JP2023038532A - Authenticity determination apparatus and program - Google Patents

Abstract

To provide an authenticity determination apparatus, or the like, configured to properly determine authenticity of an identification certificate.SOLUTION: An authenticity determination apparatus 3 includes: receiving means 301 which receives a captured image of an ID card from a user terminal 5; and authenticity determination means 302 which determines authenticity of the ID card by comparing a contour part of a character to be inspected that is formed in a predetermined range of the ID card with a contour part of an authentic character, using the captured image of the ID card. The character to be inspected is a character in a pre-printed part of the ID card.SELECTED DRAWING: Figure 4

Description

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

When opening an account at a financial institution, it is necessary to verify the identity of the person using an ID card (personal identification card) such as a driver's license. The number of similar cases is increasing.

In a normal financial institution, it is common for a user to go to the financial institution and submit an ID card, and for the financial institution to use the submitted ID card to verify the identity of the user face-to-face. In this case, the ID card can be carefully observed, and unnaturalness can be detected by the tactile feel of the card.

In addition, Patent Documents 1 and 2 describe an authenticity determination device that determines the authenticity of an ID card from an image obtained by reading the surface of the ID card with a reader such as a scanner. It is also possible to determine the authenticity of an ID card by reading it with a reader.

JP 2011-34535 A JP 2019-117549 A

Recently, financial institutions on the Internet, such as Internet banking, have become commonplace. Some financial institutions of this type perform identity verification by photographing the face of an ID card with a camera of a smartphone or the like and sending the photographed image to the financial institution.

In this case, since the identity verification is performed only by the image rather than face-to-face, it is desired to devise a way to detect forgery. However, it is difficult to detect counterfeiting from the photographed image of the ID card, which has been a problem in online applications.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and an object of the present invention is to provide an authenticity determination device and the like that can suitably determine the authenticity of a personal identification card.

A first invention for solving the above-mentioned problems is an authenticity determination apparatus for an identity verification card, which uses a photographed image of the identity verification card to check an object of inspection formed in a predetermined range of the identity verification card. The authenticity determination device comprises an authenticity determination means for determining the authenticity of the personal identification card by comparing the contour portion of the character with the contour portion of the positive character.

The font of characters to be formed on the personal identification card is predetermined. Therefore, by comparing the outline portion of the character to be inspected formed in a predetermined range of the personal identification card with the outline portion of the positive character to determine authenticity, it is possible to determine whether the character to be inspected is formed in a predetermined font. , and a fake personal identification card in which characters to be inspected are formed in a font other than a predetermined font.

It is desirable that the characters to be inspected are the characters in the pre-printed part of the personal identification card.
As for the characters in the pre-printed portion, since it is predetermined which characters are to be formed in which range, the positive characters to be compared are known in advance, and only a small number of positive data are required.

The predetermined range may be a range in which numbers or alphabets are formed as the on-demand information of the identification card.
As for the on-demand information, the characters formed in the range differ depending on the individual identity card. However, as on-demand information, there are ranges that consist only of numbers from 0 to 9, such as dates of birth, and ranges that consist only of alphabets, such as A to Z. , requiring relatively few positive data.

The authenticity determination means calculates a vector from the origin to the contour pixels in the character region image of the positive character, and calculates the correspondence beyond the vector starting from the origin in the character region image of the character to be inspected. A pixel is detected, and if the corresponding pixel is not a contour pixel, a positional difference between the detected contour pixel and the corresponding pixel is calculated as a difference vector by searching pixels in a range outside the corresponding pixel, and the difference vector is calculated. It is desirable to determine the authenticity of the personal identification card using a vector-based determination value.
Thereby, the difference between the outline portion of the character to be inspected and the outline portion of the positive character can be appropriately evaluated by the difference vector, and the authenticity determination can be preferably performed.

The contour pixels of the character to be inspected are those pixels in a binary image in which the character has a first gradation value and the background has a second gradation value, and the pixel of interest has the first gradation value and the pixels surrounding the pixel of interest are If not all of the eight pixels have the first gradation value, the target pixel is set to the second gradation value. Otherwise, the target pixel is set to the first gradation value. The contour pixels of a positive character are obtained as pixels of a gradation value, and a pixel of interest has a first gradation value in a binary image in which the character has a first gradation value and the background has a second gradation value. and four pixels above, below, to the left, and to the right of the pixel of interest do not all have the first gradation value, the pixel of interest is assigned the second gradation value; otherwise, the pixel of interest is assigned the first gradation value. It is also desirable to obtain the pixel with the second gradation value by performing the processing to obtain the second gradation value.
Since the above-described difference vector calculation method searches for pixels in the character region to be inspected that correspond to positive character contour pixels, the number of pixel searches corresponds to the number of positive character contour pixels, If the number of contour pixels of the character to be inspected is large, one search will be completed early. Therefore, as described above, by reducing the outline pixels of the positive character according to a strict criterion and increasing the outline pixels of the character to be inspected according to a loose criterion, the authentication can be performed at high speed, and the true identity can be verified. It is possible to suppress erroneously judging the certificate as false.

It is preferable that the authenticity determination device has a receiving means for receiving the photographed image from the user terminal.
As a result, it is possible to construct an authenticity determination system that uses an authenticity determination device to determine the authenticity of a photographed image of a personal identification card transmitted from a user terminal, using a network.

A second aspect of the present invention is an apparatus for determining authenticity of a personal identification card, wherein a contour portion of a character to be inspected is formed in a predetermined range of the personal identification card by using a photographed image of the personal identification card. is a program for functioning as an authenticity judging device having authenticity judging means for judging the authenticity of the personal identification card by comparing with the outline portion of positive characters.

INDUSTRIAL APPLICABILITY According to the present invention, it is possible to provide an authenticity determination device or the like capable of suitably performing authenticity determination of a personal identification card.

The figure which shows the authenticity determination system 1. FIG. 2 is a diagram showing the hardware configuration of an authenticity determination device 3; FIG. 4 is a diagram showing the hardware configuration of a user terminal 5; FIG. 3 is a block diagram showing functions of an authenticity determination device 3; FIG. The figure which shows the ID card 10. FIG. 4 is a flowchart showing an outline of processing of the authenticity determination system 1; An example of a photographed screen of the ID card 10. FIG. 4 is a flowchart showing an authenticity determination method; FIG. 10 is a diagram for explaining extraction of a character range 200; FIG. FIG. 4 is a diagram for explaining how to create a character image 300; FIG. 3 is a diagram for explaining binarization of a character image 300; 4A and 4B are diagrams for explaining notch deletion of a binary image 400; FIG. FIG. 5 is a diagram for explaining creation of an inspection image 500; FIG. 4 is a diagram for explaining calculation of a difference vector Vec; The figure explaining correction|amendment of vector v. FIG. 4 is a flow chart showing a procedure for authenticity determination. FIG. 4 is a diagram for explaining reflection of a hologram;

Preferred embodiments of the present invention will be described in detail below with reference to the drawings.

(1. Authenticity determination system 1)
FIG. 1 is a diagram showing an authenticity determination system 1 having an authenticity determination device 3 according to an embodiment of the present invention. The authentication system 1 is configured by connecting an authentication device 3 and a user terminal 5 via a network so as to be communicable. In the authentication system 1, a photographed image of a user's ID card 10 is transmitted from the user terminal 5 to the authentication device 3, and the authentication device 3 judges the authenticity of the ID card 10 from the photographed image.

FIG. 2 is a diagram showing the hardware configuration of the authentication device 3. As shown in FIG. The authenticity determination device 3 can be implemented by a computer configured by connecting the control unit 31, the storage unit 32, the communication unit 33, and the like via a bus or the like. However, the present invention is not limited to this, and various configurations can be appropriately adopted, and the authenticity determination device 3 can be realized by a plurality of computers.

The control unit 31 is composed of a CPU, ROM, RAM, and the like. The CPU calls a program related to processing of the authenticity determination device 3 stored in a storage medium such as the storage unit 32 or ROM to a work area on the RAM and executes the program. ROM is a non-volatile memory that permanently holds programs such as boot programs and BIOS, data, and so on. The RAM is a volatile memory that temporarily holds programs and data loaded from the storage unit 32, ROM, etc., and has a work area that the control unit 31 uses to perform various processes.

The storage unit 32 is a hard disk drive, a solid state drive, a flash memory, or the like, and stores programs executed by the authenticity determination device 3 in the process described later, data necessary for executing the programs, an OS, and the like.

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

A user terminal 5 is a terminal possessed by a user, which photographs 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 smart phone or a tablet terminal is used.

FIG. 3 is a diagram showing the hardware configuration of the user terminal 5. As shown in FIG. 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. be. However, it is not limited to this, and various configurations can be appropriately adopted.

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

The camera 56 is an area camera including an optical lens, an imaging device such as a CCD (Charge Coupled Device) or CMOS (Complementary Metal-Oxide Semiconductor), an A/D (Analog/Digital) converter, and the like. The camera 56 photoelectrically converts a subject image input through an optical lens using an imaging device to generate an analog image signal. Then, the A/D converter converts the analog image signal into digital image data.

FIG. 4 is a block diagram showing functions of the authentication device 3. As shown in FIG. The authenticity determination device 3 has a receiving means 301, an authenticity determination means 302, and the like.

In the receiving means 301 , the control section 31 of the authentication device 3 receives the photographed image of the ID card 10 from the user terminal 5 via the communication section 33 .

The authenticity determination means 302 determines the authenticity of the ID card 10 using the photographed image of the ID card 10 received from the user terminal 5 by the control unit 31 of the authentication device 3 . The details of this authenticity determination will be described later.

(2. ID card 10)
The ID card 10 is a personal identification card to be authenticated in this embodiment. A personal identification card is a medium used for personal identification by financial institutions, mobile phone carriers, various administrative agencies, etc. Examples include residence cards, driver's licenses, My Number cards, and special permanent resident cards. In this embodiment, a hologram is formed on the ID card 10 as a measure against counterfeiting, but the present invention is not limited to this.

FIG. 5 is a diagram showing an outline of the ID card 10 (residence card), and is a schematic illustration of the face information of the ID card 10 partially omitted.

Various face information is formed on the ID card 10 by printing. Examples of card face information include presence/absence 16, card issuance date 17, expiration date 18, and the like.

Of these, residence number 12, date of birth 13, face image 14, status of residence 15, employment restrictions 16, date of issuance 17, expiration date 18, etc. are on-demand information that differs depending on the individual ID card 10.

On the other hand, “Number”, “Date of Birth”, “Status of Residence”, and “Work Restrictions” indicate the entry fields for Residence Number 12, Date of Birth 13, Status of Residence 15, Work Restrictions 16, Date of Issuance 17, and Expiration Date 18. Characters such as "presence or absence of a card", "issuance date", "this card is...", the card issuing country 11, the name of the ID card 10 ("residence card"), etc. are commonly used for each ID card 10. These characters are pre-formed in fixed locations on the card substrate prior to printing the on-demand information and are referred to as pre-printed portions.

The ID card 10 is manufactured by printing the above-described on-demand information on a card base material on which the above-described pre-printed portion is formed in advance. The configuration of the on-demand information and the pre-printed portion differs depending on the type of ID card 10, such as a residence card, driver's license, my number card, special permanent resident card, and the like.

(3. Outline of processing of authenticity determination system 1)
FIG. 6 is a flow chart showing an outline of the processing executed by the authenticity determination system 1. As shown in FIG. S1 to S2 and S7 to S8 in FIG. 6 are processes executed by the control unit 51 of the user terminal 5 by controlling each unit of the user terminal 5. 3 is executed by controlling each part.

In this embodiment, the user first operates the user terminal 5 to launch a dedicated application program stored in advance in the storage unit 52 . Then, the user terminal 5 displays a menu screen (not shown) on the display unit 53, activates the camera 56 according to the user's selection on the menu screen, and photographs the face of the ID card 10 (S1).

FIG. 7 shows an example of the photographed screen of the ID card 10 at this time. In this embodiment, an instruction is displayed on the display unit 53 of the user terminal 5 when the camera is activated, and the ID card 10 is photographed by prompting the user to fit the ID card 10 within a predetermined frame 531 .

After photographing the ID card 10, the user terminal 5 transmits the photographed image to the authentication device 3 (S2). The photographed image is an RGB image in which the color of the pixels is determined by the gradation values of the R (red), G (green), and B (blue) components. Upon receiving the photographed image of the ID card 10 (S3), the authentication device 3 judges the authenticity of the ID card 10 using the photographed image (S4).

Authenticity determination in this embodiment is performed based on the use of a predetermined font for characters on the face of the genuine ID card 10 . The details of the authenticity determination method will be described later.

When the authenticity determination device 3 determines that the ID card 10 is not authentic (S5; NO), it transmits to the user terminal 5 that the ID card 10 is not authentic (S6). When the user terminal 5 receives the fact that the ID card 10 is not true (S7), it displays this on the display unit 53 (S8) and terminates the process.

On the other hand, when the authenticity determination device 3 determines that the ID card 10 is true (S5; YES), the authentication determination process is completed. For example, when performing the above authenticity determination as identity verification when opening an account at a financial institution on the Internet, after the authenticity determination process, the user information on the face of the ID card 10 (name, date of birth, etc.) etc.) can be acquired from the photographed image of the ID card 10 and registered, and the user information can be stored in the storage unit 52 .

(3-1. Authenticity determination based on character shape)
As described above, in the present embodiment, based on the use of a predetermined font for the characters on the face of the authentic ID card 10, the authenticity determination in S4 (see FIG. 6) is performed from the shape of the characters.

That is, the pre-printed portion of the ID card 10 and the characters of the on-demand information are formed in a predetermined range in a predetermined font. Therefore, by comparing the characters in a predetermined range extracted from the photographed image of the ID card 10 and the positive characters used in the predetermined range on the true ID card 10 in terms of shape, the positive ID card 10 and can discriminate fake ID cards 10 using different fonts.

FIG. 8 is a flow chart showing the procedure of the authentication method in S4 (see FIG. 6).

In this embodiment, in S4, first, a predetermined range of the photographed image (RGB image) of the ID card 10 is grayscale-converted to create a grayscale image. In addition, the B and R components are extracted from a predetermined range of the captured image, and an image based on the gradation values of the B component (hereinafter referred to as the B image) and an image based on the gradation values of the R component (hereinafter referred to as the R image) are created. (S401). The predetermined range can be set in advance as a range in which characters to be inspected exist, and in this embodiment, it is a range in which the characters of the pre-printed portion are formed.

Next, the authenticity determination device 3 binarizes the grayscale image (S402). A grayscale image is an image in which the brightness of pixels is represented by a gradation value of 0 to 255, where a gradation value of 0 is black and a gradation value of 255 is white. Also, the binary image is an image in which the text portion is black pixels (pixels with the first gradation value) and the background portion is white pixels (pixels with the second gradation value). This also applies to other binary images, which will be described later. However, the specifications of the grayscale image and the expression of the binary image are not limited to the above.

Next, the authenticity determination device 3 cuts out a range of characters to be inspected (referred to as a character range) from the binarized image (S403).

The extraction method is not particularly limited, but in this embodiment, first, as shown in FIG. 9A, columns 101 and rows 102 in which black pixels exist in a binarized image 100 are detected. Then, as shown in FIG. 9(b), a region where a predetermined number or more of columns 101 in which black pixels exist is continuous at a position near the center of the image 100 is defined as 101a, and a row 102 in which black pixels exist is defined as 101a. A region 102a is defined as a region that continues for a predetermined number or more at a position near the center of the region, and a range 100a consisting of the regions 101a and 102a is extracted.

The authenticity determination device 3 performs the processes shown in FIGS. 9A and 9B on the extracted range 100a as necessary, and transforms the finally extracted range 200 into a character range as shown in FIG. 9C. and Although the above predetermined number is, for example, 10 dots, it is not limited to this. FIG. 10(a) is an example in which the characters to be inspected are the characters of the pre-printed part of the ID card 10, and the character range 200 of the character "Tome" is cut out by the processing of S402 and S403.

As shown in FIG. 10B, the authenticity determination device 3 adjusts the resolution (dpi) of the original grayscale image 20 from which the character range 200 has been cut out so that the character range 200 has a predetermined size. (S404).

In this embodiment, a plurality of vertical and horizontal dot numbers (three, 89, 90, and 91 in this embodiment) are set as the predetermined size, and a plurality of gray scales converted so that the character range 200 has these sizes. Processing of S405 to S410, which will be described later, is performed on the scale image 20'. This is to reduce the influence of noise in the captured image and improve the determination accuracy. However, the predetermined size may be one, and the specific size is not particularly limited. The magnification at the time of resolution conversion is a magnification that combines the above number of dots with the number of dots in the vertical and horizontal directions of the character range 200 of the original grayscale image 20, whichever is larger. can be done.

Next, the authenticity determination device 3 cuts out the character to be inspected again from the grayscale image 20' to create a character image (S405). Here, as shown in FIG. 10(c), the range of the character image 300 is set to a size larger than the predetermined size (for example, 104 in length and width) such that the center C coincides with the center of the character range 200 in the grayscale image 20'. dot), but is not limited to this.

Next, the authenticity determination device 3 performs noise removal processing on the character image 300 (S406). In this embodiment, low-pass filter processing and expansion/contraction processing are performed as noise removal processing, thereby removing high-frequency gradation value changes (noise).

In this embodiment, in S406, the character image 300 is first subjected to low-pass filter processing. Low-pass filter processing is known, but in this embodiment, for example, as shown in the following equation (1), the gradation value pn of each pixel in a certain range centered on the target pixel of the character image 300 is A coefficient kn (weighting coefficient) corresponding to the position is multiplied to calculate the sum Σ(pn×kn), and this sum Σ(pn×kn) is divided by the sum Σkn of the coefficients kn to obtain the gradation value p0′ of the pixel of interest. , is performed with each pixel of the character image 300 as the target pixel.
p0'=Σ(pn×kn)/Σkn...(1)

However, in the present embodiment, the above sums Σ(pn×kn) and Σkn are calculated by calculating the difference between the gradation value pn and the original gradation value p0 of the target pixel, among the pixels within the above fixed range, less than a predetermined value. is calculated for a pixel where When calculating the sums Σ(pn×kn) and Σkn, by ignoring pixels with a large difference in gradation value from the pixel of interest, low-pass filtering can be performed so that edges around characters are not blurred. The predetermined value is set to 30, for example, but is not limited to this.

In S406, expansion/contraction processing of the character portion is further performed on the character image 300 after the low-pass filter processing. The expansion/contraction process is known, but in this embodiment, for example, the process of replacing the gradation value of the pixel of interest with the largest value among the gradation values of pixels in a certain range centering on the pixel of interest is performed on the character image 300. is used as a pixel of interest. After the character portion is shrunk in this way, the process of replacing the gradation value of the pixel of interest with the smallest value among the gradation values of the pixels in a certain range centering on the pixel of interest is performed in the reverse of the above. Each pixel of 300 is treated as a pixel of interest. By expanding the contracted character portion in this way, the outline of the character portion is shaped and noise is reduced.

Finally, trimming the character image 300 is performed, and the process of S406 ends. The portion to be removed by trimming is a portion having a predetermined width on the outer edge of the character image 300, and the width is determined according to the size of each fixed range set in the process of S407.

Thereafter, the authenticity determination device 3 performs binarization processing of the character image 300 (S407).

In the present embodiment, a positive binary image of a character to be inspected (“tome” in the present embodiment) is registered in advance in the storage unit 32 of the authenticity determination device 3 as positive data used for authenticity determination. In S407, the threshold for binarization is determined by comparison with positive data in order to perform optimal binarization after comparison with positive data.

More specifically, first, for the character image 300, a histogram indicating the number of pixels for each tone value is created. Then, as shown in FIG. 11A, the interval between the minimum value and the maximum value of the gradation value V appearing in the character image 300 is equally divided, and the divided value Dn and the center value Cn of each divided interval D are set. There are various setting methods, but in this example, the minimum gradation value V in the division section D is the division value Dn, and the maximum value of the division value Dn is the maximum gradation value V appearing in the character image 300. 1 greater than the value. Also, the central value Cn can be calculated by averaging the upper and lower divided values Dn. Although the number of divided sections D is actually about 16, the number is set to 3 in the example of FIG. 11 for explanation.

Next, for each divided section D, using each gradation value V in the divided section D and the number of pixels S of each gradation value V, the centroid value Mn is calculated by the following equation (2). Then, as shown in FIG. 11(b), a new division value Dn is calculated by averaging the center-of-gravity values Mn of the upper and lower division sections D. ) are updated.
Mn=Σ(V・S)/ΣS…(2)

Then, as shown in FIG. 11(c), a new central value Cn is calculated in the same manner as described above using the updated new division value Dn, and the central value Cn is updated accordingly. The processing of FIGS. 11A to 11C is repeated until there is no difference between the new center value Cn and the center value Cn before updating, and the division value Dn at the end of the processing (excluding the minimum value of the division value Dn) ) as the threshold. This provides multiple thresholds. Note that each value other than the center of gravity value Mn is an integer value, and in the above process, the calculated value is rounded off to an integer if necessary.

The authenticity determination device 3 binarizes the character image 300 with each threshold value, compares the number of black pixels at that time with the number of black pixels of the positive data, and selects the threshold value with the smallest difference as the final value. Threshold. In S407, by binarizing the character image 300 using this threshold value, optimal binarization can be performed in comparison with positive data.

FIG. 12(a) is an example of the binary image 400 obtained in the process of S407, and the authenticity determination device 3 performs notch deletion processing on this binary image 400 (S408).

The notch to be deleted is a fine (for example, 1-dot unit) unevenness. In this embodiment, as shown in FIG. When a pattern is detected, a process of replacing the pattern with a pattern having no notch is performed using each pixel of the binary image 400 as a pixel of interest. Patterns with notches and patterns without notches correspond one-to-one, and a plurality of white pixel notches and black pixel notches other than the example in FIG. 12B are prepared.

In the present embodiment, the binary image 400 subjected to the above replacement processing is subjected to the same replacement processing again as necessary. As a result, it is possible to reliably remove fine irregularities present in the binary image 400 and improve the accuracy of authenticity determination.

Next, the authentication device 3 creates an inspection image by performing character contour extraction processing on the binary image 400 after notch deletion (S409).

In the present embodiment, as shown in FIG. 13A, for a pixel of interest in a binary image 400, the pixel of interest is black (first gradation value) and at least one of the eight pixels surrounding the pixel of interest is In the case of white (second gradation value), the pixel of interest is set to white, and in the other cases, the pixel of interest is set to black. As a result, an inspection image 500 is created in which outline pixels of characters are shown in white, as shown in FIG. 13(b).

On the other hand, in the present embodiment, as shown in FIG. 13C, the same contour extraction processing is performed on positive data to obtain a positive contour image. However, the conditions for outline extraction are different from the above. For a target pixel of positive data (binary image), the target pixel is black (first gradation value) and four pixels above, below, left and right of the target pixel are is white (second gradation value), the pixel of interest is white; otherwise, the pixel of interest is black. As a result, as shown in FIG. 13(d), a positive outline image R in which the outline pixels of the character are shown in white is also created for the positive data.

As can be seen from the comparison between FIGS. 13(a) and 13(c), the condition for extracting the contour is that only the four pixels above, below, to the left and right of the pixel of interest are searched for white pixels. The positive contour image R has fewer contour pixels than the inspection image 500.

The authenticity determination device 3 then compares the contour portion of the inspection image 500 with the contour portion of the positive contour image R, and calculates a determination value used for authenticity determination based on the difference between these contour portions (S410). .

In this embodiment, first, as shown in FIG. 14A, rectangular regions circumscribing contour pixels are extracted as character regions t and r for each of the inspection image 500 and the positive contour image R. FIG. The character regions t and r are the horizontal range between the leftmost contour pixel and the rightmost contour pixel in the image (inspection image 500, positive contour image R). The vertical range is between the contour pixel located at the bottom and the contour pixel located at the bottom.

As shown in FIG. 14(b), the authenticity determination device 3 extracts a vector v (xr, yr) Ask for Then, as shown in FIG. 14(c), a corresponding pixel 502 ahead of the vector v whose starting point is the origin 501 (Xt0, Yt0) of the character region t of the inspection image 500 is detected.

If the corresponding pixel 502 is not a contour pixel, pixels are sequentially searched outward from the vicinity of the corresponding pixel 502 in a certain range (hereinafter sometimes referred to as a search range) of the character region t centered on the corresponding pixel 502 . A specific search order is not particularly limited. Then, the positional difference between the contour pixel detected first and the corresponding pixel 502 is recorded in the storage unit 32 as a difference vector Vec(x,y). If the corresponding pixel 502 is a contour pixel, (0,0) is recorded as the difference vector Vec(x,y). The origin о (Xr0, Yr0) and the origin 501 (Xt0, Yt0) are assumed to be the upper left pixels of the character regions r and t, respectively, but the invention is not limited to this.

The authenticity determination device 3 calculates the difference vector Vec(x, y) for each contour pixel of the character region r of the positive contour image R by the above procedure, obtains the sum ΣVec(x, y), and obtains Vec(x , y) is calculated by the following equation (3). N is the total number of difference vectors Vec, ie, the number of contour pixels in the character region r.
avgVec(x,y)=(1/N)ΣVec(x,y) (3)

If the absolute values of both x and y elements of avgVec are less than 0.5, the authenticity determination device 3 terminates the process, and sets the average value of the length of the difference vector Vec(x, y) when obtaining the avgVec to 100 The result obtained by multiplying by is set as the determination value Result, and the determination value Result is calculated by the following formula (4).
Result=(100/N)Σ(Vec(x) ² +Vec(y) ² ) ^1/2 … (4)

On the other hand, when the absolute value of either or both of the elements x and y of avgVec is 0.5 or more, the authenticity determination device 3 sets the origin 501 of the inspection image 500 to avgVec(x, y) is corrected (offset) by the vector IntavgVec(x, y) obtained by rounding off each element x, y, and using the above procedure, a difference vector Calculate Vec(x,y) again. Then, the determination value Result is calculated from these difference vectors Vec(x, y) according to Equation (4). Although the average value of the lengths of the difference vectors Vec(x,y) is multiplied by 100 in Equation (4), a value that is not multiplied by 100 can also be used as the determination value Result.

The processing of S405 to S410 is performed on the three grayscale images 20' (see FIG. 10B) obtained by the resolution conversion of S404, and the authenticity determination device 3 determines the determination value obtained for each grayscale image 20'. The smallest value of Result is determined as the final determination value, and authenticity determination is performed using the determination value Result (S411). A procedure for determining authenticity will be described later.

The basic procedure for calculating the determination value Result is as described above. It is also desirable to correct the position (Xt0, Yt0) of 501 .

For example, for correction of vector v, the difference in size between both character regions r and t is calculated as horizontal magnification magX and vertical magnification magY using the following equations (5) and (6). The one closer to 1 is obtained as the comparison magnification mag.
magX=(horizontal size of character area t)/(horizontal size of character area r) (5)
magY=(Vertical size of character area t)/(Vertical size of character area r) (6)

Then, as shown in FIG. 15, a vector v(xr, yr) used for detecting the corresponding pixel 502 in the character region t of the inspection image 500 is obtained by multiplying each element xr, yr by the comparison magnification mag.・Correct as mag. Each element (xr.mag, yr.mag) of the vector v.mag is rounded to an integer. The position of the origin 501 of the character region t in the inspection image 500 can also be corrected in consideration of the comparison magnification mag. or away from the center of the character region t.

In addition, regarding the search for pixels in the character region t (see FIG. 14C), the number of detections (the number of times the difference vector Vec is calculated) is recorded for each contour pixel in the character region t. At the time of searching, the detection condition may be that the pixel to be searched is a contour pixel and that the number of times the pixel is detected is equal to or less than a predetermined value. For example, if the above predetermined value is 2, a pixel with a detection count of 3 or more is not detected as a target for calculation of the difference vector Vec even if it is a contour pixel, and the next pixel is searched according to the search order. .

If the contour pixels for which the difference vector Vec is to be calculated cannot be detected even after the entire search range has been searched, the difference vector Vec(x, y), for example, is It can be recorded as (8, 8) for even times and (-8, -8) for odd times, including search times. In this way, by recording the values of the same absolute value and the opposite sign according to whether they are even or odd, it is possible to reduce the influence when calculating the sum ΣVec(x, y) of the difference vectors Vec. Note that the absolute value can be determined in consideration of the size of the search range, etc., and is not limited to 8 as described above. Also, the size, shape, etc. of the search range are not limited. For example, regarding the shape, the search range may be a square range or a circular range.

(3-2. Authenticity determination procedure using determination value Result)
As described above, in S411 (see FIG. 8), authenticity determination is performed using the determination value Result. This determination value Result is finally obtained from the grayscale image 20 created in S401. The procedure is described below.

FIG. 16 is a flow chart showing the authenticity determination procedure in S411. In this embodiment, the judgment value Resut is compared with a predetermined reference value, and if the judgment value Result is smaller than the reference value (S4110; YES), the ID card 10 is determined to be true (S4111). The reference value can be appropriately determined in consideration of determination accuracy and the like.

On the other hand, if the judgment value Resut is greater than or equal to the reference value (S4110; NO), the ID card 10 is not judged true. However, in the present embodiment, as shown in FIG. 17, the character of the binary image 400 is greatly missing due to the reflection of the hologram in the photographed image of the ID card 10, and the judgment value Result may be miscalculated. If the value Result is equal to or greater than the predetermined value (S4112; YES), the processing of S402 to S410 is performed for the B image to calculate the determination value Result (S4113).

This is different from the grayscale image 20 obtained by converting the RGB components of the photographed image of the ID card 10 into grayscale. This is because the color of the hologram may not appear and the characters may be less affected. For example, if the color of the hologram in the captured image is red, the characters will be less affected when viewing the B component of the captured image. The above constant value is set to a value larger than the reference value, and a specific value can be appropriately determined in consideration of determination accuracy and the like.

If the judgment value Result obtained in S4113 is not equal to or greater than the predetermined value (S4114; NO), the authentication device 3 compares the judgment value Result with a predetermined reference value, and if the judgment value Result is smaller than the reference value (S4115; YES), the ID card 10 is made true (S4116).

If the determination value Result is smaller than a certain value in S4112 (S4112; NO) and if the determination value Result is greater than or equal to the reference value in S4115 (S4115; NO), the ID card 10 is false (S4117).

On the other hand, if the determination value Result is equal to or greater than the predetermined value in S4114 (S4114; YES), the processing of S402 to S410 is further performed for the R image to calculate the determination value Result (S4118), and the grayscale image 20 and the B image are calculated. , and R image, the smallest value is determined as the final determination value (S4119).

When the judgment value Result is smaller than the reference value (S4115; YES), the ID card 10 is made true (S4116), and when the judgment value Result is equal to or greater than the reference value (S4115; NO), the ID card 10 is made false. (S4117).

As described above, in this embodiment, by utilizing the fact that the font of characters formed on the ID card 10 is predetermined, the outline portion of the character to be inspected formed in a predetermined range of the ID card 10 is By performing authenticity determination by comparing with the contour portion of the positive character, the true ID card 10 in which the characters to be inspected are formed in a predetermined font and the characters to be inspected are formed in a font other than the predetermined font. A fake ID card 10 can be suitably discriminated. The authenticity determination method of the present embodiment is particularly effective for the ID card 10 that is difficult to copy simply because counterfeiting prevention measures such as holograms are taken. A fake ID card 10 can be suitably discriminated.

In this embodiment, the characters to be inspected are the characters in the pre-printed portion. As for the characters in the pre-printed portion, since it is predetermined which characters are to be formed in which range, the positive characters to be compared are known in advance, and only a small number of positive data are required. Further, by comparing the shapes, it is possible to detect as a fake ID card 10 not only when the font is different, but also when the characters themselves are different.

In addition, in this embodiment, the difference between the outline portion of the character to be inspected and the outline portion of the positive character is appropriately evaluated using the difference vector Vec calculated by the method described with reference to FIG. be able to.

Here, since the calculation method of the difference vector Vec explained in FIG. , and if the number of contour pixels of the character to be inspected is large, one search is completed early. Therefore, as described with reference to FIG. 13 and the like, the number of contour pixels of positive characters is reduced according to a strict criterion, while the number of contour pixels of characters to be inspected is increased according to a loose criterion. It is possible to suppress erroneous determination of a true ID card 10 as false.

However, the present invention is not limited to those described in the above embodiments. For example, in the present embodiment, authenticity determination is performed as personal identification when opening an account, but the application scene or application purpose of the authenticity determination of the present embodiment is not particularly limited.

In this embodiment, the characters to be inspected are the characters of the pre-printed portion, but they may be the characters of the on-demand information. In this case, after performing known OCR (Optical Character Recognition) processing on a predetermined range of a photographed image including characters to be inspected to recognize the characters, positive data corresponding to the characters are used for authenticity determination.

However, regarding the on-demand information, since the characters formed in the predetermined range of the photographed image differ depending on the individual ID card 10, the amount of positive data to be prepared increases. However, as on-demand information, there are ranges in which only numbers 0 to 9 such as date of birth are formed, and ranges in which only alphabets A to Z are formed. , requiring relatively few positive data.

Further, in this embodiment, when binarizing the character image 300 in S407 (see FIG. 8), the number of black pixels at the time of binarization is compared with the number of black pixels of positive data to obtain a plurality of threshold values. Each binary image was binarized using all thresholds or a plurality of thresholds in which the number of black pixels at the time of binarization is close to the number of black pixels of positive data. , the decision value Result may be calculated according to the formula (4) according to the procedure described above, and the smallest decision value Result may be determined as the final threshold value.

In this embodiment, only one character is inspected, but a plurality of characters are inspected. A final determination that the ID card 10 is true may be made if a predetermined number or more of the characters are true.

Although the preferred embodiments of the present invention have been described above with reference to the accompanying drawings, the present invention is not limited to such examples. It is obvious that a person skilled in the art can conceive of various modifications or modifications within the scope of the technical ideas disclosed in the present application, and these also belong to the technical scope of the present invention. Understood.

1: Authenticity determination system 3: Authenticity determination device 5: User terminal 10: ID card 301: Receiving means 302: Authenticity determination means

Claims (7)

A personal identification certificate authenticity determination device,
Using a photographed image of the personal identification card, the contour portion of the character to be inspected formed in a predetermined range of the personal identification card is compared with the contour portion of the positive character to verify the authenticity of the personal identification card. An authenticity determination device comprising an authenticity determination means for performing determination. 2. The authenticity determination apparatus according to claim 1, wherein the characters to be inspected are characters of a pre-printed portion of said personal identification card. 2. The authenticity determination apparatus according to claim 1, wherein the predetermined range is a range in which numbers or alphabets are formed as the on-demand information of the personal identification card. The authenticity determination means is
Calculate a vector from the origin to the contour pixel in the image of the character area of the positive character,
Detecting a corresponding pixel ahead of the vector starting from the origin in an image of the character area of the character to be inspected,
if the corresponding pixel is not a contour pixel, calculating as a difference vector a positional difference between the contour pixel detected by searching for pixels outside the corresponding pixel and the corresponding pixel;
4. The authenticity determination device according to any one of claims 1 to 3, wherein the authenticity determination of the identification card is performed based on the determination value based on the difference vector. The contour pixels of the character to be examined are
In a binary image in which the character has the first gradation value and the background has the second gradation value, the pixel of interest has the first gradation value and at least one of the eight pixels surrounding the pixel of interest has the second gradation value. If the gradation value of obtained,
The contour pixels of a positive character are
In a binary image in which the character has the first gradation value and the background has the second gradation value, the pixel of interest has the first gradation value and at least one of the four pixels above, below, to the left and right of the pixel of interest has If it is the second gradation value, the target pixel is set to the second gradation value, otherwise, the target pixel is set to the first gradation value, thereby obtaining the second gradation value. 5. The authenticity determination device according to claim 4, wherein the information is obtained as pixels. 6. The authenticity determination device according to any one of claims 1 to 5, further comprising receiving means for receiving the photographed image from a user terminal. the computer,
A personal identification certificate authenticity determination device,
Using a photographed image of the personal identification card, the contour portion of the character to be inspected formed in a predetermined range of the personal identification card is compared with the contour portion of the positive character to verify the authenticity of the personal identification card. A program for functioning as an authenticity judging device having authenticity judging means for judging.

Images