Authenticity determination apparatus and program

Abstract

To provide an authenticity determination apparatus, and the like, capable of properly determine the authenticity of an identity verification certificate.SOLUTION: An authenticity determination apparatus 3 is configured to determine the authenticity of an ID card with a hologram formed thereon. The authenticity determination apparatus 3 includes: acquisition means 301 which stores, in a storage unit, a template image showing a hologram part and a background part with binary values for an authentic hologram, and crops a range in which the hologram is formed on the ID card from an image obtained by imaging the ID card with a visible-light camera under infrared illumination, to obtain the hologram image; binarization means 304 which forms a hologram binary image showing the hologram part and the background part of the hologram image with binary values; and authentication determination means 305 which calculates a degree of matching between the hologram shape in the hologram binary image and the hologram shape in the template image, as a determination value indicating a degree of authenticity of the ID card.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present invention relates to an authenticity determining device and a program therefor. [Background technology]

[0002] The Act on Prevention of Transfer of Criminal Proceeds requires that identity verification be carried out when entering into a contract with a financial institution or mobile carrier. For example, when opening an account at a bank, the bank will request that the applicant submit an ID card (identification proof) such as a driver's license, and will then verify the applicant's identity by visually inspecting the submitted ID card.

[0003] In some cases, ID cards are counterfeited or altered in order to open an account under a false identity for criminal purposes such as specialized fraud, but face-to-face identity verification allows the ID card to be carefully observed and any abnormalities can be detected just by feeling the card.

[0004] Meanwhile, online identity verification using eKYC (electronic Know Your Customer) has been introduced, and there is an increasing demand for authenticity determination of ID cards from images of the ID cards. Patent Document 1 describes a technology that prevents a decrease in the accuracy of determination due to a hologram on an ID card when authenticity determination of an ID card is performed from an image taken with a camera such as a smartphone. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2023-38534 A Summary of the Invention [Problem to be solved by the invention]

[0006] As mentioned above, holograms on ID cards often reduce the accuracy of authenticity determination using ID card images. However, holograms often have special shapes to prevent counterfeiting, and using the hologram itself is also considered to be an effective means of authenticating identification documents.

[0007] The present invention has been made in consideration of the above problems, and has an object to provide an authenticity determining device etc. that can suitably determine the authenticity of an identification card. [Means for solving the problem]

[0008] The first invention for solving the above-mentioned problems is an authenticity determination device for an identification card on which a hologram is formed, comprising: an acquisition means for extracting the area in which the hologram of the identification card is formed from an image of the identification card photographed with a visible light camera under infrared illumination and acquiring a hologram image; a binarization means for creating a hologram binary image which shows the hologram portion and background portion of the hologram image in binary values; and an authenticity determination means for using a template image which shows the hologram portion and background portion of a positive hologram in binary values ​​and calculating the degree of match of the hologram shape in the hologram binary image to the hologram shape in the template image as a determination value which indicates the degree of authenticity of the identification card.

[0009] In the present invention, the hologram formed on the identification card is compared with a genuine hologram, and the degree of match of their shapes is calculated as a judgment value for authenticity judgment. The shape of the hologram can be expressed by its binary image. This makes it possible to use the special shape of the hologram to detect an identification card having a hologram with a different shape as a fake identification card. Furthermore, the hologram of the identification card appears clearly in an image captured by a visible light camera under infrared illumination, and authenticity judgment can be performed using the hologram image obtained from the captured image.

[0010] It is desirable that the degree of coincidence is calculated as the ratio of the total number of pixels in the hologram portion in the hologram binary image, which correspond to the pixels at the coordinates corresponding to those pixels in the template image and which are also part of the hologram portion, to the total number of pixels in the hologram portion in the hologram binary image, when the hologram binary image and the template image are superimposed. Due to factors such as uneven lighting when photographing the identification card, there are cases where only a portion of the hologram can be extracted from the photographed image of the identification card. However, in the present invention, by calculating the degree of match as described above, it is possible to evaluate the degree of match with a positive hologram by limiting it to the hologram portion that could be extracted (without taking into account the portion that could not be extracted), and therefore it is possible to appropriately determine authenticity even in cases such as those described above.

[0011] It is desirable that the authenticity determination means calculates the degree of match while changing the position of the origin of the hologram binary image within the template image at a first scanning interval, then sets a search area centered on the position of the origin when the degree of match is greatest, and again calculates the degree of match while changing the position of the origin within the search area at a second scanning interval smaller than the first scanning interval, and sets the maximum degree of match as the determination value. The degree of match is calculated by template matching while scanning the binary hologram image as described above. In this case, a scan is first performed at coarse scanning intervals to locate the position where the degree of match is greatest, and then a precision scan is performed at fine scanning intervals in a search area centered on that position. This procedure makes it possible to shorten the processing time while improving accuracy.

[0012] It is desirable that the binarization means performs a process of binarizing the luminance of the pixel of interest using the average luminance of pixels in a block centered on the pixel of interest as a threshold value, with each pixel in the hologram image as the pixel of interest, to create a first basic binary image, and also performs a process of binarizing each pixel in the hologram image with a constant threshold value to create a second basic binary image, and if either of the pixels at corresponding positions in the first and second basic binary images is a hologram part, the means performs a process of treating the pixel at that position in the hologram binary image as the hologram part, thereby creating the hologram binary image. When binarizing a hologram image, the adaptive binarization process can extract fine patterns of the hologram appropriately, but a hologram may contain both fine and coarse patterns, and the same process may result in incomplete extraction of the coarse patterns. In the present invention, as a supplementary process for such cases, a binary image (second basic binary image) is obtained by binarizing the entire hologram image with a certain threshold value, and an OR process is performed between this image and the binary image (first basic binary image) obtained by the adaptive binarization process, thereby compensating for the incomplete extraction in the adaptive binarization process.

[0013] The authenticity determination device preferably includes a replacement means for replacing the luminance of pixels in the hologram image that have a luminance less than a threshold value with an average luminance in the hologram image before binarizing the hologram image. It is also preferable that the authenticity determination device includes a preliminary determination means for determining whether or not the hologram image contains a hologram before binarizing the hologram image. The former replacement means prevents low-brightness parts such as characters in the hologram image from affecting the accuracy of the judgment, and the latter preliminary judgment means quickly identifies obviously fake identification cards where no hologram is formed in the first place, thereby speeding up processing and reducing the load.

[0014] The second invention is a program for causing a computer to function as an authenticity determination device for an identification card on which a hologram is formed, the authenticity determination device having: an acquisition means for extracting the area in which the hologram of the identification card is formed from an image of the identification card photographed with a visible light camera under infrared illumination and acquiring a hologram image; a binarization means for creating a hologram binary image which shows the hologram portion and background portion of the hologram image in binary values; and an authenticity determination means for using a template image which shows the hologram portion and background portion in binary values ​​for a positive hologram, and calculating the degree of match of the hologram shape in the hologram binary image to the hologram shape in the template image as a determination value which indicates the degree of authenticity of the identification card. Effect of the Invention

[0015] According to the present invention, it is possible to provide an authenticity determining device etc. that can suitably determine the authenticity of an identification card. [Brief description of the drawings]

[0016] [Figure 1] FIG. 1 shows an authenticity determination system 1. [Diagram 2] FIG. [Diagram 3] FIG. 2 is a diagram showing the hardware configuration of an authenticity determination device 3. [Figure 4] FIG. 2 is a block diagram showing the functions of the authenticity determination device 3. [Diagram 5] A diagram showing an ID card 10. [Figure 6] 3 is a flowchart showing an outline of the processing of the authenticity determination system 1. [Figure 7] FIG. 2 is a diagram showing a schematic view of a part of a photographed image of an ID card 10. [Figure 8] 11 is a flowchart showing the procedure of an authenticity determination process. [Figure 9] FIG. 2 is a diagram showing an example of a hologram image 100 and a template image 200. [Figure 10] FIG. 11 is a diagram showing an example in which luminance substitution is performed. [Figure 11]5A to 5C are diagrams for explaining adaptive binarization processing. [Figure 12] 2A to 2C are diagrams for explaining the creation of a hologram binary image 130. [Figure 13] FIG. 2 is a diagram for explaining the extension of a template image 200. [Figure 14] FIG. 13 is a diagram showing an example in which only a part of the hologram 20 is extracted. [Figure 15] 3A to 3C are diagrams for explaining scanning of a hologram binary image 130. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings.

[0018] (1. Authenticity Determination System 1) Fig. 1 is a diagram showing an authenticity determination system 1 having an authenticity determination device 3 according to an embodiment of the present invention. As shown in Fig. 1, the authenticity determination system 1 is configured by connecting a scanner 2 and an authenticity determination device 3 so that they can communicate with each other by wire or wirelessly.

[0019] In authenticity determination system 1, a captured image of ID card 10 having a hologram is sent from scanner 2 to authenticity determination device 3, which then determines the authenticity from the captured image based on the hologram shape of ID card 10. There are no particular limitations on the scenes or purposes for which authenticity determination can be applied, and it can be applied to opening an account at a financial institution, signing a contract with a mobile carrier, and identity verification during procedures at various government agencies.

[0020] The scanner 2 photographs the ID card 10. As shown in Fig. 2, a camera 21 and a light 22 are provided inside the scanner 2. The scanner 2 photographs the ID card 10 set in a predetermined position with the camera 21 provided directly above it.

[0021] Camera 21 is an area camera composed of an optical lens, imaging elements such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal-Oxide Semiconductor), an A / D (Analog / Digital) conversion unit, etc., and is a visible light camera in which the sensitivity of each imaging element is set to the visible light range.

[0022] The lighting 22 irradiates illumination light onto the ID card 10 when photographing the ID card 10. In this embodiment, an infrared lighting device that irradiates infrared light is used as the lighting 22, and is provided diagonally above the ID card 10. However, the location of the lighting device 22 is not particularly limited.

[0023] 3 is a diagram showing a 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 storage unit 32, a communication unit 33, a display unit 34, etc. via a bus or the like. However, the authenticity determination device 3 is not limited to this, and various configurations can be used as appropriate.

[0024] The control unit 31 is composed of a CPU, a ROM, a RAM, etc. The CPU loads programs related to the processing of the authenticity determination device 3 stored in a storage medium such as the memory unit 32 or ROM into a work area on the RAM and executes them. The ROM is a non-volatile memory, and permanently stores programs such as the boot program and BIOS, data, etc. The RAM is a volatile memory, and temporarily stores programs and data loaded from the memory unit 32, ROM, etc., and also has a work area used by the control unit 31 to perform various processes.

[0025] The storage unit 32 is a hard disk drive, a solid state drive, a flash memory, or the like, and stores a program executed by the authenticity determination device 3 in the process described below, data necessary for executing the program, an OS, and the like. In particular, in this embodiment, a template image 200 is stored in the storage unit 32. The template image 200 is an image in which a hologram portion and a background portion of a positive hologram are represented in binary form, and details will be described later.

[0026] The communication unit 33 is a communication interface that mediates communication with the scanner 2. The display unit 34 is a liquid crystal display or the like, and displays various information related to the authenticity determination process.

[0027] 4 is a block diagram showing the functions of the authenticity determination device 3. The authenticity determination device 3 includes an acquisition unit 301, a preliminary determination unit 302, a replacement unit 303, a binarization unit 304, an authenticity determination unit 305, and the like.

[0028] The acquisition means 301 is a means for allowing the control unit 31 of the authenticity determination device 3 to receive a photographed image of the ID card 10 from the scanner 2 via the communication unit 33, and to extract from the photographed image an area in which a hologram of the ID card 10 is formed, thereby acquiring a hologram image. The hologram image will be described later.

[0029] The preliminary determination means 302 allows the control unit 31 of the authenticity determination device 3 to preliminarily determine whether or not a hologram is included in a hologram image.

[0030] The replacement means 303 is a means for causing the control unit 31 of the authenticity determination device 3 to replace the luminance of a pixel in the hologram image whose luminance is less than a threshold value with the average luminance of pixels in the hologram image.

[0031] The binarization means 304 is a means for generating a hologram binary image in which the control unit 31 of the authenticity determination device 3 indicates the hologram portion and background portion of the hologram image in binary form. The hologram binary image will be described later.

[0032] The authenticity determination means 305 is a means in which the control unit 31 of the authenticity determination device 3 uses the above-mentioned template image 200 to calculate the degree of match between the hologram shape in the hologram binary image and the hologram shape in the template image 200 as a determination value indicating the degree of authenticity of the ID card 10.

[0033] (2. ID Card 10) In this embodiment, the ID card 10 is an identity card that is the subject of authentication. An identity card is a medium used for identity verification by financial institutions, mobile phone carriers, various administrative agencies, etc., such as a residence card or a special permanent resident certificate.

[0034] 5 is a diagram showing an overview of an ID card 10 (residence card), and is a schematic diagram showing some of the face information of the ID card 10. Various face information is printed on the ID card 10, and for example, for a residence card, examples of face information include the country of issue of the card, the residence number, the birth date of the card holder, and a facial image.

[0035] In this embodiment, a hologram 20 is formed on the ID card 10 as a countermeasure against counterfeiting. The hologram 20 has a special shape, and in this embodiment, this shape is used to determine the authenticity of the ID card 10.

[0036] (3. Overview of the process of the authenticity determination system 1) Fig. 6 is a flowchart showing an outline of the processing executed by the authenticity determination system 1. S1 to S2 in Fig. 6 are processing executed by a control unit (not shown) of the scanner 2 by controlling each unit of the scanner 2, and S3 to S5 are processing executed by a control unit 31 of the authenticity determination device 3 by controlling each unit of the authenticity determination device 3.

[0037] In this embodiment, the user first places the ID card 10 in a predetermined position on the scanner 2, and the scanner 2 photographs the ID card 10 with the camera 21 in response to the user's operation (S1). In this embodiment, a photograph of the ID card 10 is obtained by photographing with a visible light camera under infrared illumination. In this photographed image, the pixel colors are represented by pixel values ​​of three channels: R (red), G (green), and B (blue).

[0038] 7(a)-(c) are schematic grayscale images of a portion of the ID card 10, including a hologram, taken by a visible light camera under infrared illumination, ultraviolet illumination, and visible light illumination, respectively. As shown in FIG. 7(a), when the ID card 10 was taken by a visible light camera under infrared illumination, the pattern of the hologram 20 appeared relatively clearly. This is believed to be because the infrared light was strongly reflected by the diffraction reflection of the hologram 20, and the visible light camera was able to capture the light whose wavelength changed from the infrared light during the diffraction reflection, etc. On the other hand, as shown in FIG. 7(b), no image of the hologram 20 was obtained when the ID card 10 was taken under ultraviolet illumination. Also, as shown in FIG. 7(c), when the ID card 10 was taken under visible light illumination, there were cases where it was difficult to distinguish the background pattern or design of the ID card 10 from the hologram 20.

[0039] The scanner 2 transmits the captured image obtained by photographing the ID card 10 in S1 to the authenticity determination device 3 (S2 in FIG. 6). When the authenticity determination device 3 receives the captured image of the ID card 10 (S3), it performs an authenticity determination process for the ID card 10 using the captured image (S4).

[0040] In this embodiment, as described above, the authenticity determination process in S4 calculates the degree of match between the hologram shape in the hologram binary image and the hologram shape in the template image 200 as a determination value. Details of S4 will be described later. The authenticity determination device 3 displays the determination value on the display unit 34 (S5) and ends the process. The person in charge can take appropriate action depending on the determination value displayed in S5.

[0041] (4. Authenticity determination based on hologram shape) Fig. 8 is a flow chart showing the procedure of the authenticity determination process in S4 (see Fig. 6) described above. In this embodiment, in S4, first, the range in which the hologram 20 of the ID card 10 is formed is cut out from the photographed image (RGB image) of the ID card 10 to obtain a hologram image (S401). The above range is determined in advance so as to include the position of the hologram 20. Symbol a in Fig. 5 shows an example of this range.

[0042] Next, the authenticity determination device 3 converts the hologram image to grayscale (S402). FIG. 9(a) is a schematic example of a grayscale converted hologram image 100. This hologram image 100 is a grayscale image in which pixel brightness is expressed by gradation values ​​of 0 to 255, with gradation value 0 being black and gradation value 255 being white. These gradation values ​​are referred to as luminance. Note that the method of grayscale conversion is well known, and a description thereof will be omitted here. Furthermore, the specifications of the grayscale image are not limited to those described above.

[0043] The authenticity determination device 3 then preliminarily determines whether or not the hologram 20 is included in the hologram image 100 (S403).

[0044] In S403, first, in the hologram image 100, the number of pixels whose luminance is greater than a threshold value th_early_judge is obtained as the number of high-luminance pixels, and a ratio is calculated to the number of high-luminance pixels in the template image 200. The threshold value th_early_judge is determined in advance.

[0045] FIG. 9(b) is a schematic example of a template image 200. The template image 200 is a binary image of the positive hologram 20, in which the hologram portion is white and the background portion is black, and the number of high-luminance pixels in the template image 200 is the number of white pixels in the template image 200. The positive hologram 20 is the hologram 20 formed on the real ID card 10, and the template image 200 can be created from the design data of the hologram 20, etc. The vertical and horizontal sizes of the template image 200 are the same as those of the hologram image 100. The method of expressing the hologram portion and the background portion in the binary image is not limited to the above, and it is sufficient if the two portions can be distinguished. This also applies to the hologram binary image described later.

[0046] The authenticity determination device 3 compares the above ratio with a predetermined reference value th_early_judge_rate, and if the ratio is less than the reference value th_early_judge_rate, it determines that the hologram image 100 does not contain a hologram 20 (S404; NO), sets the judgment value to the value "0" indicating that the ID card 10 is fake, and terminates the processing (S405).

[0047] On the other hand, if the rate is equal to or greater than the reference value th_early_judge_rate, it is determined that hologram 20 is included in hologram image 100 (S404; YES), and authenticity determination device 3 first performs luminance correction on hologram image 100 in order to determine the authenticity (S406).

[0048] The luminance correction is a process for correcting luminance variations, etc. Although the method is not particularly limited, in this embodiment, the average luminance and the standard deviation of the luminance of the pixels in the hologram image 100 are calculated, and the luminance L(x, y) of each pixel in the hologram image 100 is standardized by the following formula (1) using the average luminance mean and the standard deviation stddev. L'(x,y)=((L(x,y)-mean) / stddev)*set_stddev+set_mean…(1) Here, (x, y) are pixel coordinates, L'(x, y) is the luminance after standardization, set_stddev is the standard deviation for standardization, and set_mean is the average luminance for standardization, each of which is a predetermined value.

[0049] Next, the authenticity determination device 3 performs a luminance replacement process (S407) in order to accurately extract the hologram 20. Here, the luminance of pixels whose luminance is less than a threshold value th_get_dark_pixel is replaced with the average luminance mean calculated in S406. The threshold value th_get_dark_pixel is determined in advance.

[0050] 10 is a schematic example of a case where brightness replacement processing is performed on a portion of hologram image 100. The above replacement processing makes it possible to eliminate the effects of characters and the like that appear as low-brightness pixels in hologram image 100 and accurately extract only hologram 20.

[0051] Thereafter, the authenticity determination device 3 binarizes the hologram image 100 to create a hologram binary image (S408). The hologram binary image is an image in which the hologram portion is represented by white pixels and the background portion is represented by black pixels, similar to the template image 200.

[0052] In this embodiment, adaptive binarization processing is performed in S408. Adaptive binarization processing is processing in which binarization is performed using a different threshold value for each pixel, rather than using a fixed threshold value for the entire image.

[0053] 11(a), an average luminance p_mean is calculated for pixels in a block (region) b centered on a pixel of interest p, and the luminance of the pixel of interest p is binarized using the average luminance p_mean as a threshold value, and this process is performed for each pixel in the hologram image 100 as the pixel of interest p. In this embodiment, the block b is square, and the size of one side is a predetermined value (number of pixels). However, the shape and size of the block b are not particularly limited.

[0054] Furthermore, in this embodiment, as shown in FIG. 11(b), the peripheral portion A1 of the hologram 20 has a finer pattern than the central portion A2, and this hologram portion may appear relatively faint (dark) in the hologram image 100. Therefore, after adaptive binarization processing of the hologram image 100 is performed using a block b of a size that can appropriately extract the peripheral portion A1 of the hologram 20, supplementary processing is performed to extract the central portion A2 of the hologram 20.

[0055] More specifically, first, the size of block b is determined so that peripheral portion A1 of hologram 20 can be appropriately extracted, and then a basic binary image (first basic binary image) is created by binarizing the entire hologram image 100 by the above-mentioned process. Figure 12(a) is a schematic example of this basic binary image 110, in which the hologram 20 is well extracted from peripheral portion A1 of hologram 20 (see Figure 11(b)), but extraction is incomplete from central portion A2 (see Figure 11(b)) where the pattern is coarse.

[0056] Then, as a supplementary process, a predetermined threshold value th_bi_supple is used so that the central portion A2 of the hologram 20 can be appropriately extracted, and a basic binary image (second basic binary image) is created by binarizing the entire hologram image 100 using a certain threshold value th_bi_supple. FIG. 12(b) is an example of this basic binary image 120.

[0057] Then, an OR process is performed on these two basic binary images 110, 120 to create a hologram binary image. In this OR process, if any of the pixels at corresponding positions in the basic binary images 110, 120 is white, i.e., a hologram portion, the pixel at that position in the hologram binary image is made white. Figure 12(c) is an example of a hologram binary image 130, and it can be seen that the center part A2 of the hologram 20 (see Figure 11(b)), which was incompletely extracted by the adaptive binarization process, has been filled in by carrying out the above filling process.

[0058] The authenticity determination device 3 smoothes the hologram binary image 130 to remove noise (S409). The smoothing method is not particularly limited, and for example, a known median filter process or the like can be performed.

[0059] The authenticity determination device 3 then calculates the degree of coincidence between the hologram shape of the hologram binary image 130 and the hologram shape of the template image 200 as a determination value indicating the degree of authenticity of the ID card 10 (S410).

[0060] 13, a background region c of black pixels is added to the periphery of the template image 200, thereby expanding the template image 200. The added background region c is a rectangular frame-shaped region of a certain width h, which is determined in advance.

[0061] In this embodiment, template matching is then performed between the hologram binary image 130 and the template image 200, and the position at which the degree of match is the highest is calculated. When the hologram binary image 130 and the template image 200 are superimposed, a pixel that is a white pixel (a pixel in the hologram portion) in the hologram binary image 130 and whose corresponding pixel at the coordinates corresponding to that pixel in the template image 200 is also white is called a matched pixel, and the degree of match is calculated by the ratio of the total number of matched pixels to the total number of white pixels in the hologram binary image 130 using the following formula (2). Degree of match = (total number of matched pixels) / (total number of white pixels in the hologram binary image 130) (2)

[0062] In formula (2), the evaluation of the total number of matched pixels is a relative evaluation to the total number of white pixels in hologram binary image 130, but this is because, due to factors such as uneven lighting when photographing ID card 10, there are cases in which only a portion of hologram 20 can be extracted from the photographed image of ID card 10, as shown diagrammatically in hologram binary image 130 in Fig. 14. In this embodiment, by calculating the degree of match as in formula (2), it is possible to evaluate the degree of match with respect to positive hologram 20 by limiting it to the hologram portion that could be extracted (without considering the portion that could not be extracted), and therefore it is possible to suitably determine authenticity even in the above-mentioned cases.

[0063] Template matching is a process for calculating the degree of match while changing the position of the origin of the hologram binary image 130 within the template image 200. The origin of the hologram binary image 130 is the pixel in the upper left corner of the hologram binary image 130, but is not limited to this.

[0064] As shown in Figure 15(a), template matching is performed by first aligning the position of the origin of the hologram binary image 130 with the origin (0,0) of the template image 200, and then changing the position of the origin of the hologram binary image 130 in both the x direction and y direction at a first scanning interval n1.

[0065] The x and y directions are the horizontal and vertical directions of the template image 200, respectively, and the origin of the template image 200 is the pixel in the upper left corner of the template image 200, as described above. The above-mentioned scanning interval n1 is an integer (number of pixels) equal to or greater than 2, and the degree of match calculated by formula (2) is referred to as a wide-area degree of match. The scanning interval n1 is common to the x and y directions, and the scanning area d1 shown by hatching is a square area with vertices on the diagonal at coordinates (0,0) and (2h,2h), but is not limited to this.

[0066] After that, the authenticity determination device 3 calculates the position of the origin (x max ,y max ), a search area d2 is set with the center at n1, and the position of the origin of the hologram binary image 130 is changed in the x-direction and y-direction at the second scanning interval n2 within the search area d2 in the same manner as above, while the degree of match is calculated again using the above formula (2). The second scanning interval n2 is smaller than the first scanning interval n1, and the maximum value of the degree of match at this time is referred to as the precise degree of match. In this embodiment, this precise degree of match is used as the judgment value. It can be determined that the larger the judgment value, the higher the likelihood of the ID card 10 being genuine, and the smaller the judgment value, the lower the likelihood of the ID card 10 being genuine.

[0067] The search area d2 is a square area, and the size of one side is smaller than that of the scanning area d1 and is preset to an odd number equal to or greater than 3, but the shape and size of the search area d2 are not particularly limited. In addition, the second scanning interval n2 described above is common to the x direction and y direction, and n2=1 (1 pixel), but is not limited to this.

[0068] As described above, in this embodiment, the hologram 20 formed on the ID card 10 is compared with a positive hologram 20, and the degree of match of their shapes is calculated as a judgment value for authenticity judgment. The shape of the hologram 20 can be expressed by its binary image. In this way, by utilizing the special shape of the hologram 20, an ID card 10 having a hologram 20 with a different shape can be detected as a fake ID card 10. Furthermore, the hologram 20 of the ID card 10 appears clearly in a captured image of the ID card 10 captured by a visible light camera under infrared illumination, and authenticity judgment can be performed by using the hologram image 100 acquired from the captured image.

[0069] Due to factors such as uneven lighting when photographing the ID card 10, there are cases where only a portion of the hologram 20 can be extracted from the photographed image of the ID card 10, as shown in Figure 14. In this embodiment, however, by calculating the degree of match using the above-mentioned equation (2), it is possible to evaluate the degree of match with the positive hologram 20 by limiting it to the portion of the hologram 20 that could be extracted (without taking into account the portion that could not be extracted), and therefore it is possible to appropriately determine authenticity even in cases such as those described above.

[0070] The degree of match (match) is calculated by template matching while scanning the hologram binary image 130. In this process, a scan is first performed with a coarse scanning interval n1 to locate a position where the degree of match (wide-area match) (match) is large, and then a precision scan is performed with a fine scanning interval n2 in a search area d2 centered on that position. This procedure makes it possible to shorten the processing time while improving accuracy.

[0071] When binarizing the hologram image 100, the adaptive binarization process can suitably extract the fine patterns of the hologram 20, but as described above, the hologram 20 may contain both fine and coarse patterns, and the same process may result in incomplete extraction of the coarse patterns. As a supplementary process for such cases, in this embodiment, a binary image (second basic binary image 120) is obtained by binarizing the entire hologram image 100 with a certain threshold value, and an OR process is performed between this image and the binary image (first basic binary image 110) obtained by the adaptive binarization process, thereby compensating for the incomplete extraction in the adaptive binarization process.

[0072] Furthermore, in this embodiment, the replacement process of S407 (see FIG. 8) prevents low-brightness parts such as characters in the hologram image 100 from affecting the judgment accuracy, and the preliminary judgment of S403 (see FIG. 8) enables early discrimination of obviously counterfeit ID cards 10 in which the hologram 20 is not even formed, thereby speeding up processing and reducing the load.

[0073] However, the present invention is not limited to the above-described embodiment. For example, in this embodiment, the ID card 10 is a residence card or a special permanent resident certificate, but the ID card 10 is not limited to these and may be any personal identification card on which a hologram is formed. The range in which the hologram image 100 is cut out from the captured image of the ID card 10 varies depending on the type of ID card 10 (such as a residence card or a special permanent resident certificate).

[0074] The brightness correction in S406 and the brightness substitution in S407 are also performed as necessary, and may be omitted depending on the shooting environment and shooting range of the ID card 10. In this embodiment, when calculating the degree of match in S410, the above formula (2) is used to perform a relative evaluation of the total number of matched pixels (evaluation based on the ratio to the total number of white pixels in the hologram binary image 130), but if the shooting environment of the ID card 10 is such that the entire hologram 20 can be extracted as the hologram binary image 130, it is also possible to perform an absolute evaluation of the total number of matched pixels, for example by using the total number of matched pixels itself as the degree of match.

[0075] In this embodiment, the judgment value calculated in S410 (see FIG. 8) itself is displayed in S5 (see FIG. 6), but the authenticity determination device 3 can also determine the authenticity of the ID card 10 by comparing the judgment value with a threshold value. In S5, the judgment result can be displayed on the display unit 34 together with the judgment value or alone, and can be used as information for the person in charge to make a decision.

[0076] Although the preferred embodiment of the present invention has been described above with reference to the accompanying drawings, the present invention is not limited to the above examples. It is clear that a person skilled in the art can come up with various modified or altered examples within the scope of the technical ideas disclosed in this application, and it is understood that these also naturally belong to the technical scope of the present invention. [Explanation of symbols]

[0077] 1: Authenticity determination system 2: Scanner 3: Authenticity determination device 10: ID card 20: Hologram 21: Camera 22: Lighting 100: Hologram image 110, 120: Basic binary image 130: Hologram binary image 200: Template image 301: Acquisition method 302: Preliminary determination means 303: Substitution means 304: Binarization means 305: Authenticity determination method

Claims

1. An apparatus for determining the authenticity of an identification card on which a hologram is formed, comprising: an acquisition means for acquiring a hologram image by cutting out an area in which a hologram of the identification card is formed from an image of the identification card captured by a visible light camera under infrared illumination; a binarization means for generating a hologram binary image in which a hologram portion and a background portion of the hologram image are expressed by binary values; an authenticity determination means for using a template image in which a hologram portion and a background portion of a positive hologram are represented by binary values, and calculating a degree of coincidence between a hologram shape in the binary hologram image and a hologram shape in the template image as a determination value indicative of the degree of authenticity of the identification card; An authenticity determining device comprising:

2. 2. The authenticity determination device according to claim 1, wherein the degree of coincidence is calculated as a ratio of a total number of pixels in the hologram portion in the hologram binary image, which correspond to a pixel located at a coordinate corresponding to said pixel in the template image and which is also a hologram portion, to a total number of pixels in the hologram portion in the hologram binary image, when the hologram binary image and the template image are superimposed.

3. The authenticity determining means includes: calculating the degree of coincidence while changing the position of the origin of the hologram binary image in the template image at a first scanning interval, and then setting a search area centered on the position of the origin when the degree of coincidence is maximized; The authenticity determination device according to claim 2, characterized in that the degree of agreement is calculated again while changing the position of the origin within the search area by a second scanning interval smaller than the first scanning interval, and the maximum value of the degrees of agreement is used as the determination value.

4. The binarization means includes: a process of binarizing the luminance of the pixel of interest by using an average luminance of pixels in a block centered on the pixel of interest as a threshold value for each pixel in the hologram image as the pixel of interest, thereby creating a first basic binary image, and simultaneously creating a second basic binary image by binarizing each pixel in the hologram image by a certain threshold value; The authenticity determination device according to claim 1, characterized in that if any of the pixels at corresponding positions in the first and second basic binary images is a hologram portion, the hologram binary image is created by processing the pixel at that position in the hologram binary image as a hologram portion.

5. The authenticity determination device according to claim 1, further comprising a replacement means for replacing the brightness of pixels in the hologram image whose brightness is less than a threshold value with an average brightness in the hologram image before binarizing the hologram image.

6. 2. The authenticity determining device according to claim 1, further comprising a preliminary determination means for determining whether or not a hologram is contained in the hologram image before binarizing the hologram image.

7. Computer, An apparatus for determining the authenticity of an identification card on which a hologram is formed, comprising: an acquisition means for acquiring a hologram image by cutting out an area in which a hologram of the identification card is formed from an image of the identification card captured by a visible light camera under infrared illumination; a binarization means for generating a hologram binary image in which a hologram portion and a background portion of the hologram image are expressed by binary values; an authenticity determination means for using a template image in which a hologram portion and a background portion of a positive hologram are represented by binary values, and calculating a degree of coincidence between a hologram shape in the binary hologram image and a hologram shape in the template image as a determination value indicative of the degree of authenticity of the identification card; A program for causing the device to function as an authenticity determination device having the above-mentioned features.

Images