JP5587224B2 - Seal verification program and seal verification device - Google Patents

Description

  The present invention relates to a seal stamp verification program and a seal stamp verification apparatus for verifying a registered stamp registered in a server and a seal imprinted on a form or the like.

2. Description of the Related Art Conventionally, in a bank or the like, a stamp verification device is used to verify a seal stamp of a seal stamped on a document by a customer and a seal stamp of a registered seal registered in advance.
This seal stamp verification device compares a seal stamp image scanned from an input device such as a scanner with a registered seal image registered in advance, so that the seal stamp image and the registered seal image are obtained from the same seal stamp. It is determined whether or not.

  Specifically, the determination based on the three characteristic features of pixel matching rate, vector matching rate, and edge matching rate has been performed. For example, a grayscale image is created from each of the matching seal imprint image and the registered seal stamp image, vector calculation is performed based on the density value of the grayscale image, and the verification rate is calculated, thereby making it difficult to be affected by misalignment or blurring. (For example, refer to Patent Document 1).

  In addition, a determination based on a local analysis using a pixel clumping method and a dense method has also been performed. For example, each image is divided into a plurality of blocks and a correlation image is created for each block in order to prevent misalignment between the verification seal image and the registered seal image. An interpolated local maximum image in which pixel values are assigned only to the pixels in the vicinity of the pixel is created, and seals are collated based on a cumulative value image obtained by adding the interpolated local maximum image for each block (for example, Patent Documents). 2).

JP 2001-202514 A JP-A-9-288734

  However, the so-called three-sentence format, etc., with a relatively simple imprint shape, has many shapes that are very similar to those of company stamps, etc., with a relatively complex imprint shape. There is a problem in the judgment that is being carried out that the coincidence rate becomes high and the difference mark may be erroneously determined as the same mark.

  The present invention has been made in view of the above-described actual circumstances, and provides a seal collation program and a seal collation apparatus capable of performing highly accurate seal collation even in a three-sentence format or the like having a relatively simple seal shape. The purpose is to provide.

The present invention employs the following configuration in order to solve the above problems.
That is, according to one aspect of the present invention, seal verification program of the present invention, a computer matching a seal device, taken read by an image reading apparatus for reading a seal is seal mark image data reading the seal image was on the medium A seal frame extracting means for extracting a seal frame equivalent portion from the read seal image data using a circular shape detection process, and among the pixels constituting the read seal image data read by the image reading device , the seal frame extraction means extracts the seal stamp frame data. A portion that is a predetermined number or more continuous from the inner periphery to the center of the seal frame equivalent portion is detected as a contact portion where the seal frame equivalent portion and a character equivalent portion other than the seal frame equivalent portion are in contact with each other. Contact points for calculating contact information including continuous pixel detection means, number and position data of contact portions detected by the continuous pixel detection means, and width data of each contact portion Distribution calculating means, a seal verification program to function as the contact information comparing means for matching the seal by comparing the contact information calculated by said contact information calculating means.

In the seal collation program according to the present invention, it is preferable that the contact information calculation means uses the width data as the number of pixels that are continuous along the inner circumference in the contact portion.
Further, the seal collation program of the present invention further functions as a registration mark data storage unit that stores the contact information calculated by the contact information calculation unit in association with the read stamp image data and stores it in the storage device as registration mark data. It is desirable to be a seal verification program.

The seal collation program of the present invention further compares the contact information of the read seal image data calculated by the contact information calculation means with the contact information of the registration mark data stored in the registration mark data storage means. it is desirable that the seal verification program to function as the contact information comparing unit.

According to a further aspect of the present invention, matching a seal device of the present invention, a circular shape from the readings taken the read mark image data in the image reading apparatus for reading as a sign read image data to print image of seal that is stamped on the medium A seal frame extraction means for extracting a seal frame equivalent part using a detection process, and a seal frame equivalent part extracted by the seal frame extraction means among the pixels constituting the read seal image data read by the image reading device . A continuous pixel detecting means for detecting a portion that is continuous for a predetermined number or more from the inner periphery toward the center as a contact portion in which the portion corresponding to the character other than the portion corresponding to the seal frame and the portion corresponding to the seal frame is in contact; and contact information calculating means for calculating the contact information including width data of the number and the position data and the contact portion of the detected contact portions by said continuous pixel detection means, said contact information calculating means Thus by comparing the contact information calculated, characterized in that it comprises a contact information comparison means for collating the seal.

In the seal collation device according to the present invention, it is preferable that the contact information calculation means uses the width data as the number of pixels that are continuous along the inner circumference in the contact portion.
The seal collation apparatus of the present invention further includes registration mark data storage means for storing the contact information calculated by the contact information calculation means in the storage device as registration mark data in association with the read seal image data. desirable.

In the seal collation apparatus of the present invention, the contact information comparison means calculates the contact information of the read seal image data calculated by the contact information calculation means and the contact information of the registration mark data stored by the registration mark data storage means. and Turkey comparing the door is desired.

  According to the present invention, it is possible to improve the accuracy of collation by adding a determination condition for the same mark / different mark. In particular, in the so-called three-sentence format, where there were cases in which it was erroneously determined in the conventional judgment, there are fewer black pixels in the binarized imprint image compared to the company seal. / The difference mark can be reliably determined. Furthermore, the improvement of the judgment of the difference mark in the three-sentence format has the effect that the operation efficiency in the seal collation can be improved.

It is a functional block diagram of the seal | sticker collation apparatus to which this invention is applied. It is a flowchart which shows the flow of the seal stamp collation process which the seal stamp collation apparatus 1 performs. It is a flowchart (the 1) which shows the flow of the continuous pixel detection process which the continuous pixel detection part 12 performs. It is a flowchart (the 2) which shows the flow of the continuous pixel detection process which the continuous pixel detection part 12 performs. It is a figure for demonstrating the continuous pixel detection process which the continuous pixel detection part 12 performs. It is a figure which shows the example of an acquisition pixel work table. It is a figure which shows the example of a contact information work table. It is a flowchart (the 1) which shows the flow of the contact information calculation process which the contact information calculation part 13 performs. It is a flowchart (the 2) which shows the flow of the contact information calculation process which the contact information calculation part 13 performs. It is a figure for demonstrating the contact information calculation process which the contact information calculation part 13 performs. It is a figure which shows the example of a contact information table. It is a figure for demonstrating the position data of a contact part. It is a figure which shows the example of the seal impression of the seal stamp A. It is a figure which shows the example of the seal impression of the seal stamp B. FIG. It is a flowchart (the 1) which shows the flow of the contact information comparison process which the contact information comparison part 14 performs. It is a flowchart (the 2) which shows the flow of the contact information comparison process which the contact information comparison part 14 performs. It is a figure which shows the example of the registration mark and reading mark to compare. It is a figure which shows the example of the contact information of a registration mark and a reading mark.

  The present invention corresponds to a portion corresponding to a seal stamp frame, more strictly to a frame, in each of registration mark data registered in a server such as a financial institution and read seal data scanned by an image reading apparatus. Extract the number, position, and contact width between the inner circumference of the part and the character part inside the frame, and determine whether the extracted number, position, and contact width match between the registration mark and the reading mark. To do. However, since the seal stamps generally have bleeding or rubbing, a predetermined threshold value is provided, and if the difference is within the threshold range, it is determined that they match. The threshold value can be specified in the operating environment.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.
FIG. 1 is a functional block diagram of a seal collation apparatus to which the present invention is applied.
In FIG. 1, a seal collation apparatus 1 includes a seal frame extraction unit 11, a continuous pixel detection unit 12, a contact information calculation unit 13, and a contact information comparison unit 14, and is controlled via a management unit 10.

  The seal frame extraction unit 11 uses an outer frame detection process such as a well-known circular shape detection process from a seal stamp of a seal stamped on a medium such as a form, which is read as read seal image data by an image reading apparatus such as a scanner. A part corresponding to a seal frame is extracted. Then, the extracted information on the portion corresponding to the seal frame is stored in the seal frame information storage unit 15 on the memory.

  The continuous pixel detection unit 12 is a portion that continues a predetermined number or more from the inner circumference to the center of the portion corresponding to the seal frame extracted by the seal frame extraction unit 11 among the pixels constituting the read seal image data. Is detected as a contact portion (hereinafter also referred to as a contact point) where a portion corresponding to the character other than the portion corresponding to the seal frame is in contact with the portion corresponding to the character other than the portion corresponding to the seal frame. Then, the detected contact portion information is stored in the continuous pixel information storage unit 16 on the memory.

The contact information calculation unit 13 calculates contact information including the number of contact portions detected by the continuous pixel detection unit 12, position data of the contact portions, and width data of each contact portion. The position of each contact portion is calculated by a contact position information calculation unit 131 provided in the contact information calculation unit 13. Then, the calculated position information of each contact portion is stored in the contact position information storage unit 17 on the memory.
In addition, the width of each contact portion is calculated by calculating the number of pixels that are continuous along the inner circumference of the seal frame corresponding portion extracted by the seal frame extraction unit 11 in each contact portion by the contact width information calculation unit 132. Calculated as data. Then, the calculated width data of each contact portion is stored in the contact width information storage unit 18 on the memory.

The contact information calculated by the contact information calculation unit 13 is stored in a registration mark data storage unit (not shown) as registration mark data in association with the read mark image data.
The contact information comparison unit 14 compares the contact information of the read seal image data calculated by the contact information calculation unit 13 with the contact information of the registration mark data stored in the registration mark data storage unit. More specifically, the contact position information comparison unit 141 compares the position data of the contact portions, and the contact width information comparison unit 142 compares the width data of the contact portions.

FIG. 2 is a flowchart showing the flow of the seal collation process executed by the seal collator 1.
First, in step S21, the seal frame extracting unit 11 reads out a known circular shape detection process or the like from a seal stamp of a seal stamped on a medium such as a form, which is read as read stamp image data by an image reader such as a scanner. Using the frame detection process, the inner circumference of the seal frame equivalent part, in particular, the seal frame equivalent part is extracted.

  Next, in step S22, the continuous pixel detection unit 12 continues for a predetermined number or more from the inner periphery to the center of the portion corresponding to the seal frame extracted in step S21 among the pixels constituting the read seal image data. The portion is detected as a contact portion where the portion corresponding to the seal frame and the portion corresponding to the character other than the portion corresponding to the seal frame are in contact. More specifically, detection is performed as follows.

  3 and 4 are flowcharts showing the flow of the continuous pixel detection process executed by the continuous pixel detection unit 12, and FIG. 5 is a diagram for explaining the continuous pixel detection process executed by the continuous pixel detection unit 12. FIG. 6 is a diagram illustrating an example of the acquired pixel work table, and FIG. 7 is a diagram illustrating an example of the contact information work table.

  First, in step S301 of FIG. 3, the starting and ending pixels of the continuous pixel detection process are determined. Usually, since the continuous pixel detection process is started in order along the inner circumference (refer to the inner circumference 51 shown in FIG. 5) of the seal frame equivalent portion, an arbitrary pixel on the inner circumference 51 is determined as a starting point, The last pixel that has returned around the inner circumference 51 is determined as the end point.

  In step S302, the target range 54 to be subjected to the continuous pixel detection process is determined. This range can be determined in advance, but in the example shown in FIG. 5, from the inner periphery 51 to the center 53 of the seal frame corresponding portion, one third from the inner periphery 51 to the center 53. To the distance 52 is determined as the target range 54.

In step S303, the contact information work table 70 (see FIG. 7) is initialized.
Then, steps S304 to S410 are repeated from the starting point to the ending point determined in step S301. That is, continuous pixel detection processing is performed in order along the inner circumference 51 of the portion corresponding to the seal frame.

First, in step S304, the acquired pixel work table 60 (see FIG. 6) is initialized.
Then, steps S305 to S306 are repeated within the target range 54 determined in step S302.

  That is, in step S305, the pixels are obtained one by one from the starting pixel on the inner periphery 51 to the above-described distance 52 of the third toward the center. In step S306, if the pixel is a black pixel, “1” is set. If it is a white pixel, “0” is sequentially stored in the acquired pixel work table 60. Here, since the starting pixel is the pixel position (0, 44) on the inner periphery 51 when the pixel position of the center 53 is (0, 0), in order from this pixel position (0, 44), Pixels up to the third distance 52 are acquired. For example, nine pixels of “black pixel”, “black pixel”, “black pixel”, “white pixel”, “white pixel”, “white pixel”, “white pixel”, “white pixel”, and “white pixel” are acquired. The result is shown in FIG.

  Next, in step S407, the acquired pixel work table 60 ((a) in FIG. 6) is referred to, and it is determined whether or not “black pixels” from the top are continuous for a predetermined threshold, for example, 3 pixels or more. .

  If “black pixels” continue for a predetermined threshold or more (step S407: Yes), the coordinates on the inner circumference 51 are stored in the contact information work table 70 in step S408. In the case of FIG. 6A, since “black pixels” continue from the top by three or more pixels, (0, 44) is stored on the leftmost side as shown in FIG.

  Then, the process returns to step S304, the acquired pixel work table 60 is initialized, the pixels are acquired one by one from the pixel next to the starting point on the circumference 51 to the one-third distance 52 in step S305, and step S306. Then, “1” or “0” is stored in the acquired pixel work table 60 in order. Here, since the pixel next to the starting point is the pixel position (1, 44), pixels from the pixel position (1, 44) to the third distance 52 are acquired in order. For example, “black pixel”, “white pixel”, “black pixel”, “black pixel”, “black pixel”, “black pixel”, “black pixel”, and “black pixel” are acquired. The result is shown in FIG.

  Next, in step S407, referring to the acquired pixel work table 60 ((b) in FIG. 6), three or more “black pixels” are not consecutive from the top (the first “black pixel” is followed by “white”). Pixel ”) (step S407: No), whether or not the“ white pixel ”next to the“ black pixel ”that was not consecutive in step S409 is within a predetermined number, for example, two (whether two or more“ white pixels ”continue) ).

  In the example shown in FIG. 6B, since two or more are not continued (only one) (step S409: Yes), the “white pixel” in the acquired pixel work table 60 is changed to “black pixel” in step S410. ", That is," 0 "is rewritten to" 1 ", and the process returns to step S407. This is because the “black pixel” was originally considered due to the “rubbing” of the imprint.

  In step S407 again in the example shown in FIG. 6B, since “black pixels” continue for three or more pixels (step S407: Yes), the process proceeds to step S408, and FIG. (1,44) is stored second from the left as shown in FIG.

  When a predetermined number or more of “white pixels” continues in step S409 (step S409: No), this continuous pixel detection process is terminated, and the contact information work table 70 as shown in FIG. 7 is created.

Returning to the description of FIG.
When the contact information work table 70 is created as described above, in step S23, the contact information calculation unit 13 determines the number of contact parts, position data of the contact parts, and width data of each contact part detected in step S22. The contact information including is calculated. More specifically, the calculation is performed as follows.

  8 and 9 are flowcharts showing the flow of the contact information calculation process executed by the contact information calculation unit 13, and FIG. 10 is a diagram for explaining the contact information calculation process executed by the contact information calculation unit 13. FIG. 11 is a diagram showing an example of the contact information table, and FIG. 12 is a diagram for explaining the position data of the contact portion.

First, in step S801 in FIG. 8, the contact information table 110 (see FIG. 11) is initialized.
Then, steps S802 to S805 are repeated by the number of pixel positions stored in the contact information work table 70.

  First, in step S <b> 802, pixel position information is acquired sequentially from the contact information work table 70. For example, in the example shown in FIG. 7, the pixel position (0, 44) is first acquired.

  Next, in step S803, it is determined whether or not the pixel position information acquired last time is adjacent. In the first case, since there is no information on the pixel position acquired last time and it is not adjacent (step S803: No), in step S804, it is associated with the pixel position (0, 44) acquired in step S802. As shown in FIG. 7, the contact number “1” is assigned.

  Then, in the second step S802, the pixel position (1, 44) is acquired from the contact information work table 70, and in step S803, it is determined whether or not it is adjacent to the previously acquired pixel position (0, 44). In this case, since the pixel position (1, 44) is different from and adjacent to the pixel position (0, 44) (step S803: Yes), in step S805, the pixel position (1, 44) acquired in step S802 is obtained. 44), the same contact number “1” as the pixel position (0, 44) is assigned (see FIG. 7).

  This is repeated, and the pixel position (17, 40) is acquired from the contact information work table 70 in step S802 for the eighth time, and is adjacent to the pixel position (6, 42) acquired in the previous (seventh time) in step S803. Determine whether. Then, since the pixel position (17, 40) is not adjacent to the pixel position (6, 42) (step S803: No), the pixel position (17, 40) is associated with the pixel position (17, 40) acquired in step S802. The contact number “2” is assigned as shown in FIG.

In this way, the contact information work table 70 is completed.
Next, steps S906 to S908 in FIG. 9 are repeated for the number of contact numbers in the contact information work table 70 completed as described above.

  First, in step S906, the width of each contact portion (contact width) of the contact portion 101 and the contact portion 102 as shown in FIG. 10 is calculated. Specifically, the number of pixel positions to which the contact number “1” of the contact information work table 70 is assigned is acquired. In the example shown in FIG. 7, the pixel position to which the contact number “1” is assigned is (0, 44) (1, 44) (2, 43) (3, 43) (4, 43) (5, 43). ) (6, 42), so “7” is acquired.

  Next, in step S907, position information of each contact portion is calculated. Specifically, among the pixel positions to which the same contact number is assigned, for example, the first pixel position, the center pixel position, and the like are calculated as position information of each contact portion.

  In step S908, a contact information table (see FIG. 11) is created. When the above-described steps S906 to S908 are repeated for the number of contact numbers in the contact information work table 70, the contact information table as shown in FIG. 11 is completed.

  Here, the position information is represented by an XY plane in which the pixel position of the center 53 is (0, 0) as shown in FIG. The contact information calculated by the contact information calculation unit 13 is registered as registration mark data by being stored in a registration mark data storage unit (not shown) in association with the read mark image data.

Returning to the description of FIG.
In step S24, the contact information comparison unit 14 compares the contact information of the read mark image data calculated in step S23 with the contact information of the registration mark data stored in the registration mark data storage unit in advance. More specifically, the comparison is performed as follows.

  15 and 16 are flowcharts showing the flow of contact information comparison processing executed by the contact information comparison unit 14, FIG. 17 is a diagram showing examples of registration marks and reading marks to be compared, and FIG. It is a figure which shows the example of the contact information of a registration mark and a reading mark.

First, a case where the imprint Y in FIG. 17B is compared with the registration mark X (FIG. 17A) will be described.
First, in step S1501 in FIG. 15, a contact information table (see FIG. 18) of a registration mark (imprint X) and a reading mark (imprint Y) is acquired.

  In step S1502, it is determined whether the “number of contacts” is the same from the contact information table. Since the number of contacts of the registration mark (imprint X) is “6” and the number of contacts of the reading mark (imprint Y) is “6” (step S1502: Yes), the process proceeds to step S1503.

  Next, in step S1503, the contact position and contact width, which are contact information of the contact number 1 of the registration mark (imprint X) and the contact number 1 of the reading mark (imprint Y), are compared. In step S1504, it is determined whether or not these pieces of contact information match. Since the contact position of the registration mark (imprint X) is (0, 44) and the contact position of the reading mark (imprint Y) is different at (5, 45) (step S1504: No), the contact position to be compared is shifted. In step S1505, the contact positions to be compared are shifted one by one, and in step S1506, the contact information is compared at the shifted contact positions. In the case of the reading mark (imprint Y), since none of the contact numbers 1 to 6 coincides with the registration mark (imprint X), the process proceeds to step S1607 in FIG. 16 and the contact information comparison process is terminated.

Next, the case where the imprint Z of FIG. 17C is compared with the registration mark X (FIG. 17A) will be described.
First, in step S1501 of FIG. 15, a contact information table (see FIG. 18) of a registration mark (imprint X) and a reading mark (imprint Z) is acquired.

  In step S1502, it is determined whether the “number of contacts” is the same from the contact information table. Since the number of contacts of the registration mark (imprint X) is “6” and the number of contacts of the reading mark (imprint Z) is “6” (step S1502: Yes), the process proceeds to step S1503.

  Next, in step S1503, the contact position and the contact width, which are contact information of the contact number 1 of the registration mark (imprint X) and the contact number 1 of the reading mark (imprint Z), are compared. In step S1504, it is determined whether or not these pieces of contact information match. The contact position of the registration mark (imprint X) is (0, 44), and the contact position of the reading mark (imprint Z) coincides with (0, 44) (step S1504: Yes), so in steps S1608 to S1609, The contact information of the next contact numbers is compared.

  If all pieces of contact information match (step S1609: YES), it is determined in step S1610 that both stamps are the same mark. On the other hand, if any of the contact information does not match (step S1609: No), it is determined in step S1607 that the two stamps are different marks.

  As described above, the embodiment to which the present invention is applied has been described. However, the seal collation apparatus 1 according to this embodiment is a white pixel / black color of a target imprint as in the determination of the same mark / different mark in the prior art. In addition to the determination process based on the pixel ratio, the seal collation process of the present invention can be further performed to improve the determination accuracy for the same mark / different mark. In particular, in the so-called three-sentence format, since there are few black pixels in the binarized seal image compared to the company seal, it is possible to reliably discriminate the same mark / difference mark in the three-sentence format by adding information to be determined. It becomes possible.

  As described above, the embodiments of the present invention have been described with reference to the drawings. However, the above-described embodiments of the present invention are not limited to hardware, a DSP (Digital Signal Processor) board, or a CPU as a function of a seal verification device. It can be realized by firmware or software on the board.

  In addition, the seal collation apparatus to which the present invention is applied is not limited to the above-described embodiment as long as the function is executed, and even a single apparatus or a system composed of a plurality of apparatuses Needless to say, the integrated device may be a system in which processing is performed via a network such as a LAN or a WAN.

  It can also be realized by a system including a CPU, a ROM or RAM memory connected to a bus, an input device, an output device, an external recording device, a medium driving device, and a network connection device. That is, a ROM or RAM memory, an external recording device, or a portable recording medium in which a software program for realizing the system of the above-described embodiment is recorded is supplied to the seal verification device, and the computer of the seal verification device is programmed. Needless to say, this can also be achieved by reading and executing.

  In this case, the program itself read from the portable recording medium or the like realizes the novel function of the present invention, and the portable recording medium or the like on which the program is recorded constitutes the present invention.

  Examples of portable recording media for supplying the program include flexible disks, hard disks, optical disks, magneto-optical disks, CD-ROMs, CD-Rs, DVD-ROMs, DVD-RAMs, magnetic tapes, and nonvolatile memory cards. Various recording media recorded via a network connection device (in other words, a communication line) such as a ROM card, electronic mail or personal computer communication can be used.

  The computer (information processing apparatus) executes the program read out on the memory, thereby realizing the functions of the above-described embodiment, and an OS running on the computer based on the instructions of the program. Performs part or all of the actual processing, and the functions of the above-described embodiments are also realized by the processing.

  Furthermore, a program read from a portable recording medium or a program (data) provided by a program (data) provider is stored in a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer. After being written, the CPU of the function expansion board or function expansion unit performs part or all of the actual processing based on the instructions of the program, and the functions of the above-described embodiments are also realized by the processing. obtain.

  That is, the present invention is not limited to the embodiment described above, and can take various configurations or shapes without departing from the gist of the present invention.

DESCRIPTION OF SYMBOLS 1 Seal verification apparatus 10 Management part 11 Seal frame extraction part 12 Continuous pixel detection part 13 Contact information calculation part 14 Contact information comparison part 15 Seal frame information storage part 16 Continuous pixel information storage part 17 Contact position information storage part 18 Contact width information storage Part 51 Inner circumference 52 1/3 distance 53 Center 54 Target range 60 Acquisition pixel work table 70 Contact information work table 101 Contact part 102 Contact part 110 Contact information table 131 Contact position information calculation part 132 Contact width information calculation part 141 Contact Position information comparison unit 142 Contact width information comparison unit

Claims (8)

The computer of the seal verification device
Seal frame extracting means for extracting the seal frame corresponding parts with circular detection processing from readings taken the read mark image data in the image reading apparatus for reading a read mark image data imprints seal that is stamped on the medium,
Of the pixels constituting the read seal image data read by the image reading device , a portion that continues for a predetermined number or more from the inner periphery to the center of the seal frame equivalent portion extracted by the seal frame extraction means, Continuous pixel detection means for detecting as a contact portion where a seal frame equivalent portion and a character equivalent portion other than the seal frame equivalent portion are in contact;
Contact information calculation means for calculating contact information including the number and position data of the contact portions detected by the continuous pixel detection means and width data of each contact portion;
Contact information comparing means for comparing the contact information calculated by the contact information calculating means to collate a seal;
Seal verification program to function as.   2. The seal collation program according to claim 1, wherein the contact information calculation unit uses, as the width data, the number of pixels that are continuous along the inner circumference in the contact portion. Registration mark data storage means for storing the contact information calculated by the contact information calculation means in the storage device as registration mark data in association with the read seal image data;
A seal collation program according to claim 1 or 2 for functioning as: It said contact information comparison means for comparing the contact information of the registration mark data stored in the contact information and the registration mark data storing means of the read indicia image data calculated by said contact information calculating means,
A seal collation program according to claim 3 for functioning as: A seal frame extracting means for extracting the seal frame corresponding portion from the readings taken the read mark image data in the image reading apparatus for reading a read mark image data imprints seal that is stamped on the medium using a circular detection process,
Of the pixels constituting the read seal image data read by the image reading device , a portion that continues for a predetermined number or more from the inner periphery to the center of the seal frame equivalent portion extracted by the seal frame extraction means, Continuous pixel detection means for detecting as a contact portion where a seal-corresponding portion and a character-corresponding portion other than the seal-frame equivalent portion are in contact;
Contact information calculation means for calculating contact information including the number and position data of the contact portions detected by the continuous pixel detection means and width data of each contact portion;
Contact information comparing means for comparing the contact information calculated by the contact information calculating means and checking the seal;
A seal verification device comprising:   6. The seal collation apparatus according to claim 5, wherein the contact information calculation means uses, as the width data, the number of pixels that are continuous along the inner circumference in the contact portion. Registration mark data storage means for storing the contact information calculated by the contact information calculation means in the storage device as registration mark data in association with the read seal image data;
The seal collation apparatus according to claim 5 or 6, characterized by comprising: Said contact information comparison means that compares the contact information of the registration mark data stored in the contact information and the registration mark data storing means of the read indicia image data calculated by said contact information calculating means
Seal verification apparatus according to claim 7, wherein the this.