Authenticity determination device and program

Abstract

To provide an authenticity determination device, etc. which enable appropriate authenticity determination of an identification card.SOLUTION: An authenticity determination device 3 provided herein determines authenticity of an ID card having a face image formed thereon. The authenticity determination device 3 comprises reception means 301 for receiving an image of an ID card from a user terminal 5, and authenticity determination means 302 configured to use the image of the ID card to determine authenticity of the ID card on the basis of a feature of corners of a background area of the face image. The features may for example be the shape of the corners, in which case the authenticity determination means 302 regards the ID card to be authentic if the corners are not identified to have a right angle.SELECTED DRAWING: Figure 4

Description

[Technical Field]

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

[0002] When opening an account at a financial institution, identification is required using an ID card (personal identification) such as a My Number card. However, there has been an increase in cases where ID cards are forged or altered in order to open accounts under the guise of another person for criminal purposes such as special fraud.

[0003] At typical financial institutions, users go to the institution to submit their ID card, and the financial institution then uses the submitted ID card to verify the user's identity in person. In this case, the ID card can be carefully observed, and any anomalies can be detected by touch alone.

[0004] Furthermore, Patent Documents 1 and 2 describe an authenticity determination device that determines the authenticity of an ID card from the image obtained by reading the face of the ID card with a reading device such as a scanner, and it is also possible to determine the authenticity of an ID card by reading a submitted ID card with a reading device such as a scanner. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Laid-Open No. 2011-34535 [Patent Document 2] Japanese Patent Application Publication No. 2019-117549 Summary of the Invention [Problem to be solved by the invention]

[0006] Recently, online financial institutions such as online banks have become common. Some of these financial institutions verify identity by taking a photo of the face of an ID card with a smartphone camera and sending the image to the financial institution.

[0007] In this case, identity verification is performed only by image, not face-to-face, so there is a need for a way to detect counterfeit or altered ID cards. However, it is not easy to detect a fake ID card from an image alone, which has been an issue when applying online.

[0008] For example, if someone falsifies an ID card by attaching a piece of paper with a fake face image printed on it, the fake ID card can be easily detected if the person is identified face-to-face. However, it is not easy to detect this if the person is identified based solely on the image on the ID card.

[0009] The present invention has been made in view of the above problems, and has as its object to provide an authenticity determination device and the like that can suitably determine the authenticity of an identification card. [Means for solving the problem]

[0010] The first invention for solving the above-mentioned problems is an apparatus for determining the authenticity of an identification card on which a face image is formed, which has an authenticity determination means for determining the authenticity of the identification card by using the image of the identification card and based on the features of the corners of the background area of ​​the face image. The feature of the corner is the shape of the corner, and the authenticity determination means determines that the identification card is authentic when the corner is not determined to be a right angle. The authenticity determination device is characterized by:

[0011] The corners of the background area of ​​the facial image on an ID card have characteristics unique to that ID. For example, in the case of a My Number card, the corners of the background area of ​​the facial image are rounded and the outline is blurred. Therefore, when the characteristics are changed as a result of forgery or alteration of the ID card, the present invention can effectively detect the fake ID card.

[0012] before The authenticity determination means, for example, detects straight lines from an edge image that detects the vertical edge of the corner and an edge image that detects the horizontal edge of the corner, and determines whether the corner is a right angle based on the angle formed by the straight lines detected from both edge images. In the first invention This makes it possible to suitably determine the authenticity of identification cards whose corners in the background area of ​​the face image are not right-angled. When determining the authenticity, as described above, straight lines are detected from the vertical and horizontal edge images of the corners, and it is possible to suitably determine whether the corners are right-angled or not from the angles formed by the detected straight lines.

[0013] The feature of the corner may be, for example, the clarity of the outline of the corner, and it is also desirable that the authenticity determination means determines the personal identification card to be authentic when the outline is not determined to be clear. The second invention is an authenticity determination device for an identification card on which a facial image is formed, which has an authenticity determination means that uses the image of the identification card to determine the authenticity of the identification card based on the characteristics of the corners of the background area of ​​the facial image, wherein the characteristics of the corners are the clarity of the outline of the corners, and the authenticity determination means determines the identification card to be authentic if the outline is not determined to be clear. The authenticity determination means, for example, performs a Hough transform on the edge image in which the corner edges are detected, and determines whether the contour is clear based on the number of curves obtained by the Hough transform that pass through the point where the curves intersect the most. This allows for suitable authentication of identification cards in which the contours of the corners of the background area of ​​the facial image are unclear. The Hough transform, a conventional technique, can be used to determine the authenticity of an identification card. The number of intersections of curves obtained by the Hough transform is an index indicating the reliability of contour detection. Therefore, this number can be used to suitably determine whether the contour is clear.

[0014] It is desirable that the authenticity determination device has a receiving means for receiving an image of the personal identification card from a user terminal. This makes it possible to construct, via a network, an authenticity determination system that determines the authenticity of an identification card using an image of the identification card transmitted from a user terminal.

[0015] No. 3 The invention is an apparatus for determining the authenticity of an identification card on which a face image is formed, comprising a computer and an authenticity determination means for determining the authenticity of the identification card based on the image of the identification card and the characteristics of the corners of the background area of ​​the face image. The feature of the corner is the shape of the corner, and the authenticity determination means determines that the identification card is authentic when the corner is not determined to be a right angle. This is a program that functions as an authenticity determination device. The fourth invention is a program for causing a computer to function as an authenticity determination device for an identification card on which a facial image is formed, the authenticity determination device having an authenticity determination means that uses the image of the identification card to determine the authenticity of the identification card based on the characteristics of the corners of the background area of ​​the facial image, the characteristics of the corners being the clarity of the outline of the corners, and the authenticity determination means that determines the identification card to be authentic if the outline is not determined to be clear. [Effects of the Invention]

[0016] According to the present invention, it is possible to provide an authenticity determination device and the like that can suitably determine the authenticity of an identification card. [Brief explanation of the drawings]

[0017] [Figure 1] FIG. 1 is a diagram showing an authenticity determination system 1. [Figure 2] FIG. 2 is a diagram showing the hardware configuration of the authenticity determination device 3. [Figure 3] FIG. 2 is a diagram showing the hardware configuration of a user terminal 5. [Figure 4] FIG. 2 is a block diagram showing the functions of the authenticity determination device 3. [Figure 5] 1 is a diagram showing an ID card 10. FIG. [Figure 6] 3 is a flowchart showing an outline of the processing of the authenticity determination system 1. [Figure 7] An example of the ID card 10 photo capture screen. [Figure 8] 10 Examples of Fake ID Cards. [Figure 9] 10 is a flowchart showing an authenticity determination method. [Figure 10] 3A to 3C are diagrams illustrating edge detection in the inspection image 100. [Figure 11] 3A to 3C are diagrams for explaining the creation of a binary image 300. [Figure 12] 10A and 10B are diagrams illustrating line detection using a Hough transform. [Figure 13] A diagram showing detection lines LV and LH. [Figure 14] Examples of an inspection image 100, edge images 200a, 200b, and a binary image 300. [Figure 15] FIG. 10 is a diagram illustrating calculation of an inner product. [Figure 16] A diagram showing ranges r1 and r2. DETAILED DESCRIPTION OF THE INVENTION

[0018] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings.

[0019] (1. Authenticity Determination System 1) 1 is a diagram showing an authenticity determination system 1 having an authenticity determination device 3 according to an embodiment of the present invention. The authenticity determination system 1 is configured by connecting the authenticity determination device 3 and a user terminal 5 via a network so that they can communicate with each other. In the authenticity determination system 1, an image of a user's ID card 10 is sent from the user terminal 5 to the authenticity determination device 3, and the authenticity determination device 3 determines the authenticity of the ID card 10 from the image.

[0020] 2 is a diagram showing the hardware configuration of the authenticity determination device 3. The authenticity determination device 3 can be realized by a computer configured by connecting a control unit 31, a storage unit 32, a communication unit 33, 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, and it is also possible to realize the authenticity determination device 3 using multiple computers.

[0021] The control unit 31 is composed of a CPU, ROM, RAM, etc. The CPU loads programs related to the processing of the authenticity determination device 3 stored in storage media such as the memory unit 32 and ROM into a work area on the RAM and executes them. The ROM is a non-volatile memory that permanently stores programs such as the boot program and BIOS, as well as data. The RAM is a volatile memory that temporarily stores programs and data loaded from the memory unit 32, ROM, etc., and also has a work area that the control unit 31 uses to perform various processes.

[0022] The storage unit 32 is a hard disk drive, a solid state drive, a flash memory, or the like, and stores programs executed by the authenticity determination device 3 in the processes described below, data required for program execution, an OS, and the like.

[0023] The communication unit 33 is a communication interface that mediates communication via a network, and communicates with the user terminal 5 .

[0024] The user terminal 5 is a terminal carried by the user, which takes a picture of the ID card 10 and transmits the photographed image to the authenticity determination device 3. As the user terminal 5, for example, a mobile terminal such as a smartphone or a tablet terminal is used.

[0025] Fig. 3 is a diagram showing the hardware configuration of the user terminal 5. As shown in Fig. 3, the user terminal 5 is configured by connecting a control unit 51, a storage unit 52, a display unit 53, an input unit 54, a communication unit 55, a camera 56, an audio input / output unit 57, etc. via a bus or the like. However, the configuration is not limited to this, and various other configurations may be used as appropriate.

[0026] The control unit 51, the storage unit 52, and the communication unit 55 are substantially the same as the above-described control unit 31, the storage unit 32, and the communication unit 33. The display unit 53 has a display device such as a liquid crystal panel, and is provided with a touch panel as an input unit 54 for inputting information to the user terminal 5. The audio input / output unit 57 has a microphone and a speaker used for audio input and output.

[0027] Camera 56 is an area camera that includes an optical lens, an imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal-Oxide Semiconductor), an A / D (Analog / Digital) converter, etc. Camera 56 photoelectrically converts the subject image input through the optical lens using the imaging element to generate an analog image signal. The A / D converter then converts the analog image signal into digital image data.

[0028] 4 is a block diagram showing the functions of the authenticity determination device 3. The authenticity determination device 3 includes a receiving means 301, an authenticity determination means 302, and the like.

[0029] The receiving means 301 is a means by which the control unit 31 of the authenticity determination device 3 receives an image of the ID card 10 from the user terminal 5 via the communication unit 33 .

[0030] The authenticity determining means 302 determines the authenticity of the ID card 10 by using the image of the ID card 10 received by the control unit 31 of the authenticity determining device 3 from the user terminal 5. Details of this authenticity determination will be described later.

[0031] (2. ID Card 10) In this embodiment, the ID card 10 is an identification card that is the subject of authentication determination. An identification card is a medium used for identity verification by financial institutions, mobile phone carriers, various administrative agencies, etc., and in this embodiment, it is a My Number card.

[0032] FIG. 5 is a diagram showing an outline of an ID card 10 (My Number Card), and is a schematic illustration of the face of the ID card 10 with some of the card face omitted.

[0033] Various information is printed on the face of the ID card 10, and for example, in the case of a My Number card, the face information includes the user's face image 101, name, address, date of birth, expiration date, etc.

[0034] Of these, the face image 101 is formed with a rectangular region R as the background, but the corners of this background region R are rounded and the outline is blurred and unclear due to shading processing.

[0035] (3. Overview of the processing 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 and S7 to S8 in Fig. 6 are processing executed by the control unit 51 of the user terminal 5 by controlling each unit of the user terminal 5, and S3 to S6 are processing executed by the control unit 31 of the authenticity determination device 3 by controlling each unit of the authenticity determination device 3.

[0036] In this embodiment, the user first operates the user terminal 5 to launch a dedicated application program pre-stored in the storage unit 52. The user terminal 5 then displays a menu screen (not shown) on the display unit 53, and activates the camera 56 in accordance with the user's selection on the menu screen to photograph the face of the ID card 10 (S1).

[0037] 7 shows an example of the screen for capturing the ID card 10. In this embodiment, when the camera is started, instructions are displayed on the display unit 53 of the user terminal 5 to prompt the user to place the ID card 10 within a predetermined frame 531, and then the ID card 10 is captured.

[0038] The user terminal 5 photographs the ID card 10 and transmits the image obtained to the authenticity determination device 3 (S2). This image is a color image (RGB image) in which the pixel colors are determined by the gradation values ​​of each of the R (red), G (green), and B (blue) components.

[0039] The authenticity determination device 3 receives the image of the ID card 10 (S3), and then determines the authenticity of the ID card 10 using the image of the ID card 10 (S4). The authenticity determination in this embodiment is performed based on the features of the corners of the background region R of the face image 101. The authenticity determination method will be described in detail later.

[0040] If the authenticity determination device 3 determines that the ID card 10 is fake (S5; NO), it transmits a message to the user terminal 5 that the ID card 10 is fake (S6). When the user terminal 5 receives a message that the ID card 10 is fake (S7), it displays this message on the display unit 53 (S8) and ends the process.

[0041] On the other hand, if the authenticity determination device 3 determines that the ID card 10 is authentic (S5; YES), it completes the authenticity determination process. For example, when authenticity determination is performed as identity verification when opening an account at a financial institution on the Internet, after the authenticity determination process, user information (such as name and date of birth) on the face of the ID card 10 can be obtained from an image of the ID card 10 as information required to open the account, and the user information can be registered and stored in the memory unit 52.

[0042] (4. Authenticity determination based on corner features of background region R of face image 101) As described above, the corners of the background region R of the facial image 101 on the ID card 10 are rounded and their outlines are unclear. On the other hand, as shown in FIG. 8, if an ID card 10 is forged by attaching a rectangular piece of paper 102 on which a fake facial image 101 is printed or the like to the ID card 10, the corners of the background region R (the area of ​​the piece of paper 102) of the facial image 101 will become right-angled and their outlines will be clearly defined. Therefore, it is possible to detect a fake ID card 10 from these differences in characteristics. Note that the methods of forgery and alteration of fake ID cards 10 that can be detected by the authenticity determination of this embodiment are not limited to these, and any method that changes the characteristics of the corners described above will do.

[0043] FIG. 9 is a flowchart showing the steps of the authenticity determination method in S4 of FIG.

[0044] In this embodiment, first, in the image of the ID card 10, a range corresponding to a corner of the background region R of the facial image 101 is extracted as a test image (S401). This range is set in advance according to the position of the background region R on the ID card 10. Symbol r1 in FIG. 5 is an example of this range, which is set in the upper left corner of the background region R.

[0045] Next, the authenticity determination device 3 converts the inspection image to a predetermined resolution (S402). The resolution conversion can be performed using a known method such as the bilinear method.

[0046] The authenticity determination device 3 also performs noise removal on the inspection image after the resolution conversion (S403). Noise removal can be performed by image processing using a known filter such as a median filter.

[0047] Reference numeral 100 in Fig. 10 denotes an example of an inspection image obtained by the processes of S401 to S403 when the corners of the background region R of the facial image 101 are right-angled as shown in Fig. 8. The authenticity determination device 3 then performs edge detection on the inspection image 100 (S404).

[0048] Although the method of edge detection is not particularly limited, in this embodiment, as shown in the following equation (1), the gradation value pn of each pixel in a certain range centered on the pixel of interest in inspection image 100 is multiplied by a coefficient kn (weighting coefficient) corresponding to the position of each pixel to calculate the sum Σ(pn×kn), and the absolute value abs(Σ(pn×kn)) of the sum Σ(pn×kn) is set as the gradation value p0' of the pixel of interest. In S404, this image processing is performed on each pixel in inspection image 100 as the pixel of interest. p0'=abs(Σ(pn×kn))…(1)

[0049] FIG. 10 shows an example of a matrix (edge ​​detection filter) of the coefficient kn described above, with the center of the matrix corresponding to the position of the pixel of interest. In this embodiment, vertical and horizontal edge detection are performed, and different matrices are used for each edge detection. As a result, vertical and horizontal edges are individually detected for the corners of the background region R from a single inspection image 100. In FIG. 10, reference numeral 200a denotes an edge image in which vertical edges have been detected, and reference numeral 200b denotes an edge image in which horizontal edges have been detected.

[0050] Next, the authenticity determination device 3 binarizes each of the edge images 200a and 200b to create a binary image (S405).

[0051] In this embodiment, binarization is performed based on the ranking of the gradation values ​​of each pixel in the edge images 200a and 200b. That is, a certain number of pixels are extracted in the edge images 200a and 200b in descending order of gradation value, and these pixels are binarized together with the other pixels. As a result, the number of pixels extracted as pixels with high gradation values ​​is basically the same (the above-mentioned certain number) even if the edge images 200a and 200b are different.

[0052] In this embodiment, the above gradation values ​​are used as the gradation values ​​for each of the RGB color components, and a binary image 300 is created for each color component as shown in Fig. 11, and noise removal is performed as necessary. Noise removal can be performed, for example, by expanding and contracting the edge portions. In the binary image 300 in Fig. 11, the edge portions are represented by white pixels.

[0053] Next, the authenticity determination device 3 performs line detection on the binary image 300 (S406).

[0054] Here, a Hough transform is used to detect straight lines. The Hough transform is a conventional technique, but to briefly explain it, for example, as shown in FIG. 12(a), a perpendicular line is dropped from the origin O to a straight line L that passes through a pixel P in the edge portion of a binary image 300, and the angle of the perpendicular line with respect to a predetermined reference line S is defined as θ, and the length of the perpendicular line is defined as ρ. Since there are an infinite number of straight lines L that pass through pixel P, if ρ and θ are calculated for each straight line L and all of these values ​​are represented on a ρ-θ coordinate system, a curve as shown in FIG. 12(b) can be obtained. Note that the amount of calculation can be reduced by limiting the range of θ for which the curve is calculated.

[0055] When the curves in Fig. 12(b) are found for each pixel in the edge portion, a point Q appears where the most curves intersect, as shown in Fig. 12(c). This means that a common straight line L is drawn to many of the pixels P1, P2, ... in the edge portion, as shown in Fig. 12(d), and the Hough transform detects this straight line L using the coordinates (θq, ρq) of the point Q. The number of curves that pass through the point Q is an index that indicates the reliability of line detection, i.e., the accuracy of detection of the contours of the corners of the background region R, and in this embodiment, this is referred to as the degree of concentration.

[0056] This is an outline of line detection using the Hough transform. In this embodiment, the line detection is performed separately for each of the RGB binary images 300 shown in FIG. 11, and the point Q on the ρ-θ coordinate where the most curves intersect is determined for each binary image 300. R , Q G , Q B Then, these points Q R , Q G , QB Compare the concentration of the points Q and Q max (Point Q R , Q G , Q B The final straight line is determined based on the values ​​of ρ and θ of the above (either of the above). This straight line will be referred to as the "detection line" hereinafter.

[0057] The above processing is performed for each of the vertical edge image 200a and the horizontal edge image 200b, and the above detection lines are obtained for each of the vertical and horizontal edge images 200a and 200b. Figure 13 shows the detection line L obtained from the binary image 300 of the vertical edge image 200a. V and the detection line L obtained from the binary image 300 of the horizontal edge image 200b. H are shown on the edge images 200a and 200b.

[0058] Here, the authenticity determination device 3 uses the above-mentioned concentration level to determine whether the outline of the corner of the background region R is clear (S407).

[0059] That is, if the corner contours of the background region R are blurred, as shown in Fig. 14, even if vertical and horizontal edge images 200a and 200b are created from inspection image 100, no clear lines will appear in binary image 300, resulting in a low degree of concentration. On the other hand, if the corner contours are clear, as in inspection image 100 in Fig. 10, clear lines will appear in binary image 300, resulting in a high degree of concentration. Therefore, it is possible to determine whether the corner contours of background region R are clear based on the level of concentration.

[0060] In S407, the authenticity determination device 3 performs the above-mentioned process for each of the vertical and horizontal edge images 200a and 200b. max The degree of concentration in both the vertical and horizontal edge images 200a and 200b is compared with a predetermined threshold. If the degree of concentration is equal to or less than the threshold in both the vertical and horizontal edge images 200a and 200b, it is determined that the corner contours of the background region R are not clear (S407; NO), and the ID card 10 is determined to be genuine (S408) as shown in FIG. 5, and the process ends.

[0061] On the other hand, if the concentration level exceeds the threshold in either the vertical or horizontal edge image 200a or 200b, it is determined that the outlines of the corners of the background region R are clear (S407; YES). In this case, it is determined that there is a possibility that the ID card 10 is a fake ID card 10 as shown in Figure 8, and it is further determined whether the corners of the background region R are right-angled (S409).

[0062] In S409, the authenticity determination device 3 detects the detection line L obtained from the binary image 300 of the vertical edge image 200a. V and the detection line L obtained from the binary image 300 of the horizontal edge image 200b. H Based on the angle formed by the two pixels, it is determined whether the corner of the background region R is a right angle or not.

[0063] That is, when the corners of the background region R of the face image 101 are rounded, as shown in FIG. 14, the detection line L obtained from the binary image 300 of the vertical and horizontal edge images 200a and 200b is V , L H The slopes of the detection line L V , L H On the other hand, when the corners of the background region R are right-angled as in the inspection image 100 of FIG. 10, the angle formed by the detection line L becomes close to 0° or 180° as shown in FIG. V , L H are perpendicular to each other, and the detection line L V , L H The angle formed by the detection line L approaches 90°. V , L H Based on the angle formed by the arrows, it is possible to determine whether the corners of the background region R are right-angled or not.

[0064] More specifically, in S409, the authenticity determination device 3 detects the detection line L as shown in FIG. V , L H The inner product of the unit vectors is calculated, and the absolute value of the inner product is compared with a predetermined value. V , L H The unit vector of the detection line L V , L H The absolute value of the inner product is the detection line L V , LH The angle formed by the detection line L V , L H When the slopes of the detection line L are the same, it becomes 1. V , L H is 0 when they are orthogonal.

[0065] If the absolute value of the dot product exceeds a predetermined value, the authenticity determination device 3 determines that the corners of the background region R are not right-angled (S409; NO), and concludes that the ID card 10 is genuine (S408) as shown in Figure 5, and ends the process. On the other hand, if the absolute value of the dot product is equal to or less than the predetermined value, the authenticity determination device 3 determines that the corners of the background region R are right-angled (S409; YES), and concludes that the ID card 10 is a fake ID card 10 as shown in Figure 8 (S410), and ends the process.

[0066] As described above, in this embodiment, the authenticity of the ID card 10 is determined by utilizing the unique features of the ID card 10 that are found in the corners of the background region R of the facial image 101 on the ID card 10. Therefore, if the features are changed as a result of forgery or alteration of the ID card 10, a fake ID card 10 can be suitably detected.

[0067] In particular, this embodiment can suitably determine the authenticity of an ID card 10 in which the corners of the background region R of the face image 101 are not right-angled, as shown in Fig. 5. When determining the authenticity, straight lines are detected from the vertical and horizontal edge images 200a and 200b as shown in Fig. 13, and the detection line L V , L H Whether the corner is a right angle or not can be suitably determined from the angle formed by the arrows.

[0068] Furthermore, in this embodiment, it is possible to suitably determine the authenticity of an ID card 10 in which the corners of the background region R of the facial image 101 have unclear contours. The Hough transform, a conventional technique, can be used to determine the authenticity, and the number of intersections of the curves obtained by the Hough transform (see FIG. 12(c)) is an index indicating the accuracy of contour detection. Therefore, this number can be used to suitably determine whether the contour is clear.

[0069] In this embodiment, the authenticity determination system 1 that determines the authenticity of the ID card 10 from an image of the ID card 10 transmitted from the user terminal 5 can be constructed using a network.

[0070] However, the present invention is not limited to the above-described embodiment. For example, in the present embodiment, authenticity determination is performed as identity verification when opening an account, but the application scene or purpose of the authenticity determination of the present embodiment is not particularly limited.

[0071] In the above-mentioned S401 (see FIG. 9), the test image 100 is obtained by extracting the range r1 in the upper left corner of the background region R of the face image 101 from the image of the ID card 10, but it is also possible to extract multiple ranges and perform the authentication process described with reference to FIG. 9 etc. for each of the multiple test images 100. This improves the accuracy of the authentication determination.

[0072] 16 shows an example of extracting multiple areas from an image of an ID card 10. In addition to the area r1 in the upper left corner of the background region R, the area r2 in the upper right corner can also be extracted to obtain multiple test images 100. For the test image 100 extracted from the area r2 in the upper right corner, the same authentication process as for the test image 100 extracted from the area r1 in the upper left corner can be performed by flipping the image horizontally in advance. If the ID card 10 is determined to be genuine for both test images 100, the final authentication result is determined to be true. However, the criteria for authenticity determination are not limited to this, and the final authentication result may be determined to be true if the ID card 10 is determined to be genuine for any of the test images 100.

[0073] In addition, in this embodiment, by creating a binary image 300 from each of the RGB components of the edge images 200a and 200b and performing an authenticity determination, the influence of the background pattern of the ID card 10 can be reduced and the accuracy of the authenticity determination can be improved, but the binary image 300 may be created for only one of the color components, or the binary image 300 may be created after converting the edge images 200a and 200b to grayscale.

[0074] In this embodiment, in S405 (see FIG. 9), binarization is performed based on the ranking of the gradation values ​​of each pixel in the edge images 200a and 200b, but the binarization method is not limited to this. As is well known, binarization can also be performed by comparing the gradation values ​​of each pixel in the edge images 200a and 200b with a predetermined threshold value.

[0075] In this embodiment, in the above-mentioned S407 (see FIG. 9), if the concentration level exceeds a threshold in either the vertical or horizontal edge image 200a or 200b, the contours of the corners of the background region R are determined to be clear; however, if the concentration level exceeds a threshold in both the vertical and horizontal edge images 200a and 200b, the contours of the corners of the background region R may also be determined to be clear.

[0076] In this embodiment, both the shape (S409 in FIG. 9) and the clarity of the outline (S407) are determined for the corners of the background region R of the facial image 101, but it is also possible to perform only one of them. Also, while the ID card 10 is a My Number card, this is not limited to this, and the method can be applied to any background region R of the facial image 101 where the outline of the corners is unclear or the corner shape is not right-angled.

[0077] While the preferred embodiments of the present invention have been described above with reference to the accompanying drawings, the present invention is not limited to these examples. It is clear that those skilled in the art can conceive of various modifications or alterations within the scope of the technical ideas disclosed herein, and it is understood that these modifications also fall within the technical scope of the present invention. [Explanation of symbols]

[0078] 1: Authenticity determination system 3: Authenticity determination device 5: User terminal 10: ID card 100: Inspection image 101:Facial image 200a, 200b: Edge images 300: Binary image 301: Receiving method 302: Authenticity determination means

Claims

1. An apparatus for determining the authenticity of an identification card on which a face image is formed, an authenticity determination means for determining the authenticity of the identification card based on the image of the identification card and the features of the corners of the background area of ​​the face image; the corner feature is the shape of the corner; The authenticity determining device is characterized in that the authenticity determining means determines the personal identification card to be authentic when the corner is not determined to be a right angle.

2. The authenticity determination device according to claim 1, characterized in that the authenticity determination means detects straight lines from an edge image in which the vertical edges of the corner are detected and an edge image in which the horizontal edges of the corner are detected, and determines whether the corner is a right angle based on the angle formed by the straight lines detected from both edge images.

3. The corner feature is a clear outline of the corner, 3. The authenticity determination device according to claim 1, wherein said authenticity determination means determines said personal identification card to be authentic when said outline is not clearly discerned.

4. An apparatus for determining the authenticity of an identification card on which a face image is formed, an authenticity determination means for determining the authenticity of the identification card based on the image of the identification card and the features of the corners of the background area of ​​the face image; The corner feature is a clear outline of the corner, The authenticity determination device is characterized in that the authenticity determination means determines the personal identification card to be authentic when the outline is not clearly determined.

5. The authenticity determination device according to claim 3 or 4, characterized in that the authenticity determination means performs a Hough transform on the edge image in which the edges of the corners are detected, and determines whether the contour is clear based on the number of curves obtained by the Hough transform that pass through the point where the curves intersect the most.

6. 6. The authenticity determining device according to claim 1, further comprising a receiving means for receiving an image of the personal identification card from a user terminal.

7. Computer, An apparatus for determining the authenticity of an identification card on which a face image is formed, an authenticity determination means for determining the authenticity of the identification card based on the image of the identification card and the features of the corners of the background area of ​​the face image; the corner feature is the shape of the corner; The authenticity determination means is a program for causing the device to function as an authenticity determination device that determines the personal identification card to be authentic if the corner is not determined to be a right angle.

8. Computer, An apparatus for determining the authenticity of an identification card on which a face image is formed, an authenticity determination means for determining the authenticity of the identification card based on the image of the identification card and the features of the corners of the background area of ​​the face image; The corner feature is a clear outline of the corner, The authenticity determination means is a program for functioning as an authenticity determination device that determines the personal identification card to be authentic when the outline is not clearly determined.

Images