and identity verification at various administrative agencies, financial institutions, mobile phone carriers, etc., such as a driver's license, My Number card, residence card, special permanent resident certificate, etc. However, the ID card 10 is not limited to these.

FIGS. 4A and 4B schematically show examples of the faces of a driver's license and a residence card as the ID card 10, respectively. The ID card 10 is a substantially rectangular card base material on which face information such as the card holder's name, date of birth, address, expiry date, and facial photograph are printed, but other information such as a driver's license may also be used. Information on the face of the ID card 10 is also printed, such as the type of driver's license in the case of a residence card and status of residence in the case of a residence card, and the contents and position of the information on the face of the ID card 10 vary depending on the type of the ID card 10.

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

(3. Function of authenticity determination device 3)
FIG. 5 is a block diagram showing the functions of the authenticity determination device 3. The authenticity determination device 3 includes an acquisition means 301, an authenticity determination means 302, and the like.

The acquisition means 301 is for the control section 31 of the authenticity determination device 3 to receive and acquire the photographed image of the ID card 10 and the type identification information of the ID card 10 from the reading device 2 via the communication section 33. The photographed images of the ID card 10 include the above-mentioned visible light image and infrared image.

In the authenticity determination means 302, the control unit 31 of the authenticity determination device 3 acquires images of inspection areas at different positions 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, The authenticity of multiple types of ID cards 10 is determined using a common algorithm from images of the inspection area. Details of the authenticity determination will be described later.

(4. Outline of authentication 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 the control unit (not shown) of the reading device 2 by controlling each part of the reading device 2, and S4 to S6 are processes executed by the control unit 31 of the authenticity determining device 3. This is a process executed by controlling each part of the system.

In this embodiment, the user first sets the ID card 10 in a predetermined position on the reading device 2, and the reading device 2 reads the IC chip of the ID card 10 according to the user's operation and reads the type identification information of the ID card 10. At the same time (S1), the ID card 10 is photographed using the visible light camera 21 and the infrared camera (S2).

Here, in S2, when the ID card 10 is photographed by the visible light camera 21, the reading device 2 lights up both light sources 22 as shown in FIG. 7(a) to photograph the ID card 10, and further, After photographing the ID card 10 with only one light source 22 turned on as shown in FIG. 7(b), the ID card 10 is photographed with only the other light source 22 turned on as shown in FIG. 7(c). Take pictures.

As shown in FIG. 7A, a photographed image (visible light image) taken with both light sources 22 turned on is used for comparison with an infrared image, which will be described later. In addition, as shown in FIGS. 7(b) and 7(c), a pair of photographed images (visible light images) obtained by lighting up the light sources 22 located on both sides of the ID card 10 on one side at a time are the images of the steps described below. Used for detection. Hereinafter, the former photographed image may be referred to as a "comparison image," and the latter pair of photographed images may be referred to as a "step detection image."

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

Note that both visible light images and infrared images of the ID card 10 are images in which the color of each pixel is expressed by the gradation values of each component of R (red), G (green), and B (blue). shall be. In an infrared image, the R, G, and B tone values of each pixel are almost the same. However, the infrared image taken of the ID card 10 by an infrared camera may be a grayscale image that expresses the brightness level of each pixel using gradation values, and in this case, in S205 (see FIG. 14) described later No grayscale conversion is required.

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. The person in charge who sees the display section 34 can take appropriate actions thereafter. The authenticity determination device 3 may display the authenticity determination result of the ID card 10 as well as instructions according to the determination result on the display unit 34 to urge the person concerned to take an appropriate response.

(5. Authenticity determination of ID card 10)
In the above S5, as shown in the flowchart of FIG. 8, a determination is made based on a step detection image that is a visible light image (S10), and a determination is made based on a comparison between a comparison image that is a visible light image and an infrared image (S20). If the ID card 10 is determined to be true in any of the determinations (S30; YES), the ID card 10 is finally determined to be true (S40). On the other hand, if it is determined that the ID card 10 is not authentic (S30; NO), the ID card 10 is determined to be a fake (S50). Each determination will be explained below.

(5-1. Judgment based on step detection image)
In S10, if the ID card 10 is tampered with, such as by pasting a piece of paper with fake card information printed on it, or by writing false card information after scratching off the ID card 10's information, the ID card 10 will be tampered with. The authenticity of the ID card 10 is determined by utilizing the fact that a level difference occurs due to scratches or scraping marks, and that the level difference appears in the level difference detection image.

For example, as shown in FIG. 9(a), when a piece of paper 101 is pasted on the ID card 10, if one of the light sources 22 is turned on to emit illumination light 221 when photographing the ID card 10, the light source 22 will be close to the light source 22. The end portion 102 of the other piece of paper 101 appears brighter due to the diffuse reflection of the illumination light 221 generated from the step. On the other hand, at the end 103 farther from the light source 22, the vicinity of the end 103 appears dark due to the shadow caused by the step. Therefore, alterations such as pasting the piece of paper 101 on the ID card 10 can be detected from such bright or dark areas.

On the other hand, as shown in FIG. 9(b), if there is a scratch mark 104 on the ID card 10, if one of the light sources 22 is turned on to irradiate illumination light 221 when photographing the ID card 10, the side closer to the light source 22 will be At the end 105 of the scraped trace 104, the vicinity of the end 105 appears dark due to the shadow caused by the step. On the other hand, the end 106 farther from the light source 22 appears brighter due to the diffuse reflection of the illumination light 221 generated from the step. Therefore, alterations such as scraping off the face information of the ID card 10 can be detected from such bright or dark areas.

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

The authenticity determination device 3 resizes and reduces the images of the pair of ID cards 10 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 of grayscale conversion is not particularly limited.

Next, the authenticity determination device 3 creates a difference image by calculating the difference between the gradation values of both images (S103). More specifically, the gradation value difference between pixels at corresponding positions in both images is calculated, and the difference image is created by using the absolute value as the gradation value of the pixel at the position.

FIG. 11(a) is an example of an ID card 10 that has been altered by pasting a piece of paper 101, and FIG. 11(b) is an image 130 of a pair of ID cards 10 obtained in the processing up to S102 for the ID card 10. This is an example. In S103, by calculating the difference between the gradation values of these images 130, a difference image 140 is obtained as shown in FIG. 11(c).

In the example of FIG. 11(a), a piece of paper 101 is pasted on the name, address, and face photo fields of the driver's license shown in FIG. 3(a), and in the image 130 shown in FIG. A bright area 131 or a dark area 132 appears as a pasting mark. A portion that appears as a bright portion 131 in one image 130 appears as a dark portion 132 in the other image 130. As a result, as shown in FIG. 11(c), in the difference image 140, the tone values on both sides of the piece of paper 101 become large.

After that, the authenticity determination device 3 compares the gradation value of each pixel of the difference image 140 with a predetermined threshold value, and detects a pixel with a gradation value larger than the threshold value as a bright spot (S104).

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

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 storage unit 32 (S107), and performs a predetermined inspection from the difference image 140 based on this setting information. An image of the inspection area is obtained by cutting out the area (S108), and a histogram showing the number of bright spots at each position in a predetermined direction within the inspection area is created (S109).

FIG. 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 FIG. 12(b), and a plurality of positions are set for each type of ID card 10.

In S108, this setting information 310 is referred to, and position information 312 of the inspection area a corresponding to the type 311 of the ID card 10 is acquired from the type identification information of the ID card 10 acquired in S4, and using this position information 312. An inspection area a is cut out from the difference image 140. In addition, in the setting information 310, a threshold value 313 to be applied in S111 described later for each inspection area a is also set corresponding to the position information 312 of each inspection area a.

FIG. 13(a) shows an image in which the inspection area a of the name and date of birth of the ID card 10 in FIG. This is an example of a histogram created for the inspection area a in the long side direction, and the number of bright spots is large at locations (bright lines) where bright spots are lined up in the short side direction of the ID card 10.

The authenticity determination device 3 extracts a continuous range C in which the positions of bright spots are continuous in the histogram of each inspection area a (S110). FIG. 13(b) is an enlarged view of the continuous range C on the left side of FIG. 13(a). In the continuous range C, there is a part where the number of bright spots is 0 between the positions c1 and c2 where the bright spots exist, but here, the positions c1 and c2 where the bright spots exist are far apart. However, if the separation is less than or equal to the reference length, those positions c1 and c2 are considered to be continuous and set as a continuous range C. The above standard length can be determined as appropriate.

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

This is because even if there are bright spots in the difference image 140, if they are not present in a certain amount of clusters, there is a high possibility that they are noise unrelated to the authenticity of the ID card 10. . For example, the continuous range C on the right side of the histogram in FIG. 13(c) is due to noise, and the total number of bright spots within the continuous range C is small. Therefore, if all continuous ranges C are considered to be caused by such noise, the ID card 10 is determined to be true.

Note that the above-mentioned threshold value 313 is obtained by multiplying the height (the number of pixels in the vertical direction) of each inspection area a by a predetermined coefficient, and has a value corresponding to the height of the inspection area a. The value of the coefficient can be determined as appropriate, for example, 1.2. Further, the determination value may be based on the number of bright spots within the inspection area a, and the calculation method thereof is not limited to the above. For example, it may simply be the total number of bright spots within the inspection area a. The threshold value 313 also differs depending on the method of calculating the determination value.

If the determination value exceeds the threshold 313 in any continuous range C (S111; NO), the authenticity determination device 3 determines that the ID card 10 is not authentic (S112) and ends the process.

In S10, the authenticity determination process of the ID card 10 can be performed as described above. Alteration by pasting a piece of paper 101 or the like is often performed on specific card information such as name and address, and the location of this information differs depending on the type of ID card 10. However, in this embodiment, by referring to the setting information 310 and cutting out different inspection areas a depending on the type of ID card 10 to make a determination, it is possible to check the face information of different types of ID cards 10 that is expected to be falsified. On the other hand, a common algorithm corresponding to S109 to S111 in FIG. 10 can be applied.

Note that in the above example, the ID card 10 was determined to be incorrect based on the bright spots originating from the pasting marks on the ID card 10, but even if the ID card 10 has scratch marks 104, the difference image 140 is determined in the same way as above. Since a bright spot appears in the ID card 10, such an ID card 10 can be detected as not being genuine.

(5-2. Judgment based on comparison of comparison image and infrared image)
In S20 described above, the regular ID card 10 is manufactured by printing each area of the card using a predetermined printing method, and depending on the ink used, the appearance of the shading in these areas is different from visible light. Authenticity is determined by utilizing the differences between the image and the infrared image.

For example, areas printed with ink containing components that absorb infrared rays, such as carbon, appear as dark areas (areas of high concentration) in both visible light images and infrared images, but areas printed with ink that does not absorb infrared rays appear as dark areas (areas of high concentration) in both visible light images and infrared images. The area appears as a dark area in a visible light image, and appears as a light area (a low density area) in an infrared image. Therefore, it is possible to suitably detect cases where forgery, falsification, etc. are carried out using ink that has different infrared absorption characteristics from the ink used in the genuine ID card 10.

FIG. 14 is a flowchart showing the procedure for determining authenticity in S20. In this embodiment, in S20, the comparison image (visible light image) and infrared image received in S4 are first resized to a predetermined size (S201). This speeds up subsequent processing. The above-mentioned size is the same for the comparison image and the infrared image, and for example, the original comparison image and infrared image are reduced to about 1/2, but the size is not limited to this.

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

Next, the authenticity determination device 3 creates a spectral image from the comparison image after the mask processing (S203). In this process, an image is created as a spectral image, with the tone values of each pixel being the tone values of the R, G, and B components of each pixel of the comparison image. Hereinafter, an image based on the gradation values of the B component will be referred to as a B image, an image based on the gradation values of the G component will be referred to as a G image, and an image based on the gradation values of the R component will be referred to as an R image. The B image, G image, and R image are spectral images showing the shading of the R, G, and B components, respectively.

Further, in S203, an image is created as a spectral image in which the largest gradation value of each pixel among the gradation values of R, G, and B components of each pixel of the comparison image is used. This is an image that shows the degree of brightness of each pixel of the comparison image as gradation, and is hereinafter referred to as a V (brightness) image. For example, in the comparison image, if the tone values of the R, G, and B components of a certain pixel are (R, G, B) = (10, 20, 30), the tone value of the corresponding pixel of the V image becomes 30.

As a result, in subsequent processing, the shading of each color component of the comparison image, or the shading indicating the degree of brightness of each pixel of the comparison image, is used as the shading of the comparison image (visible light image). become.

The authenticity determination device 3 binarizes each of the spectral images created in S203 (S204). Although the binarization method is not particularly limited, in this embodiment, binarization is performed using Otsu's method. Otsu's method is a method of automatically determining a threshold value for binarization from a tone value histogram of the entire image, and is known in the image processing field. However, it is also possible to perform binarization using a predetermined threshold value.

FIG. 15A is an example of a binary image 200 of spectral images (B image, G image, R image, and V image). These binary images 200 are spectral images in which high-density parts (dark parts) are represented by black pixels and low-density parts (light parts) are represented by white pixels, and the printed parts are basically black pixels. It becomes a pixel (dark area).

However, in the binary image 200 of the B image, G image, and R image, the parts printed in these colors (for example, the parts printed in red in the case of an R image) do not appear as black pixels, but as white pixels. Appears as (Atanbe). On the other hand, a portion printed in a color close to the complementary color of these colors (for example, a portion printed in red in the case of a B image) appears as a black pixel.

The authenticity determination device 3 also performs gray scale conversion on the infrared image after the mask processing, and then performs binarization processing (S205). Grayscale conversion is performed because the gradation values of the R, G, and B components of pixels in an infrared image may differ from each other, but as mentioned above, it can be omitted if the infrared image is a grayscale image. is also possible. Gray scale conversion can be performed using known techniques.

The infrared image is binarized using a predetermined threshold value, unlike the previous step. It is desirable that the threshold value be set to an appropriate value depending on the type of ID card 10. However, as described above, binarization may be performed using Otsu's method. FIG. 15(b) is an example of a binary image 300 of an infrared image. In an infrared image, a portion printed with ink containing a component that absorbs infrared rays becomes a high-density portion (dark portion), and in the binary image 300, this portion appears as a black pixel.

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

FIG. 16(a) is a diagram showing the setting information 320 acquired in S206. In this setting information 320, position information 322 of the inspection area b in the ID card 10 is set according to the type 321 of the ID card 10, and the position of the inspection area b (position information 322) is as shown in FIG. 16(b). As shown in FIG. 2, the settings are different for each type of ID card 10, and a plurality of settings are set for each type of ID card 10. In S306, the setting information 320 is referred to, and the position information 322 of the inspection area b corresponding 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. An inspection area b is cut out from both the binary images 200 and 300 using

Further, in the setting information 320, a determination method 323 (mode A, mode B described later) to be applied in S208 (described later) for each inspection area b, a threshold value 324 used for determination, and information 325 of a spectral image used for determination are specified for each inspection area b. The location information 322 is set in correspondence with the location information 322 of . The determination method 323 will be described later.

The authenticity determination device 3 determines whether the inspection area b is positive or not (whether the inspection area b belongs to the regular ID card 10 or not) 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 satisfy a predetermined standard is determined as a discriminant value. Based on the comparison result of the threshold value 324, it is determined whether the inspection area b is correct or not. Particularly in this embodiment, the above-mentioned predetermined criteria etc. differ for each inspection area b. More specifically, it differs depending on whether the inspection area b is printed with an ink containing a component that absorbs infrared rays or an ink that does not. Hereinafter, differences in the methods (referred to as modes) for determining whether the inspection area b is correct or incorrect will be explained.

<Mode A. When inspection area b is a part printed with ink containing a component that absorbs infrared rays>
When the inspection area b is a part of the regular ID card 10 that is printed with ink containing a component that absorbs infrared rays, the printed part contains both a spectral image and an infrared image, as shown in FIG. 17(a). This becomes a dark part and appears as a black pixel in these binary images 200 and 300.

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

FIG. 17C shows pixels that are black in the binary image 200 of the spectral image and white in the binary image 300 of the infrared image as white pixels, and other pixels as black pixels. In order to detect alterations caused by writing 12 with ink having different infrared absorption characteristics as described above, the authenticity determination device 3 examines the inspection area b cut out from the binary image 200 of the spectral image and the binary image 300 of the infrared image. , the number of pixels that are black in the former binary image 200 and white in the latter binary image 300 (white pixels in FIG. 17(c)) is counted, and the counted number is used as a discriminant value.

Then, the discrimination value is compared with a threshold value 324, and if the discrimination value is less than or equal to the threshold value 324, it is determined that the inspection area b is positive, and if the discrimination value exceeds the threshold value 324, it is determined that the inspection area b is not positive. In this case, the above-mentioned predetermined criterion is ``the spectral image should be a dark area, and the infrared image should be a light area (the binary image 200 should be a black pixel, and the binary image 300 should be a white pixel)'' It is.

<Mode B. When inspection area b is a part printed with ink that does not absorb infrared rays>
If inspection area b is a part of the regular ID card 10 that is printed with ink that does not absorb infrared rays, the printed part will be a dark part in the spectral image, as shown in FIG. It becomes a light part in the image, appears as a black pixel in the binary image 200 of the spectral image, and appears as a white pixel in the binary image 300 of the infrared image.

On the other hand, in FIG. 18(b), in the inspection area b of the ID card 10, the portion printed with ink that does not absorb infrared rays is printed with ink containing a component that absorbs infrared rays. In this case, the printed portion 14 becomes a dark part 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.

FIG. 18C shows pixels that are black in both the binary image 200 of the spectral image and the binary image 300 of the infrared image as white pixels, and the other pixels as black pixels. The authenticity determination device 3 uses an inspection area b cut out from the binary image 200 of the spectral image and the binary image 300 of the infrared image in order to detect forgery or alteration due to printing with inks having different infrared absorption characteristics as described above. , the number of black pixels (white pixels in FIG. 18C) in both binary images 200 and 300 is counted, and the counted number is used as a discriminant value.

Then, the discrimination value is compared with a threshold value 324, and if the discrimination value is less than or equal to the threshold value 324, it is determined that the inspection area b is positive, and if the discrimination value exceeds the threshold value 324, it is determined that the inspection area b is not positive. In this case, the above-mentioned predetermined criterion is "the pixels should be dark in the spectral image and the infrared image (the pixels should be black in the binary images 200 and 300)".

In this way, in S208, by referring to the setting information 320, the determination method 323 determined for each inspection area b is carried out according to the difference in ink used, etc., and the inspection area b cut out in S206 is positive. Determine whether or not. FIG. 16B also shows a determination method 323 (mode A, mode B) applied to the inspection area b for some inspection areas b. As shown in FIG. 16(b), the position of the inspection area b to which mode A is applied differs between multiple types of ID cards 10 due to differences in the ink used when printing each area of the ID card 10. Similarly, the position of the inspection area b to which mode B is applied also differs among the plurality of types of ID cards 10.

In addition, the spectral image used for discrimination in mode A and mode B can basically be a V image because the inspection area b is mainly set in the character part, but in exceptional cases, it may be printed in color. In order to make that part appear as a dark part in the spectral image, it is desirable to use a color close to the complementary color of the printing color. In this way, the information 325 (see FIG. 16(a)) indicating which spectral image is used for discrimination for each inspection area b is also set in the setting information 320, and is referenced in S208 together with the threshold value 324. Ru.

The authenticity determination device 3 repeats the processing of S207 to S208 until the above determination is made for all inspection areas b (S209; NO), and after determining whether all inspection areas b are positive or not. (S209; YES), the authenticity of the ID card 10 is determined based on the determination results of each inspection area b.

In this embodiment, when all the inspection areas b are positive (S210; YES), the ID card 10 is determined to be true (S211), and in other cases (S210; NO), the ID card 10 is determined to be not true ( S212), but is not limited to this. For example, if the number of inspection areas b that are determined to be positive is greater than or equal to a predetermined number, the ID card 10 may be determined to be true.

In S20, the authenticity determination process of the ID card 10 can be performed as described above. As described above, the position of each piece of card information such as name and address differs depending on the type of ID card 10, and the ink used when printing each piece of card information also differs depending on the type of ID card 10. In this embodiment, by referring to the setting information 320 and making a determination by cutting out inspection areas b at different positions depending on the type of ID card 10, each of the different types of ID cards 10 is processed in step S208 in FIG. A corresponding common algorithm can be applied.

As explained above, the structure of the face of the ID card 10 (position of face information, etc.) differs depending on the type of ID card 10, but in this embodiment, a common algorithm is enabled based on the type identification information of the ID card 10. Authenticity is determined from images of inspection areas a and b at different positions depending on the type of ID card 10. Thereby, in this embodiment, the authenticity of a plurality of types of ID cards 10 can be suitably determined without switching the algorithm for each type of ID card 10.

An example of a common algorithm is the flow from S109 to S111 in FIG. In this embodiment, if the ID card 10 is tampered with, such as by pasting a piece of paper with fake card information printed on it, or by writing fake card information after scratching off the ID card 10's card information, the ID card 10 is There is a difference in level due to pasting marks and scraping marks, and when the light source 22 located on one side of the ID card 10 is turned on and the ID card 10 is photographed, the difference in level appears as a bright part or a dark part. The authenticity of the card 10 can be determined. Furthermore, by obtaining an image of the ID card 10 from each of a pair of step detection images taken with the light sources 22 on both sides of the ID card 10 turned on one side at a time, and taking the difference between these images, the above-described method can be obtained. Only the portion where the difference in level has occurred can be extracted as the difference image 140, and the authenticity can be suitably determined.

Another example of the common algorithm is S208 in FIG. In this embodiment, the regular ID card 10 is manufactured by printing each area of the card using a predetermined printing method, and the appearance of the shading in these areas is compared depending on the ink used, etc. Authenticity can also be determined by utilizing the difference between an optical image (visible light image) and an infrared image. For example, areas printed with ink containing components that absorb infrared rays, such as carbon, appear as dark areas (areas of high concentration) in both the comparison image and the infrared image, but areas printed with ink that does not absorb infrared rays appear as dark areas (areas of high concentration) in both the comparison image and the infrared image. The area appears as a dark area in the comparison image and as a light area (area of low density) in the infrared image. Therefore, it is possible to suitably detect cases where forgery, falsification, etc. have been carried out using ink that has different infrared absorption characteristics from the ink used in the genuine ID card 10.

Further, in this embodiment, since a plurality of inspection areas a and b are set for each of a plurality of types of ID cards 10, it is possible to improve the accuracy of authenticity determination by each algorithm. Furthermore, by using the determination based on the above two algorithms in combination, it is possible to deal with a wide range of counterfeiting methods, alteration methods, etc. of the ID card 10.

However, the present invention is not limited to the above embodiments. For example, in the present invention, it is also possible to determine authenticity based on the presence or absence of an IC chip in the ID card 10. In this case, if the reading device 2 fails to read the IC chip in S1, it sends information to the effect that the IC chip could not be read to the authenticity determination device 3 in S3, and the authenticity determination device 3 transmits the information. If received, the ID card 10 is determined to be a fake.

In addition, the authenticity determination device 3 examines the inspection areas a and b that caused the ID card 10 to be determined to be invalid, that is, the inspection area a that has a continuous range C in which the determination value exceeds the threshold value 313 in S111, and The inspection area b determined as such may be displayed on the display unit 34. This allows the person in charge to check the area and visually detect erroneous judgments due to dust or the like, or to show the area to the holder of the ID card 10 and explain the judgment result. The inspection areas a and b may be displayed together with the card image, or only the inspection areas a and b may be displayed in an enlarged manner.

In addition, the common algorithm is not limited to the above, and for example, the presence or absence of inconsistencies in character information obtained by OCR of the image of the inspection area of the ID card, such as date of birth, is determined by the paragraph [2019-209603] The determination may be made by the method described in [0043] to [0045].

In addition, the purpose of determining authenticity is not particularly limited, and can be used not only when opening an account at a financial institution, when signing a contract for a mobile terminal, verifying the identity during procedures at various administrative agencies, and when creating a form using the ID card 10. The card to which the present invention is applicable is not limited to the ID card 10. The present invention is also applicable to identity verification when making various applications and issuing media using an ID photo machine.

Further, 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 described above, the configuration of the face of the ID card 10 differs depending on the type of the ID card 10, so the ID card It is also possible to obtain the ten type identification information from the photographed image of the ID card 10. Alternatively, the user may input the type identification information of the ID card 10 to the authenticity determination device 3, and the authenticity determination device 3 side may acquire the type identification information input by the user. These techniques make it possible to apply the present invention to cards without IC chips.

Although preferred embodiments of the present invention have been described above with reference to the accompanying drawings, the present invention is not limited to such examples. It is clear that those skilled in the art can come up with various changes or modifications within the scope of the technical idea disclosed in this application, and these naturally fall within the technical scope of the present invention. Understood.

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 the card from an image of an inspection area of the card,
acquisition means for acquiring a photographed image of the card and type identification information that can identify the type of the card;
Based on the captured image and the type identification information, images of inspection areas at different positions depending on the type of card are acquired, and a common algorithm is used to determine the authenticity of the plurality of types of cards from the images of the inspection area. means for determining authenticity,
An authenticity determination device comprising: The photographed images of the card are a pair of photographed images taken with light sources provided on both sides of the card turned on 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,
2. The authenticity determining device according to claim 1, wherein the common algorithm calculates a determination value based on the number of bright spots in the image of the inspection area, and compares the determination value with a threshold value. The captured images of the card are a visible light image and an infrared image of the card,
The common algorithm is
The number of pixels in the inspection area whose shading in the visible light image and the infrared image satisfy a predetermined standard is determined as a discrimination value, and from the comparison result between the discrimination value and a threshold value, it is determined that the inspection area is positive. 3. The authenticity determining device according to claim 1 or 2, wherein the device determines whether or not. 2. The authenticity determination device according to claim 1, wherein a plurality of said inspection areas are set for each of a plurality of types of said cards. computer,
An authenticity determination device that determines the authenticity of the card from an image of an inspection area of the card,
acquisition means for acquiring a photographed image of the card and type identification information that can identify the type of the card;
Based on the captured image and the type identification information, images of inspection areas at different positions depending on the type of card are acquired, and a common algorithm is used to determine the authenticity of the plurality of types of cards from the images of the inspection area. means for determining authenticity,
A program for functioning as an authenticity determination device, comprising:

Images