Authenticity determination device and program

Abstract

To provide an authenticity determination device capable of suitably conducting an authenticity determination of a personal identification certificate, as well as having high popularization properties.SOLUTION: An authenticity determination device 3 includes: discrimination means 301 configured to binarize an image of a potentially fusion-printed character of an ID card obtained from a card surface image of the ID card by each of a plurality of threshold values, and according to a result of the binarization at each threshold value, to discriminate whether or not the character is a fusion-printed character; and authenticity determination means 302 configured to conduct an authenticity determination of the ID card from a discrimination result by the discrimination means 301.SELECTED DRAWING: Figure 3

Description

[Technical field]

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

[0002] Various applications may require identity verification using an ID card such as a driver's license, and it is necessary to verify the authenticity of the ID card in order to prevent fraudulent applications using forged or altered ID cards.

[0003] Therefore, Patent Document 1 describes a method of determining authenticity using an image of a driver's license or the like based on a stepped portion of a line printed by a thermal transfer method. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2019-117549 A Summary of the Invention [Problem to be solved by the invention]

[0005] In order to determine the authenticity of a driver's license or other document based on its fine features, a high-resolution reading device is required. However, such reading devices are expensive, posing a challenge in terms of widespread use.

[0006] Another issue with authenticity determination using images of ID cards such as driver's licenses is the risk of a genuine card being erroneously determined to be a fake due to dirt on the ID card, etc. Also, when performing a determination by comparison with positive data, it can be very labor-intensive to create the positive data when a reading device is first introduced or changed, and there is also a risk of the positive data being biased due to a small number of samples (genuine cards) for creating the positive data.

[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 and is highly versatile. [Means for solving the problem]

[0008] The first invention for solving the above-mentioned problems is an authenticity determination device characterized by having a discrimination means for binarizing an image of the melt-printed characters on an identification card obtained from an image of the face of the identification card at each of a plurality of threshold values, and determining whether the characters have been melt-printed based on the results of the binarization at each threshold value, and an authenticity determination means for determining the authenticity of the identification card from the discrimination results by the discrimination means.

[0009] In the present invention, the results of binarizing the image of the melt-printed characters on the identification card at each of a plurality of thresholds are different from those when the image is printed by other methods, and this makes it possible to suitably determine the authenticity of the identification card, and to detect fake identification cards in which the characters are printed by methods other than melt printing. In addition, when determining authenticity using the results of binarizing the image of the characters at multiple thresholds, a high-resolution reading device is not required, and complex calculations are not required, making this method highly applicable. Furthermore, since the present invention determines whether the characters are melt-printed or not, the positive data does not depend on the type of identification card, and the positive data is small because the characters to be determined are limited, so that creating the positive data does not require a lot of labor.

[0010] It is desirable that the discrimination means discriminates whether or not each of the multiple characters has been melt-printed, and the authenticity determination means compares the number of characters determined to have been melt-printed with a reference value to determine the authenticity of the identification card. By determining whether a plurality of characters on the identification card have been melt-printed or not and comprehensively determining the authenticity of the identification card from the determination result, the result of the authenticity determination becomes less susceptible to the influence of localized stains on the identification card.

[0011] Preferably, said characters are numbers. Even on different IDs, numbers such as "1" and "2" are often commonly used. Therefore, by using numbers as the characters to be identified, it is easier to collect samples to create positive data, and there is less risk of the positive data being biased.

[0012] It is also preferable that the determining means obtains index values ​​for a plurality of evaluation indexes from the results of binarization using each threshold value, and determines whether or not the characters have been melt-printed using the plurality of index values. By comprehensively determining whether or not a character is melt-printed using a plurality of evaluation indexes, it is possible to improve the accuracy of the determination.

[0013] The discrimination means determines the degree of approximation of the index value to a positive value, multiplies the degree of approximation by a weighting coefficient to obtain a score, calculates the sum of the scores across a plurality of the evaluation indexes as an overall score, and compares the overall score with a predetermined discrimination value to determine whether the character has been melt-printed, and it is desirable that at least one of the positive value, the coefficient, and the discrimination value differ depending on the character. This makes it possible to distinguish between characters such as "1" and "2", improving the accuracy of distinguishing whether or not a character has been melt-printed.

[0014] The evaluation index preferably includes the difference between the area of ​​a black dot when binarization is performed with the minimum threshold at which a black dot is detected and the area of ​​a black dot when binarization is performed with the next smaller threshold when a pixel with a gradation value equal to or less than a threshold is regarded as a black dot. It is also preferable to include the minimum threshold at which a black dot is detected. Furthermore, it is also preferable to include the difference between the area of ​​a black dot when binarization is performed with the minimum threshold and the area of ​​a black dot when binarization is performed with the maximum threshold, and it is also preferable to include the number of consecutive black dots when binarization is performed with the minimum threshold at which a black dot is detected. These evaluation indices make it possible to express the characteristics of the melt-printed characters when they are binarized using multiple threshold values, making it easier to distinguish this method from other printing methods.

[0015] The second invention is a program for causing a computer to function as an authenticity determination device having a discrimination means for binarizing an image of melt-printed characters on an identification card obtained from an image of the face of the identification card at each of a plurality of threshold values, and determining whether the characters have been melt-printed based on the results of the binarization at each threshold value, and an authenticity determination means for determining the authenticity of the identification card from the discrimination results by the discrimination means. Effect of the Invention

[0016] 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 and is highly applicable. [Brief description of the drawings]

[0017] [Figure 1] FIG. 1 shows an authenticity determination system 1. [Diagram 2] FIG. 2 is a diagram showing the hardware configuration of an authenticity determination device 3. [Diagram 3] FIG. 2 is a diagram showing the function of the authenticity determination device 3. [Figure 4] A diagram showing an ID card 10. [Diagram 5] 3A to 3C are diagrams for explaining printing on an ID card 10. [Figure 6] 1 is a flowchart showing the flow of an authenticity determining method. [Figure 7] FIG. 13 is a diagram showing an area a from which a card face image is cut out. [Figure 8] FIG. 4 is a diagram for explaining a change in black dots. [Figure 9] FIG. 4 is a diagram for explaining the continuity of black dots. [Figure 10] FIG. 13 is a diagram for explaining a determination method using an index value. [Figure 11] Diagram showing positive values ​​and coefficients by letter. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[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 determines the authenticity of an ID card 10, and has a reading device 2 and the authenticity determination device 3. The reading device 2 and the authenticity determination device 3 are connected to each other so as to be able to communicate with each other via wired or wireless communication means.

[0020] The reader 2 is for reading the ID card 10 and includes a scanner 21 and an IC chip reader 22 .

[0021] The scanner 21 is for acquiring an image of the face of the ID card 10, and may be, for example, a known scanning device.

[0022] The IC chip reading unit 22 reads data stored in an IC chip (not shown) of the ID card 10, and may be, for example, a known reader / writer.

[0023] In this embodiment, the scanner 21 and the IC chip reading unit 22 are configured as an integrated device, but they may be configured as separate devices. Also, a camera or the like can be used to capture an image of the face of the ID card 10.

[0024] The authenticity determination device 3 determines the authenticity of the ID card 10 based on an image of the face of the ID card 10.

[0025] 2 is a diagram showing the hardware configuration of the authenticity determination device 3, and the authenticity determination device 3 can be realized by a computer configured by connecting a control unit 31, a storage unit 32, a communication control unit 33, etc. via a bus, etc. However, the authenticity determination device 3 is not limited to this, and various configurations can be used as appropriate.

[0026] 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.

[0027] 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 necessary for executing the programs, an OS, etc. These programs and data are read out and executed by the control unit 31 as necessary.

[0028] The communication control unit 33 is a communication interface that mediates communication, and performs communication with the reader 2 .

[0029] Fig. 3 is a block diagram showing the functions of the authenticity determination device 3. As shown in Fig. 3, the authenticity determination device 3 includes a discrimination means 301, an authenticity determination means 302, and the like.

[0030] The discrimination means 301 is a means for determining whether or not the characters have been printed by a melting type thermal transfer method based on the results of binarization performed by the control unit 31 of the authenticity determination device 3, which performs binarization using a plurality of threshold values ​​for the image of the characters on the ID card 10 obtained from the face image of the ID card 10. The details of this discrimination will be described later.

[0031] The authenticity determining means 302 is a means by which the control unit 31 of the authenticity determining device 3 determines the authenticity of the ID card 10 based on the above-mentioned discrimination result.

[0032] (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 in various applications, such as a driver's license, a My Number card, a residence card, or a special permanent resident card.

[0033] 4 is a diagram showing an overview of an ID card 10, and is a schematic diagram showing an example of the face of the ID card 10. The ID card 10 has the card holder's name 12, date of birth 13, address 14, face image 18, issue date 15 of the ID card 10, issue number 16, expiration date 17, etc. printed on a substantially rectangular card substrate.

[0034] On the ID card 10, the name 12, the characters of the date of birth 13 excluding "year", "month", "day", and "birth", the address 14, the face image 18, the characters of the date of issue 15 excluding "year", "month", and "day", the characters of the issue number 16 excluding "number" and "issue number", the expiration date 17, etc. are on-demand information that differs for each ID card 10, and are formed by printing at a fixed position on the card substrate by a thermal transfer method using a thermal head. The characters other than the face image 18 are printed by a melting type thermal transfer method, and the face image 18 is printed by a dye-sublimation type thermal transfer method. Hereinafter, the former printing method may be referred to as melting printing, and the latter printing method as dye-sublimation printing.

[0035] The configuration of the on-demand information described above varies depending on the type of ID card 10, such as a driver's license, My Number card, residence card, or special permanent resident card.

[0036] (3. Thermal transfer printing) Printing by the thermal transfer method is performed by a thermal transfer printer 100 shown in Fig. 5(a). In the thermal transfer printer 100, while transporting the ID card 10 by transport rollers 103, a thermal transfer ribbon 200 wound around a supply reel 101 is unwound and transported in the transport direction of the ID card 10 indicated by the arrow, and on the way there, heat is applied to the thermal transfer ribbon 200 by a thermal head 110 to transfer the transfer layer of the thermal transfer ribbon 200 onto the ID card 10. After transfer, the thermal transfer ribbon 200 is taken up by a take-up reel 102.

[0037] As shown in Fig. 5(b), the thermal head 110 applies heat to the thermal transfer ribbon 200 from the thermal head element 111 provided on its underside. The thermal transfer ribbon 200 has a transfer layer 202 provided on a substrate 201, and in melt printing, when the thermal head element 111 applies heat to a predetermined range c of the transfer layer 202, the transfer layer 202 in this range c adheres to the ID card 10, and when the thermal transfer ribbon 200 is taken up by the take-up reel 102 and separated from the ID card 10, it peels off from the substrate 201. As a result, the transfer layer 202 is transferred onto the ID card 10, and printing is performed.

[0038] The thermal transfer ribbon 200 used for melt printing has a high black density of the transfer layer 202. In addition, the area to which the transfer layer 202 is transferred is limited to the area to which heat is applied, and no transfer occurs in areas to which heat is not applied, so the outline of the printed area appears clearly.

[0039] On the other hand, in sublimation printing, a sublimable dye is provided on the transfer layer 202 of the thermal transfer ribbon 200, and as shown in Fig. 5(c), when the thermal head element 111 applies heat to a predetermined area c of the transfer layer 202, the sublimable dye in this area c of the transfer layer 202 vaporizes and thermally diffuses into the receiving layer 10a of the ID card 10. In this way, printing is performed on the ID card 10.

[0040] The sublimation dye used in sublimation printing has a lower black density than the transfer layer 202 of the thermal transfer ribbon 200 used in melt printing. In addition, a part of the sublimation dye is thermally diffused widely around the part of the receiving layer 10a corresponding to the range c, so the outline of the printed part is not as clear as in melt printing.

[0041] (4. Overview of Authenticity Determination Method) Fig. 6 is a flowchart showing an outline of an authenticity determination method executed by the authenticity determination device 3. The control unit 31 of the authenticity determination device 3 controls each unit of the authenticity determination device 3 to execute each step in Fig. 6.

[0042] 6 is started, for example, by setting the ID card 10 in the reading device 2 and inputting a command to start the process to the reading device 2. The reading device 2 obtains an image of the face of the ID card 10 by the scanner 21, and the authenticity determination device 3 receives and obtains the image of the face of the ID card 10 from the reading device 2 (S1).

[0043] The authenticity determination device 3 cuts out an area including the characters printed on the ID card 10 from the face image (S2), and performs OCR (Optical Character Recognition) processing on the cut-out image (S3) to identify the characters in the image. The OCR processing is well known, and a description thereof will be omitted.

[0044] In this embodiment, the numbers used in the date of birth 13, date of issue 15, issue number 16, expiration date 17, etc. are used as the melt-printed characters, and area a is cut out for a plurality of characters (numbers) as shown in Fig. 7. In the ID card 10, the printing areas for each number in the date of birth 13, date of issue 15, issue number 16, expiration date 17, etc. are predetermined, so the printing areas can be cut out from the card face image.

[0045] It is desirable that the areas a to be cut out are located in a dispersed manner throughout the card. This is because stains and smudges on the ID card 10 often occur locally, and if multiple areas a are close together, all of the cut-out images of these areas a may be affected by the stains and smudges, which may lead to erroneous judgment. In consideration of the judgment accuracy, it is desirable that the number of areas a be 10 or more, but is not limited to this.

[0046] The authenticity determination device 3 then binarizes the cut-out image of each region a to obtain a binary image for the character in each region a (S4). In this embodiment, in particular, the cut-out image of each region a is binarized with each of a plurality of thresholds, and as a result, a plurality of binary images are obtained for each character.

[0047] Thereafter, the authenticity determination device 3 uses the multiple binary images obtained for each character to determine whether or not each character has been melt-printed (S5). The details of this determination will be described later.

[0048] The authenticity determination device 3 performs an authenticity determination of the ID card 10 based on the determination result in S5. In this embodiment, the number of characters determined to be melt-printed is compared with a predetermined reference value, and if the number of characters is less than the reference value (S6; NO), the ID card 10 is determined to be fake (S7), and the authenticity determination process is terminated by displaying this fact on a display device (not shown) to inform the user. The above reference value is not particularly limited and can be determined taking into consideration the accuracy of determination, etc. The larger the reference value, the stricter the determination will be.

[0049] On the other hand, if the characters determined to be melt-printed are equal to or greater than the reference value (S6; YES), the authenticity determining device 3 determines that the ID card 10 is genuine (S8) and ends the authenticity determining process.

[0050] (5. Identifying whether or not the characters are melt-printed) Next, the determination as to whether or not the characters have been melt-printed, which is performed in S5, will be described.

[0051] Figure 8(a) shows pixels (hereafter referred to as black dots) whose gradation values ​​are below the threshold when an image containing part of a melt-printed character is binarized using a threshold. There are eight thresholds in total: 10, 16, 32, 48, 64, 72, 100, and 128, and Figure 8(a) shows black dots when binarized using each threshold. The gradation value indicates the brightness of a pixel; the lower the value, the closer it is to black, and the higher the value, the closer it is to white.

[0052] As mentioned above, black density is high in melt printing, so black dots appear even when binarization is performed with a low threshold value of 10. Also, once a black dot appears, there is not much change in the area of ​​the black dot even if the threshold value is raised.

[0053] On the other hand, for comparison, Figures 8(b) and (c) show the changes in black dots when binarization is performed for dye-sublimation printed characters and inkjet printed characters, respectively, with the threshold value similarly changed.

[0054] As mentioned above, sublimation printing has a lower black density than melting printing, so when binarization is performed with a low threshold of "10," black dots do not appear, unlike melting printing, as shown in Figure 8(b). On the other hand, as the threshold is increased, the area of ​​the black dots changes significantly as the diffused parts of the sublimation dye begin to appear as black dots, and because the sublimation dye thermally diffuses over a wide area as mentioned above, the area of ​​the black dots increases at a high threshold of "128."

[0055] The black density of inkjet printing is similar to that of melt printing, and the change in black dots is generally similar to that of melt printing, as shown in Figure 8(c). However, because inkjet printing uses an area gradation method, at a low threshold value of "10", the spaces between the dots become white and the area of ​​the black dots is smaller than that of melt printing. When the threshold value is increased from there, the spaces between the dots become black and the area of ​​the black dots increases rapidly.

[0056] Fig. 8(d) shows the change in the area of ​​black dots (hereinafter, sometimes referred to as black area) with the change in threshold value for the above-mentioned melt printing, sublimation printing, and inkjet printing. In this embodiment, based on the observation results of the black dots described in Fig. 8(a) to (c), the following evaluation indices are calculated (index values): A. change in black area in the low threshold band, B. minimum threshold value at which black dots are detected, C. total change in black area, and D. value for the continuity of black dots. These index values ​​are used to determine whether or not characters have been melt printed.

[0057] (A. Change in black area in the low threshold range) As mentioned above, in the case of dye-sublimation printed characters, due to the influence of the diffused parts of the sublimation dye, the change in the black area is large between the minimum threshold at which black dots are detected ("16" in the example of FIG. 8(b)) and the next smallest threshold ("32" in the example of FIG. 8(b)). In the case of inkjet printed characters, due to the characteristics of the area gradation method, the change in the black area is also large between the minimum threshold at which black dots are detected ("10" in the example of FIG. 8(c)) and the next smallest threshold ("16" in the example of FIG. 8(b)). On the other hand, in the case of melt-printed characters, the change in the black area is not so large even if the threshold is increased, and this is also the case in the low threshold range.

[0058] Therefore, in this embodiment, as an index value showing the change in the black area in the low threshold band, the difference between the black area when binarized with the smallest threshold at which black dots are detected and the black area when binarized with the next smallest threshold is calculated by subtracting the former from the latter, as shown by symbol A in Fig. 8(d). However, the specific method of calculating the index value is not limited to the above, and any method that can quantify the difference between the two areas will do.

[0059] (B. Minimum threshold for detecting black dots) As mentioned above, black appears dark in thermal printing and inkjet printing, so black dots can be detected even with a low threshold value of "10". In contrast, the black density is low in dye-sublimation printing, so the minimum threshold value at which black dots are detected is large. Therefore, in this embodiment, the minimum threshold value at which black dots are detected can be obtained as an index value, as shown by symbol B in Figure 8(d).

[0060] (C. Total change in black area) As mentioned above, in the case of melt-printed characters, the change in the black area is not so large even if the threshold is increased, and the change in the black area when viewed across the entire threshold (referred to as the total change in the black area) is also small. On the other hand, in the case of dye-sublimation printing, due to the low black density and the influence of the diffused parts of the sublimation dye, the black area changes significantly as the threshold increases, and the total change in the black area becomes large. Also, in the case of inkjet printing, the black area at the low threshold "10" is small, so the total change in the black area becomes large.

[0061] Therefore, in this embodiment, as an index value showing the total change in the black area, the difference between the black area at the minimum threshold and the black area at the maximum threshold is calculated by subtracting the former from the latter, as shown by symbol C in Fig. 8(d). However, the specific method of calculating the index value is not limited to the above, and any method can be used as long as it can quantify the difference between the two areas.

[0062] (D. Continuity of black dots) Due to the characteristics of the thermal transfer printing method described above, there is a clear difference in density between the printed and non-printed areas on the ID card 10. Therefore, as shown in Figure 9(a), even if the threshold is low, if the threshold is high enough to detect black dots, many black dots will be detected, and these black dots will be continuous to form large islands.

[0063] On the other hand, in the case of dye-sublimation printing, due to the difference in the thermal transfer method from melting printing, the continuity of black dots is low at the minimum threshold at which black dots are detected, as shown in Figure 9(b).In the case of inkjet printing, as shown in Figure 9(c), at the minimum threshold at which black dots are detected, the spaces between the halftone dots become white due to the characteristics of the area gradation method, so the continuity of black dots is also low.

[0064] Therefore, in this embodiment, a binary image binarized with the minimum threshold at which black dots are detected is targeted, and the number of consecutive black dots in a predetermined direction in the binary image is calculated as an index value indicating the continuity of black dots, as shown by symbol D in Fig. 9. The predetermined direction is, for example, the vertical direction of the binary image, and when calculating the index value, for example, all columns of the binary image are scanned in the vertical direction, and the maximum number of consecutive black dots is used as the index value. However, the specific method of calculating the index value is not limited to this, and any method can be used as long as it can quantify the continuity of black dots.

[0065] A discrimination method using the index values ​​of each evaluation index A to D will be described with reference to Fig. 10. In this embodiment, in the above-mentioned S5 (see Fig. 6), the cut-out image of the character in each region a shown in Fig. 7 is binarized with eight thresholds of 10, 16, 32, 48, 64, 72, 100, and 128 to obtain the index values ​​of the above-mentioned evaluation indexes A to D, and the degree of approximation of each index value to a positive value is calculated. The degree of approximation is, for example, the ratio of the index value to the positive value, but is not limited to this and may be anything that indicates the closeness of both values.

[0066] Then, the degree of approximation of each of the evaluation indexes A to D is weighted by a coefficient, and a score for each of the evaluation indexes A to D is calculated by multiplying the degree of approximation by the coefficient.

[0067] The authenticity determination device 3 calculates a total score by adding up these scores for the evaluation indexes A to D, and compares the total score with a predetermined discrimination value. If the total score is equal to or greater than the discrimination value, the authenticity determination device 3 determines that the character is a melt-printed character, and if the total score is less than the discrimination value, the authenticity determination device 3 determines that the character is not a melt-printed character.

[0068] In this manner, it is possible to accurately determine whether the characters in each area a are melt-printed or not, and to prevent misidentification. The positive values ​​and coefficients described above can be determined for each of the evaluation indexes A to D by conducting preliminary experiments or the like on characters printed by various printing methods including melt printing. As shown in FIG. 11, the positive values ​​and coefficients for some or all of the evaluation indexes can be set to different values ​​depending on the character, and the values ​​corresponding to the characters identified in S3 (see FIG. 6) can be used. However, the sum of the coefficients of the evaluation indexes A to D remains the same even if the character changes ("10" in the example of FIG. 11).

[0069] In the example of Fig. 11, the discrimination value is the same regardless of the character ("7" in the example of Fig. 11), but the discrimination value may be changed depending on the character. The discrimination value can also be set by conducting a prior experiment on characters printed by various printing methods including melt printing.

[0070] As described above, in this embodiment, the authenticity of the ID card 10 can be suitably determined by utilizing the fact that the results of binarizing the cut-out image of the melt-printed characters on the ID card 10 at each of a number of threshold values ​​differ from those when the ID card is printed by other methods. This makes it possible to detect fake ID cards 10 on which characters are printed by a method other than melt-printing, whether the entire card face is forged or only part of the character string is forged.

[0071] Furthermore, when authenticity is determined using the results of binarizing an extracted image of characters using multiple thresholds, a high-resolution reading device 2 is not required, and no complex calculations are required, making this method highly applicable. Furthermore, since this embodiment determines whether characters have been melt-printed or not, the positive data does not depend on the type of ID card 10, and the positive data (for example, the "positive value" in Figure 11) can be reduced by limiting the characters to be determined, so creating the positive data does not require a lot of labor.

[0072] In addition, in this embodiment, a determination is made as to whether or not multiple characters on the ID card 10 have been melt-printed, and the authenticity of the ID card 10 is comprehensively determined from the results of that determination, making the results of the authenticity determination less susceptible to influences such as localized stains on the ID card 10.

[0073] In this embodiment, the characters to be identified are numbers such as "1" and "2" that are often commonly used even on different ID cards 10, making it easier to collect samples for creating positive data and reducing the risk of the positive data being biased. Numbers are also preferable in that they generally have low line density and are less likely to be crushed during binarization.

[0074] Furthermore, in this embodiment, by comprehensively determining whether or not a character is melt-printed using a plurality of evaluation indexes A to D, it is possible to improve the accuracy of determination.

[0075] In this embodiment, whether or not a character is melt-printed is determined using the method described in Fig. 10, and further, by changing the positive value, coefficient, discrimination value, etc. used in this case depending on the character, it becomes possible to discriminate depending on characters such as "1" and "2", improving the accuracy of discriminating whether or not a character is melt-printed. Note that in this embodiment, the positive value and coefficient are changed depending on the character, but it is sufficient if at least one of the positive value, coefficient, and discrimination value is made different depending on the character.

[0076] Furthermore, in this embodiment, by using the evaluation indexes A to D described above, it is possible to express the characteristics of the melt-printed characters when they are binarized using each of multiple threshold values, making it easier to distinguish this method from other printing methods.

[0077] However, the present invention is not limited to the above embodiment. For example, in this embodiment, after multiple areas a are cut out from the face image of the ID card 10, the characters contained in the areas a are identified by OCR processing, but it is also possible to first perform OCR processing on the entire face of the ID card, and then cut out areas a where specific characters such as "1" and "2" can be identified from the face image.

[0078] In this embodiment, numbers such as "1" and "2" are used as the characters melt-printed on the ID card 10, but this is not limited thereto, and letters such as the alphabet can also be used. In this embodiment, the threshold values ​​used for binarization are set to a total of eight levels, namely 10, 16, 32, 48, 64, 72, 100, and 128, but the number and values ​​of the threshold values ​​are not limited thereto, and can be determined appropriately through prior experiments, etc.

[0079] The method of determining whether a character is melt-printed is not limited to the above, and although, for example, all of the evaluation indexes A to D are used in the present embodiment, in some cases, one or more of the evaluation indexes A to D may be selected and used for the determination, and other evaluation indexes that represent the characteristics of the melt-printing graph in Fig. 8(d) may also be used. For example, in the case of melt-printing, the difference in the black area between the maximum threshold value "128" and the next largest threshold value "100" is about halfway between inkjet printing and dye-sublimation printing, and is different from both inkjet printing and dye-sublimation printing, so that this difference can be used as an evaluation index.

[0080] In this embodiment, the degree of approximation of the index value of each of the evaluation indexes A to D to a positive value is used for the judgment, but it is also possible to compare the index value of each of the evaluation indexes A to D with a positive value to judge whether they match or not, and to judge whether the characters are melt-printed or not based on the number of matching indexes. The judgment of whether they match or not can be made, for example, by whether the difference between the index value and the positive value is within a certain range.

[0081] In addition, in this embodiment, the authenticity determination device 3 and the reading device 2 are separate entities, but it is also possible to integrate them by incorporating the authenticity determination device 3 into the reading device 2. In this case, a computer (not shown) inside the reading device 2 may be made to function as the authenticity determination device 3.

[0082] In addition, in this embodiment, authenticity determination is performed as identity verification at the time of various applications, but the application scene or purpose of the authenticity determination of this embodiment is not particularly limited.

[0083] 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]

[0084] 1: Authenticity determination system 2: Reading device 3: Authenticity determination device 10: ID card 100: Thermal transfer printer 301: Discrimination means 302: Authenticity determination method

Claims

1. a discrimination means for binarizing an image of characters printed on the identification card, obtained from an image of the face of the identification card, at each of a plurality of threshold values, and discriminating whether or not the characters have been printed on the basis of the results of the binarization at each threshold value; an authenticity determining means for determining the authenticity of the identification card based on the result of the determination by the determining means; An authenticity determining device comprising:

2. The determining means determines whether or not each of the plurality of characters has been melt-printed, 2. The authenticity determining device according to claim 1, wherein said authenticity determining means determines the authenticity of said identification card by comparing the number of said characters determined to have been melt-printed with a reference value.

3. 3. The authenticity determining device according to claim 1, wherein the characters are numbers.

4. The authenticity determination device according to any one of claims 1 to 3, characterized in that the discrimination means calculates index values ​​for a plurality of evaluation indexes from the results of binarization at each threshold value, and uses the plurality of index values ​​to discriminate whether the characters have been melt-printed.

5. the discrimination means determines a degree of approximation of the index value to a positive value, multiplies the degree of approximation by a weighting coefficient to obtain a score, determines a total score by summing the scores among a plurality of the evaluation indexes, and compares the total score with a predetermined discrimination value to discriminate whether the characters have been melt-printed or not; 5. The authenticity determining device according to claim 4, wherein at least one of the positive value, the coefficient, and the discriminant value varies depending on the character.

6. The authenticity determination device according to claim 4 or claim 5, characterized in that the evaluation index includes the difference between the area of ​​a black dot when binarization is performed using the minimum threshold value at which a black dot is detected, and the area of ​​a black dot when binarization is performed using the next smallest threshold value, when a pixel with a gradation value equal to or less than a threshold value is regarded as a black dot.

7. 7. The authenticity determination device according to claim 4, wherein the evaluation index includes a minimum threshold value at which a black dot is detected when a pixel having a gradation value equal to or less than the threshold value is regarded as a black dot.

8. The authenticity determination device according to any one of claims 4 to 7, characterized in that the evaluation index includes the difference between the area of ​​a black dot when binarization is performed with a minimum threshold value and the area of ​​a black dot when binarization is performed with a maximum threshold value, when a pixel whose gradation value is equal to or less than a threshold value is defined as a black dot.

9. The authenticity determination device according to any one of claims 4 to 8, characterized in that the evaluation index includes the number of consecutive black dots when binarization is performed with the minimum threshold value at which black dots are detected, when pixels with gradation values ​​equal to or less than a threshold value are regarded as black dots.

10. Computer, a discrimination means for binarizing an image of characters printed on the identification card, obtained from an image of the face of the identification card, at each of a plurality of threshold values, and discriminating whether or not the characters have been printed on the basis of the results of the binarization at each threshold value; an authenticity determining means for determining the authenticity of the identification card based on the result of the determination by the determining means; A program for causing the device to function as an authenticity determination device having the above-mentioned features.

Images