JPS58201181A - Seal impression collating method - Google Patents

Abstract

PURPOSE:To simplify processing and improve precision by regarding points where a contour line changes abruptly as singular points, calculating distances between singular points of a seal impression to be collated and a reference seal impression with regard to only singular points distributed at the circumference of the seal impression, and discriminates whether the seal impression is true. CONSTITUTION:A reader 50 which reads a code number printed on a check 1 and a camera device 3 which takes a picture of a seal impression on the check 1 are provided in the middle of a conveyance path for the check. The camera device 3 takes a picture of the seal impression to be collated and its binary- coded signal to a picture processor 4. The picture processor 4 regards the points where the contour line changes abruptly as singular points and collates couples of singular points of the objective seal impression and reference seal impression. In this case, distances between singular points are calculated with regard to only singular points distributed at the circumference, and the calculated data are used as truth/falsehook discriminati on dataon the seal impression.

Description

Detailed Description of the Invention The present invention reads the impression of a seal stamped on a check, etc., converts it into an image, compares this with an image of a reference seal imprint stored in a memory in advance, and determines the authenticity of the used seal based on the degree of matching. This relates to a seal verification method for identifying fakes.

The conventional method of matching this type of seal stamp involves comparing the entire constituent strokes of each image of the stamp to be compared and the reference stamp, which makes the process of matching the data of both images extremely complicated, and the data used for data matching is extremely complicated. There were disadvantages such as increased memory capacity.

Therefore, the inventor extracted the point where the outline changes sharply from each image of the reference seal impression and the matched seal impression as a singular point, and after selecting multiple pairs of singular points in corresponding parts between both seal impressions, We have developed a method to determine the authenticity of a used seal by calculating the distance between each singular point and comparing the total value of each calculated data with a predetermined reference value.

According to this method, it is sufficient to compare data only for multiple pairs of corresponding singular points, which greatly simplifies the matching process. In addition, it has the advantage of being able to set a small memory capacity for data matching. It was done.

However, since this method also calculates the distance between singular points for all pairs of singular points, there is room for further improvement from the perspective of simplifying the matching process.

Therefore, the inventor compared and studied the impressions of fake seals and those of genuine seals, and found that, as shown in Fig. 11, the two seals are generally similar near the center, but in the periphery. It was found that the degree of agreement was poor and there was a large discrepancy between the two seal impressions.

The present invention focuses on the characteristics of such counterfeit seal impressions, and when comparing pairs of singular points in the verified seal impression and the reference seal impression, the distance between the singular points distributed in the central part of the seal impression is determined. By omitting the calculation and calculating the distance between singular points only for the singular points distributed in the surrounding area,
We decided to use the calculated data as data for determining authenticity of seals.

According to the present invention, it is possible to omit the distance calculation for the singular points distributed in the central part of the seal impression, so compared to the above-mentioned methods, the verification process can be further simplified, the verification time can be shortened, and the discrimination accuracy can also be reduced. There is no risk of it happening. In addition, since the distance calculation data used for authenticity determination can be reduced, memory capacity can be saved accordingly, and many other excellent effects can be achieved.

The present invention will be specifically described below based on embodiments shown in the drawings.

FIG. 1 shows an example of a device for determining whether a stamp stamped on a check is a genuine stamp or a counterfeit stamp.

The illustrated device stores a plurality of checks 1 into a box-like case 10.
The checks located at the bottom of the case 10 are taken out one by one and sent onto the conveyor belt 11.

During the transportation of each check 1, the stamp imprinted on the check is checked, and the device 2 installed at the downstream position of the transportation path determines whether the check has a genuine stamp or a counterfeit stamp based on the results. The checks are divided into three types: used checks and unidentifiable checks, and collection cases 21. ．． 2
Send it to 2゜23.

In the middle of the conveyance path, there is a reading device 5 that reads the code number printed on the check 1 using an optical or magnetic method.
0 and a camera device 3 that images the seal imprinted on the check 1, the output of the reading device 50 is sent to the external memory 5, and the output of the camera device 3 is sent to the image processor 4 via a data bus. 40. A plurality of reference seal impressions are data stored in the external memory 5, and based on the code number read by the reading device 50, image data of the corresponding reference seal impression is extracted and sent to the image processor 4.

The camera device 3 includes a reading line sensor 31 and a binarization circuit 32, as shown in FIG. An optical signal corresponding to the configuration of an image is extracted, and this optical signal is photoelectrically converted to output an analog image signal il. Further, the binarization circuit 32 binarizes the image signal and sends the binarized signal 12 to the image processor 4 via the data bus 40 in bit serial form corresponding to columns. In the figure, an oscillator 33 supplies a read pulse to the read line sensor 31 and also supplies a clock pulse to an X-axis coordinate counter 34 (column counter) for calculating the point coordinates of the current signal. Furthermore, this X-axis coordinate counter 34
A carry signal i3 is output from , and this carry signal i3
is supplied to a Y-axis coordinate counter 35 (row counter) for calculating the Y-axis coordinate, and each output of these X-axis coordinate counter 34 and Y-axis coordinate counter 35 is connected to a data bus 40.
The image is input to the image processor 4 via the image processor 4.

The image processor 4 includes a program memory 41 that stores various programs necessary for checking seal impressions and determining authenticity, in addition to programs such as the singular point selection program shown in FIGS. 6 and 7, and programs for calculating the distance between singular points. An image memory 42 that stores data for identifying the seal imprint image in correspondence with its XY coordinates (for example, coordinates indicating the outline of the seal imprint, etc.) and various data regarding singular points, and reading data from the image memory 42 and decoding the program. It is comprised of an arithmetic control unit 43 (hereinafter simply referred to as CPU) that executes and controls various calculations and a series of processes related to seal verification. The distribution controls the operation of the device 2.

FIG. 3 is an enlarged view of the edges of strokes, etc. in the seal impression, and illustrates how to determine singular points.

First, from one point P on the contour j to both sides, determine the points R that are a predetermined contour length WL, WR (specifically, the number of points in the XY coordinates along the contour l), and then Draw a parallelogram with two sides of minutes PL and PR to determine another point S. Next, the points p and s and the points L and R are connected, respectively, and the ratio between the length of the line segment ps and the length of the line segment LR is calculated. Similarly, the position of the point P is sequentially moved along the contour line l, and the point that becomes smaller is determined as the singular point. In the figure, line segments PL, P
The angle α between R is defined as a “singular angle”.

FIG. 4 shows an example of a seal impression, and the position of the singular point P determined by the method of FIG. 3 is indicated by a black circle.

Each singular point P appears at a portion where the contour line l changes sharply at an angle of at least 90 degrees, specifically at an edge of a stroke or a concave portion.

Figure 5 shows the outlines of corresponding parts of the reference seal imprint λ and the verified seal imprint on the same coordinates, and the coordinates of each pair of singular points P and Q are expressed as (X, Y) (X 'lY
'), the distance d between the singular points P and Q is given by the following equation.

d-(X-X/)2+(Y-Y/)2In the figure,
Angles α and αl are singular angles, and angles β and β are radiation angles, respectively.

The CPU 43 calculates a large number of singular points P for the verified seal impression and the reference seal impression using the method shown in FIG.

Q is extracted, and then the singular point selection program shown in FIG.
t I P2 + −−+ Pn,・Ql r Q21
......, Qn is extracted, and the distance calculation program between singular points shown in FIG.
21... The distance between the singular points is calculated for Pi, Qi, and the authenticity of the used seal is determined based on the total value of the calculated data.

In Figure 6, at the "start" point, a large number of singular point data for each seal impression (coordinates of the singular point, singular angle, radiation angle, etc. when the center coordinate of the seal impression is (0,0)) is stored in the image memory. 42. By the way, the seal imprint to be verified inputted from the camera device 3 has an angular deviation from the reference seal imprint, so the CPU 43 first inputs this angular deviation (referred to as rotation angle) as data in step 60, and then inputs the data in step 61. Read one piece of information about the singularity data of the reference seal impression. In the next step 62, a check is made to see if the data is complete, and the result is No. Therefore, in step 63, various data such as selection reference values are initialized, and then in step 6
In step 4, one piece of singularity data of the stamp to be verified is read. In the next step 65, it is checked whether the data is complete, and the judgment is N'O, so in step 66 it is checked whether the singular points of both seal impressions are both located on the concave contour line or the convex contour line. If not, it is determined in steps 68 and 69 whether the difference in radiation angle and the distance between both singular points are within a reference value. In this case, in step 67, the rotation angle θ
Based on this, the singular point coordinates of the seal imprint to be verified are transformed, the radiation angle is corrected, and the seal imprint is aligned with the reference seal imprint. Thus, when each of the determinations in steps 66, 68, and 69 is YES, it is determined that the singular points of both seal impressions are in a similar positional relationship, and each singular point data is stored in the image memory 42 in step 70.

Then, in step 71, the next singular point data of the seal imprint to be verified is specified, and the process returns to step 64.

When the same process is executed for all the singularity data of the seal imprint to be verified, the determination in step 65 becomes YES.
In step 72, the next singularity data of the reference seal imprint is designated, and the process returns to step 61. Execute the same iterative process for all the singular point data of the reference seal impression below.1. When the determination in step 62 is YES, the next step 73
Proceed to. In step 73, it is checked whether or not there are a plurality of singular points in the to-be-verified seal imprint that have a similar positional relationship to one singular point in the reference seal imprint, and the determination in step 73 is N.

At this time, each singular point is registered as a "pair of singular points", and each singular point data is stored in a predetermined area of the image memory 42. On the other hand, when the determination in step 73 is YES, the calculation process of the evaluation value T is executed in step 74 and the maximum value selection process of the evaluation value T is executed in step 75, whereby one singularity is selected and the selected singularity is Only the point data is stored in a predetermined area of the image memory 42 together with the corresponding singularity data of the reference seal impression.

The above evaluation value T (Total Merit value) is
It is given by the following formula.

However, Wr, Wf, and Wd are weighting coefficients, and MR.

MFlMd is obtained from the following equation using each singular point data (shown in FIG. 5).

MR=lβ−βlI MF-1α-α11 Thus, each singular point Pj forms a pair between both seal impressions.

The data of Qj (J-1, 2, . . . , n) is stored one by one in the predetermined areas 100 and 101 of the image memory 42 shown in FIG. 10 (1), and then the CPU
43 executes the program shown in FIG. 7 to determine the authenticity of the seal used.

In FIG. 7, first, in step 81, the center coordinates (Xo, Yo) of the seal imprint image to be verified are calculated.

In this case, the CPU 43 first detects the maximum value Xmax and minimum value Xm1n of the X coordinate, and the maximum value Ymax and minimum value Ymin of the Y coordinate, as shown in FIG. Introducing into the equation, the center coordinate (Xo.

Yo) is calculated.

Next, in step 82, the counter C is initialized to "1", and then in step 83, it is checked whether "processing of all data has been completed". The determination in step 83 is No, and in the next step 84 it is checked whether the contents of the counter C have reached a certain number of processed data, and the determination is NO, so the process advances to step 85 and the image memory 42 Each data of singular points Pt and Ql is read from areas 100 and 101 of . Next, in step 86, the CPU 43 checks whether the singular point Pi of the reference seal imprint to be read out (or the singular point Q1 of the verified seal imprint) is located in the periphery of the seal imprint.

In this case, the CPU 43 determines that this singular point P1 is at the center coordinates (
Xo, Yo), it is checked whether the singular point P is located outside a certain reference radius (represented by diagonal lines in FIG. 9).

When satisfies the following equation, it is determined that the seal is located at the periphery of the seal impression.

When the determination in step 86 is YES, in step 87 each data of the singular point P1r Qt is temporarily stored in another memory area 102, 103 (shown in FIG. 10 (2)), and then the next step 88 is performed. So the singular point P1 +
The distance d between Qt is calculated using the following formula.

This calculated data d is calculated in the first total area L in step 89.
D! (shown in FIG. 10 (3)), the data of the next singular point P21 Q2 is specified in step 90, and 1 is added to the contents of counter C in step 91.
Return to step 83.

If the singular point P1 is located at the center of the seal impression, the determination at step 86 is NO, the distance calculation at step 87 is omitted, and the process proceeds to step 92, where the data of the next singular point is specified.

Thus, similar processing is performed at the singular point P2. It is executed for each data from Q2 onwards, and when the determination in step 83 or step 84 is YES, the process proceeds to step 93, where each data in the first total area LD1 is stored in the second total area LD2 (in descending order of value). (shown in FIG. 10(4)).

Then, data located in the middle in the data array of the second tally area LD2 is determined as the average value dM, and in the next step 94, this average value dM is printed by a printer. The average value dM is then compared in size with a predetermined reference value, and based on the result, it is determined whether the used seal is a genuine seal or a counterfeit seal.

[Brief explanation of the drawing]

Figure 1 is an explanatory block diagram showing a configuration example of a seal authenticity determination device, Figure 2 is a circuit block diagram of a camera device, Figure 3 is an explanatory diagram showing how to determine a singular point, and Figure 4 is an explanatory diagram of a seal imprint. An enlarged view showing an example, FIG. 5 is an explanatory diagram showing the positional relationship between singular points in the reference seal imprint and the verified seal imprint, FIG. Flowchart showing the calculation program, FIG. 8 is an explanatory diagram showing the method of calculating center coordinates, FIG. 9 is an explanatory diagram showing the position of the singular point that is the target of distance calculation, and FIG. 10 (1)
~(4) is an explanatory diagram showing the memory contents of the image memory, the first
FIG. 1 is an explanatory diagram showing the deviation of the seal impression. a... Reference seal imprint b... Verified seal imprint P, Q... Singular point d... Distance between singular points Patent applicant Tateishi Electric Co., Ltd. Agent Patent attorney Mitsuru Suzuki Yama Agent Patent attorney Kenji Asaya

Claims (1)

[Claims] The image of the seal imprint to be verified is compared with the image of the reference seal imprint, and points where the outline changes sharply are extracted as singular points from both seal imprint images. After selection, the distance between the pair of singular points distributed in the peripheral areas excluding the central part of both seal impressions is calculated, and the authenticity of the seal is determined based on the aggregate value of each calculated data. Seal verification method.