JP5145882B2 - Authenticity determination device, program, and storage medium - Google Patents

Description

  The present invention relates to a true / false determination apparatus, a program, and a storage medium.

  In recent years, techniques for preventing counterfeiting and guaranteeing originals of paper documents such as title securities and confidential documents have been studied.

For example, in Patent Document 1, a random pattern formed by paper fibers of a paper document is registered in advance, and the paper document is compared by comparing the random pattern of the paper document to be collated with the registered random pattern. Techniques for matching are described.
JP 2004-102562 A

  An object of the present invention is to make a true / false determination of a set of sheet-like objects composed of a plurality of sheets in a short time.

  In the invention of the true / false determination apparatus according to claim 1, the reference data representing the characteristics of the predetermined area obtained by reading in advance the predetermined area on the surface of the true sheet-like material having random unique characteristics. Acquisition means for acquiring, reading means for reading the surface of the sheet-like object to be determined, and extraction of comparison data representing characteristics of a part of the comparison area of the surface of the sheet-like object read by the reading means; And comparing the extracted comparison data and the reference data by moving the position of the comparison area from a reference position, and determining means for determining the authenticity of the sheet-like object based on a comparison result; The position of the comparison region when it is determined that one sheet-like object in the one set is true when determining the authenticity of a set of objects composed of one sheet-like object. Remember When the position of the comparison area is stored in the storage means and the storage means, the position of the comparison area of the other sheet-like object in the one set is set with the position of the comparison area as the reference position. Control means for controlling the determination means so as to be moved.

  According to a second aspect of the present invention, in the authenticity determination apparatus according to the first aspect, the control means is configured such that the sheet-like object is true when the comparison area is moved within a predetermined range including the reference position. If it is not determined that there is a position, the determination means is controlled so that the position of the comparison area is moved with a position that is point-symmetric with respect to the center of the sheet-like object as a new reference position.

  According to the invention of claim 3, the computer extracts the comparison data representing the characteristics of a part of the comparison area on the surface of the sheet-like object to be determined, and the extracted comparison data and the true characteristic having random unique characteristics. The comparison with the reference data representing the characteristics of the predetermined area obtained by reading the predetermined area on the surface of the sheet-like material in advance is repeated by moving the position of the comparison area from the reference position, and the comparison result is obtained. A step of determining the authenticity of the sheet-like object on the basis of one sheet-like object in the one set when determining the authenticity of a set of objects composed of a plurality of sheet-like objects Storing the position of the comparison area when the object is determined to be true in the storage means; and, if the position of the comparison area is stored in the storage means, the position of the comparison area is the reference Place As a program for executing the steps of: controlling to move the position of the comparison area other sheet-like object in the set.

  The invention according to claim 4 is a storage medium storing the program according to claim 3.

  According to the invention of claim 1, claim 3, and claim 4, compared with the case of determining the authenticity of a set of objects consisting of a plurality of sheet-like objects without changing the reference position, The effect that the authenticity of one set of objects can be determined in a short time is obtained.

  According to the invention of claim 2, when the comparison region is moved within a predetermined range including the reference position, when the sheet-like object is not determined to be true, the method of moving the comparison region is not changed. As compared with, an effect that the authenticity of one set of objects can be determined in a short time is obtained.

  Hereinafter, an example of an embodiment of the present invention will be described in detail with reference to the drawings.

  As shown in FIG. 1, a multifunction machine 10 having a function of authenticating according to an embodiment of the present invention includes a paper fingerprint database server 14 and a plurality of (two in FIG. Are connected to client PCs 16A and 16B. Although FIG. 1 illustrates a configuration in which one multifunction device 10 is connected, a configuration in which a plurality of multifunction devices having the same function are connected may be employed.

  The paper fingerprint database server 14 is configured to include a network interface, a controller, and a storage device (each not shown), and in accordance with a registration instruction to the paper fingerprint database server 14 received via the network interface, Register data according to the registration instruction in the device. Also, the paper fingerprint database server 14 reads data corresponding to the read instruction from the storage device in response to the read instruction from the paper fingerprint database server 14 received via the network interface, and returns it to the transmission source of the read instruction. .

  The paper fingerprint database server 14 has unique features collected from an arbitrary area (hereinafter referred to as “paper fingerprint area”) of a predetermined size on each paper (original) for each paper that is a target of authenticity determination. Reference data to be represented (hereinafter referred to as “paper fingerprint data”) is registered. Here, since it is impossible to control the entanglement of the fibrous material forming the paper at the time of manufacture, the entanglement of the fibrous material forming the paper can be regarded as random. As a result, data corresponding to an image obtained by reading an arbitrary area can be information representing a characteristic unique to the paper (original) in an arbitrary area on the paper (original).

  Here, in the case of a document composed of a plurality of sheets of paper, each of the paper fingerprint data of the same set of paper (original) is associated with the paper fingerprint database so that it can be seen that it is included in the same set. Registered in the server 14. In many cases, paper fingerprint data is collected from an area of a predetermined size at the same position between the same set of papers (originals).

  The client PCs 16 </ b> A and 16 </ b> B transmit image data and operation instructions to the multifunction device 10 and receive an operation state signal from the multifunction device 10.

  Next, a schematic configuration of the multifunction machine 10 will be described with reference to FIG.

  The multifunction machine 10 is provided with a system controller 26 to which a CPU 18, a ROM 20, a RAM 22, and the like are connected by a bus 24. The multifunction device 10 includes a network interface 28 for connecting to a network, an operation panel and a display, a user interface 30 for performing various input operations and displaying the operation state of the multifunction device 10, a scanner unit 32, a printer, and the like. The unit 34, the HDD 36, and the reading device 38 are included. The network interface 28, the user interface 30, the scanner unit 32, the printer unit 34, and the HDD 36 are connected to the bus 24 of the system controller 26, and the entire multifunction device 10 is controlled by the system controller 26.

  The system controller 26 can be connected to the paper fingerprint database server 14 and the client PCs 16A and 16B via the network interface 28.

  The scanner unit 32 reads the original image when the original is placed on a platen glass (not shown), and generates image data corresponding to the original image. In the present embodiment, the document image is represented by, for example, a resolution of 400 dpi and a gradation of an 8-bit gray scale. The multifunction machine 10 according to the present embodiment is provided with a so-called automatic document feeder (ADF) that automatically feeds placed documents one by one.

  The printer unit 34 applies, for example, an electrophotographic process, and records image data according to image data input from the client PCs 16A and 16B via the network, image data of a document image read by the scanner unit 32, and the like. And so on.

  The HDD 36 is an OS (operating system), a program for executing authenticity determination processing to be described later, data used for executing the program, image data generated by the scanner unit 32, and an image input via a network or the like. It is a non-volatile storage device that stores data and the like.

  The reading device 38 is loaded with a storage medium 40 such as a magneto-optical disk, an optical disk, or a magnetic disk, and the storage contents are transmitted from the storage medium 40. For example, there are a magneto-optical disk device for reading the storage contents of a magneto-optical disk, an optical disk device for reading the storage contents of an optical disk, and a magnetic disk device for reading the storage contents of a magnetic disk.

  In such a multifunction machine 10, the CPU 18 of the system controller 26 reads out the program stored in the HDD 36, stores it in the RAM 22, and executes each of the programs stored in the RAM 22. In the present embodiment, by executing a program by the CPU 18, in the multifunction machine 10, a true / false determination process is performed to determine whether or not the paper document read by the scanner unit 32 is an original.

  The program stored in the HDD 36 and the data used for executing the program may be stored in the storage medium 40 and read by the reading device 38. When the program is stored in the storage medium 40 as described above, when the storage medium 40 is loaded into the reading device 38, the CPU 18 of the system controller 26 reads the program stored in the storage medium 40 and stores it in the RAM 22. Store.

  Next, the authenticity determination process by the system controller 26 will be described.

  FIG. 3 shows a processing routine for authenticity determination by the system controller 26. A program for this processing routine is stored in the ROM 20 of the system controller 26.

  In step 100, it is determined whether or not a document for authenticity determination is set in the scanner unit 32. If the determination is affirmative, the process proceeds to step 102, and if the determination is negative, the process returns to step 100.

  In step 102, it is determined whether or not the authenticity determination target is a set of originals composed of a plurality of sheets. This determination may be made as one set when there are a plurality of documents set in the scanner unit, or may be set as one set when the user interface 30 inputs a set of documents made up of a plurality of sheets. Good.

  In step 104, the scanner unit 32 scans one original. Since the MFP 10 of this embodiment includes an automatic document feeder (ADF), the document placed on the top of a plurality of sheets is scanned and image data is stored.

  In step 106, it is determined whether or not position data indicating a reference position serving as a reference for the position when searching for the position of the paper fingerprint area is stored in the RAM 22. If not stored, the process proceeds to step 108, and if stored, the process proceeds to step 116.

  In step 108, the position of the paper fingerprint area is searched with the origin as the reference position, and the authenticity of the document is determined as follows.

  Next, referring to FIGS. 4 and 5, the original authenticity determination routine in step 108 will be described.

  The search for the position of the paper fingerprint area according to the present embodiment is performed by dividing the document into a plurality of blocks (in the case shown in FIG. 4A, for example, as shown in FIG. 4A), 28 divisions), and by determining whether or not each block includes a paper fingerprint area.

  In step 150 of FIG. 5, the block located at the origin is selected. That is, in the case shown in FIG. 4A, the block “1” is selected.

  In step 152, the position of the comparison area is determined so as to be positioned at the corner of the block. That is, in the case illustrated in FIG. 4B, the position of the comparison region is determined so as to be positioned in the region B1.

  In step 154, an image of the comparison region at the position determined in step 152 (hereinafter referred to as “comparison image”) is extracted.

  In step 156, a comparison process is performed.

  Next, the comparison processing routine in step 156 will be described. With reference to FIGS. 6 and 7, the comparison routine for two different patterns will be described.

  FIG. 6 shows a routine when the size of the comparison area is the same as that of the paper fingerprint area.

  In step 200, comparison data corresponding to the comparison image is extracted from the image data obtained by the processing in step 104. In the present embodiment, for example, the size of the paper fingerprint area and the size of the comparison area are 64 × 64 dots (about 4 mm × about 4 mm).

  In step 202, paper fingerprint data is acquired. Here, when the position data indicating the reference position for searching for the position of the paper fingerprint area is not stored in the RAM 22, the paper fingerprint database server 14 stores the paper fingerprint data that has not been compared yet. Get either. When the position of the paper fingerprint area is detected, the paper fingerprint data of the originals included in the same set registered in the paper fingerprint database server 14 in association with the paper fingerprint data is read and stored in the RAM 22. That is, when the position data indicating the reference position is stored in the RAM 22, any of the paper fingerprint data that has not been compared yet is acquired from the RAM 22.

  In step 204, the correlation value between the paper fingerprint data and the comparison data is calculated by the normalized correlation method according to the following equation (1).

ステップ２０６では、ステップ２０４で求めた相関値が閾値を超えているか否か判定する。なお、相関値の閾値としては例えば「０．３」を用いることができる。ステップ２０６の判定が肯定された場合にはステップ２０８へ移行し、照合成立とする。また、ステップ２０６の判定が否定された場合はステップ２１０へ移行し、未だ比較が行なわれていない紙指紋データがないか否かを判定する。判定が肯定された場合はステップ２１２へ移行し、判定が否定された場合はステップ２０２へ戻る。ステップ２１２では、照合不成立とする。

In step 206, it is determined whether or not the correlation value obtained in step 204 exceeds a threshold value. For example, “0.3” can be used as the threshold value of the correlation value. If the determination in step 206 is affirmative, the process proceeds to step 208, where collation is established. If the determination in step 206 is negative, the process proceeds to step 210 to determine whether there is any paper fingerprint data that has not been compared. If the determination is affirmative, the process proceeds to step 212, and if the determination is negative, the process returns to step 202. In step 212, verification is not established.

  FIG. 7 shows a routine when the size of the comparison area is larger than the paper fingerprint area.

  In step 250, comparison data corresponding to the comparison image is extracted from the image data obtained by the processing in step 104.

  In step 252, paper fingerprint data is acquired. Here, when the position data indicating the reference position for searching for the position of the paper fingerprint area is not stored in the RAM 22, the paper fingerprint database server 14 stores the paper fingerprint data that has not been compared yet. Get either. When the position of the paper fingerprint area is detected, the paper fingerprint data of the originals included in the same set registered in the paper fingerprint database server 14 in association with the paper fingerprint data is read and stored in the RAM 22. That is, when the position data indicating the reference position is stored in the RAM 22, any of the paper fingerprint data that has not been compared yet is acquired from the RAM 22.

  In step 254, the data extraction position in the comparison area is initialized.

  In step 256, data (calculation target data) of an area having the same size as the paper fingerprint area located at the set data extraction position is extracted from the comparison data. For example, the size of the paper fingerprint area is 32 × 32 dots (about 2 mm × about 2 mm), and the size of the comparison area is 64 × 64 dots (about 4 mm × about 4 mm).

  In step 258, the correlation value between the paper fingerprint data and the calculation target data is calculated by the normalized correlation method according to the above-described equation (1), and the correlation value obtained by the calculation is stored in the RAM 22.

  In step 260, it is determined whether or not the entire comparison area has been calculated and stored. If the determination is affirmative, the process proceeds to step 264, and if the determination is negative, the process proceeds to step 262.

  In step 262, the data extraction position is moved vertically or horizontally by one dot, and the process returns to step 256. Thus, steps 256 to 262 are repeated until the determination in step 260 is affirmed. In this embodiment, since the paper fingerprint area is 32 × 32 dots and the comparison area is 64 × 64 dots, the correlation value is calculated (64−32 + 1) × (64−32−1) = 1089 times, and 1089 Correlation values are obtained.

  When the calculation of the correlation value is completed, the determination at step 260 is affirmed and the routine proceeds to step 264, where the maximum value is extracted from the large number of correlation values obtained by the above calculation.

In step 266, after calculating the standard deviation and average value of a large number of correlation values, the calculated standard deviation / average value and the maximum value of the correlation value obtained in step 264 are respectively substituted into the following equation (2). Then, the normalized score of the maximum correlation value is calculated.
Normalized score = (maximum correlation value-average correlation value) / standard deviation of correlation values (2)
In step 268, it is determined whether or not the maximum correlation value obtained in step 264 exceeds the threshold value and the normalized score calculated in step 266 exceeds the threshold value. For example, “0.3” can be used as the threshold value of the maximum correlation value, and “5.0” can be used as the threshold value of the normalized score. If the determination in step 268 is affirmed, the process proceeds to step 270, where collation is established. If the determination in step 268 is negative, the process proceeds to step 272 to determine whether there is any paper fingerprint data that has not been compared. If the determination is affirmative, the process proceeds to step 274, and if the determination is negative, the process returns to step 252. In step 274, verification is not established.

  In step 158, it is determined whether or not collation is not established. If the determination is affirmative, the process proceeds to step 160. If the determination is negative, the process proceeds to step 110 in FIG.

  In step 160, it is determined whether or not there is an area in which comparison processing has not been performed in the selected block. If the determination is affirmative, the process proceeds to step 164. If the determination is negative, the process proceeds to step 162.

  In step 162, the position of the comparison area is moved. That is, for example, as indicated by an arrow in FIG. 4B, the position of the comparison region is moved from the region B1 to the region B2 (in the case shown in FIG. 4B, the region B1 and the region B2 are partly overlapping). This movement width is desirably a width of one dot. In addition, based on the comparison result, the movement width may be half the width of the comparison area while the degree of correlation is small, and the width may be narrowed as the degree of correlation increases.

  In step 164, it is determined whether there is any block for which comparison processing has not been performed. If the determination is affirmative, the process proceeds to step 110 in FIG. 3, and if the determination is negative, the process proceeds to step 166.

  In step 166, a block is selected. For example, in the case shown in FIG. 4A, the blocks are selected in the order indicated by the arrow 4A.

  Next, in step 110, it is determined whether or not the position where the paper fingerprint data is collected is detected. If the determination is affirmative, the process proceeds to step 112, and if the determination is negative, the process proceeds to step 114.

  In step 112, the position where the paper fingerprint data is collected is stored in the RAM 22 as a reference position.

  In step 114, it is determined whether there is a next document. If there is no document, the process proceeds to step 122 described later, and if there is a document, the process returns to step 104.

  Next, the processing routine of step 116, which is shifted when it is determined in step 106 that position data indicating the reference position is stored in the RAM 22, will be described with reference to FIGS.

  In step 300 of FIG. 8, a block including the reference position of the position data stored in the RAM 22 is selected. That is, in the case shown in FIG. 9, the block “1” is selected.

  In step 302, comparison processing is performed on all the blocks adjacent to the block selected in step 300. That is, in the case shown in FIG. 9A, the comparison processing is performed on the blocks “1” to “9”. Further, as shown in FIG. 9B, if there is no adjacent block, the comparison process is performed on the blocks “1” to “6”.

  Next, the processing routine of step 302 will be described with reference to FIG.

  In step 350, the position of the comparison area is determined so as to be positioned at the corner of the selected block.

  In step 352, an image of the comparison region at the position determined in step 350 (hereinafter referred to as “comparison image”) is extracted.

  In step 354, a comparison process is performed. This comparison processing routine is the same as the comparison processing routine in step 156 of FIG.

  In step 356, it is determined whether or not collation is established. If the collation is not established, the process proceeds to step 358, and if the collation is established, the process proceeds to step 304 in FIG.

  In step 358, it is determined whether or not there is an area in which comparison processing has not been performed in the selected block. If there is no unexecuted area, the process proceeds to step 362, and if there is an unexecuted area, the process proceeds to step 360.

  In step 360, the position of the comparison area is moved. This movement width is desirably a width of one dot. In addition, the movement width may be half the width of the comparison area while the degree of correlation is small based on the comparison result, and the width may be narrowed as the degree of correlation increases.

  In step 362, it is determined whether or not comparison processing has been performed on all blocks adjacent to the block selected in step 300. That is, in the case shown in FIG. 9A, it is determined whether or not the comparison process has been performed on the blocks “1” to “9”. If the determination is affirmative, the process proceeds to step 304 in FIG. 8, and if the determination is negative, the process proceeds to step 364.

  In step 364, a block is selected. For example, in the case illustrated in FIG. 9C, the blocks are selected in the order indicated by the arrow C1. In the case shown in FIG. 9D, the blocks are selected in the order indicated by the arrow D1.

  In step 304, a block including the reference position of the position data stored in the RAM 22 and the position to be pointed is selected. That is, in the case shown in FIG. 9C, the block “10” is selected. In the case shown in FIG. 9D, the block “7” is selected.

  In step 306, comparison processing is performed on all the blocks adjacent to the block selected in step 304. That is, in the case shown in FIG. 9C, the comparison process is performed on the blocks “10” to “16”. Block selection is performed in the order indicated by arrow C2. Since blocks “4” and “5” have already been compared, they are excluded from processing. In the case shown in FIG. 9D, comparison processing is performed on the blocks “7” to “12”. Block selection is performed according to the order indicated by the arrow D2. This comparison processing routine is the same as the processing routine in step 302 described above.

  If it is determined in the above-described step 102 that the authenticity determination target is not a set of originals consisting of a plurality of sheets, the scanner unit 32 scans the originals (step 118) and the paper fingerprint with the origin as the reference position. The position where the data is collected is searched, and the authenticity of the original is determined (step 120). The process at step 120 is the same as the process at step 108.

In step 122, the result of true / false judgment is output. The output is performed by displaying on the display of the user interface 30. Alternatively, the image may be formed on the recording paper by the printer unit 34. Further, it may be performed by notifying the client PCs 16A and 16B via the network 12. Note that it is also considered that a document determined to be false was determined to be false because scanning was performed upside down. In this case, the operator who obtained the result of the authenticity determination may cause the scanner unit 32 to scan the back surface and cause the system controller 26 to perform the authenticity determination again. Alternatively, the system controller 26 may cause the scanner unit 32 to scan the back side of the document after the process of step 164 in FIG. 3 and perform the same processes as in steps 150 to 164. Similarly, after the processing in step 306 in FIG. 8, the scanner unit 32 may scan the back side of the document and perform the same processing as in steps 300 to 306. Note that the determination performed in step 102 in FIG. May be performed after the determination in step 110. That is, when the paper fingerprint data is associated with other paper fingerprint data, it is determined that the document is one of a set of a plurality of sheets. At this time, if the paper fingerprint data is not associated with other paper fingerprint data, the process of step 112 is omitted.

  Further, a form in which a paper fingerprint area is searched without performing block division may be used.

  As described above, according to the present embodiment, when determining the authenticity of a set of documents composed of a plurality of sheets, 1 is determined from the position of the paper fingerprint area of the document first determined to be true in the set. The paper fingerprint area of another document in the set is searched. Thereby, the paper fingerprint area can be searched in a short time, and the productivity of the document authenticity determination process can be improved.

It is a conceptual diagram which shows the whole image of this Embodiment. 1 is a schematic configuration diagram of a multifunction machine according to an embodiment. It is a flowchart which shows the routine of the true / false determination process which concerns on this Embodiment. (A) is a conceptual diagram of block division, and (B) is a conceptual diagram of a comparison area. It is a flowchart which shows the routine of the detection process of a paper fingerprint area | region when an origin is made into a reference position. It is a flowchart which shows the routine of a comparison process. It is a flowchart which shows the routine of a comparison process. It is a flowchart which shows the routine of the detection process of a paper fingerprint area | region when the position of the paper fingerprint area | region already detected is made into a reference position. It is a conceptual diagram for demonstrating the selection order of a block. It is a flowchart which shows the routine which performs a comparison process with respect to all the blocks adjacent to the block containing a reference position.

Explanation of symbols

10 MFP 14 Paper fingerprint database server 16A, 16B Client PC
26 System Controller 28 Network Interface 32 Scanner Unit 34 Printer Unit 36 HDD
38 Reading device 40 Storage medium

Claims (4)

Obtaining means for obtaining reference data representing the characteristics of the predetermined area obtained by reading in advance a predetermined area on the surface of a true sheet-like material having random unique characteristics;
Reading means for reading the surface of the sheet-like object to be judged;
Extraction of comparison data representing the characteristics of a part of the comparison area on the surface of the sheet-like object read by the reading means, and comparison between the extracted comparison data and the reference data from the reference position to the comparison area A determination means for determining whether the sheet-like object is true or false based on a comparison result.
The position of the comparison region when it is determined that one sheet-like object in the one set is true when determining the authenticity of a set of objects composed of a plurality of sheet-like objects Storage means for storing
When the position of the comparison area is stored in the storage means, the position of the comparison area of another sheet-like object in the one set is moved using the position of the comparison area as the reference position. Control means for controlling the determination means;
A true / false determination device.   If the sheet-like object is not determined to be true when the comparison area is moved within a predetermined range including the reference position, the control means is configured to perform the operation with respect to the center of the sheet-like object. The authenticity determination apparatus according to claim 1, wherein the determination unit is controlled to move the position of the comparison area with a point-symmetric position as a new reference position. On the computer,
Extraction of comparison data representing the characteristics of a part of the comparison area on the surface of the sheet-like object to be determined, and a predetermined area on the surface of the true sheet-like object having random unique characteristics with the extracted comparison data The comparison with the reference data representing the characteristics of the predetermined area obtained by reading in advance is repeated by moving the position of the comparison area from the reference position, and the authenticity of the sheet-like object is determined based on the comparison result. Determining
The position of the comparison region when it is determined that one sheet-like object in the one set is true when determining the authenticity of a set of objects composed of a plurality of sheet-like objects Storing in a storage means;
When the position of the comparison area is stored in the storage means, the position of the comparison area of another sheet-like object in the one set is moved using the position of the comparison area as the reference position. Controlling step;
A program for running   A storage medium storing the program according to claim 3.

Images