JP2007006139A - Verification device, verification method and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a verification device, a verification method and program for improving reliability of photographic paper. <P>SOLUTION: The verification device is provided with an imaging means for imaging a photographing layer printed on a photographing paper where prescribed content is printed, and a patterned layer on an inner face of the photographing paper; an extracting means for extracting characteristics of the photographing layer taken by the imaging means as first characteristic information, and the characteristic of the patterned layer as second characteristic information; and collating means for collating the first characteristic information and the second characteristic information with the information registered as references for recognizing the photographing paper. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a verification apparatus, a verification method, and a program, and is suitable for application when identifying contents attached to paper.

  Conventionally, paper has been used as an object for printing various contents, and photographic paper on which the contents (hereinafter referred to as “print contents”) are printed is, for example, a commodity exchange medium such as money, a content certification medium such as a certificate, or an individual. It often has high value because it functions as various media such as information storage media such as copyrighted works.

  For this reason, various countermeasures for preventing tampering with paper media have been proposed. As one of the countermeasures, pattern information based on a pattern specific to the paper from a specified area of the paper is attached to the paper as a barcode, for example. Whether the paper is the original or a copy based on the result of matching between the pattern information acquired from the designated area of the paper with the barcode and the pattern information in the barcode. An identification device adapted for identification has been proposed by the present applicant (see, for example, Patent Document 1).

That is, when the print content of a paper with a barcode attached is duplicated, the barcode is also duplicated on the duplicate paper, but the pattern information obtained from the duplicate paper is the original paper pattern information obtained from the barcode. Therefore, the identification device can identify that the paper is a duplicate.
PCT / JP2005 / 001176

  However, since such an identification device identifies paper itself, for example, impersonation is detected when the photo part of a license printed on paper with personal information such as a photo as a print content is replaced with another photo. As a result, there is a problem that the reliability of the photographic paper is impaired.

  The present invention has been made in consideration of the above points, and an object of the present invention is to propose a verification apparatus, a verification method, and a program capable of improving the reliability of photographic paper.

  In order to solve such a problem, the present invention is a verification apparatus that images a printing layer printed on the surface of a photographic paper on which a predetermined printing content is printed, and a pattern layer on the inner surface of the photographic paper. Means for extracting the feature of the print layer imaged by the imaging means as first feature information, and extracting the feature of the pattern layer as second feature information, and the first feature information And collation means for collating the second feature information with information registered as a reference for identifying the photographic paper.

  Therefore, since this verification apparatus can detect the print content and the property change of the base paper of the photographic paper, the print content printed on the photographic paper at the time of issuance can be replaced with another print content. A wide variety of alterations can be detected, such as copying to another paper.

  Further, the present invention is a verification method, the first step of imaging a print layer printed on the surface of a photographic paper on which a predetermined print content is printed, and a pattern layer on the inner surface of the photographic paper, A second step of extracting the imaged features of the print layer as first feature information and extracting the features of the pattern layer as second feature information; the first feature information and the second feature information; A third step of collating the characteristic information with information registered as a reference for identifying the photographic paper is provided.

  Therefore, since this verification method can detect the print contents and the property changes of the photographic paper base paper, the print contents printed on the photographic paper at the time of issuance can be replaced with other print contents. A wide variety of alterations can be detected, such as copying to another paper.

  Further, the present invention is a program, which images a printing layer printed on the surface of a photographic paper on which a predetermined printing content is printed, and a pattern layer on the inner surface of the photographic paper, Extracting the imaged features of the print layer as first feature information, extracting the features of the pattern layer as second feature information, the first feature information and the second feature information, The information registered as a reference for identifying the photographic paper is collated.

  Therefore, this program can detect changes in the print contents and the photographic paper base paper, so that the print contents printed on the print paper at the time of issuance can be replaced with other print contents, and the print paper can be separated. A wide variety of alterations can be detected, such as copying on paper.

  As described above, according to the present invention, the image layer printed on the surface of the photographic paper and the pattern layer on the inner surface of the photographic paper are imaged, and the characteristics of the imaged print layer and the pattern layer are respectively described. By extracting the first feature information and the second feature information as the first feature information and the second feature information, the first feature information and the second feature information are collated with information registered as a reference for identifying the photographic paper. Since it is possible to detect the photographic contents and the property changes of the photographic paper base, it is possible to detect a wide variety of alterations, thus realizing a verification device, a verification method, and a program that can improve the reliability of the photographic paper. .

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

(1) Configuration of Identification Device According to this Embodiment In FIG. 1, reference numeral 1 denotes the overall configuration of an identification system according to this embodiment, which is issued by an issuing device 2 that issues a certificate WRT and issued by the issuing device 2 And a verification device 3 that verifies the certificate WRT.

  In the case of this embodiment, the issuing device 2 uses personal information such as characters (hereinafter referred to as personal identification characters) PR and photographs PT, for example, for identifying individuals as paper (hereinafter referred to as certification). This is called a base paper) and printed on ST to create a certificate WRT.

  At this time, the issuing device 2 uses information representing the characteristics of the photograph PT (hereinafter referred to as photograph feature data) as an identifier of the photograph PT and the base paper ST itself, and a complicated entanglement of fibers in the base paper ST. Generating the information (hereinafter referred to as pattern feature data) representing the characteristic of the unique pattern (hereinafter referred to as pattern) configured in the above, and the identifier of the entire certificate WRT including the photograph PT and the base paper ST As a result, information representing the characteristics of the certificate WRT (hereinafter referred to as certificate characteristic data) is generated and printed on the certificate WRT as a two-dimensional barcode (hereinafter referred to as an identification code) DS. It is made to register by doing.

  On the other hand, the verification device 3 detects the presence or absence of alteration in the certificate WRT based on the identification code DS attached to the certificate WRT.

(2) Configuration of issuing device As shown in FIG. 2, the issuing device 2 has an operation unit 12, a display unit 13, and a predetermined storage medium for a control unit 11 that controls the entire issuing device 2. An input interface 14 for inputting data stored in the image or data captured by an electronic camera, a pattern acquisition unit 15 for acquiring a pattern on the base paper ST, a data processing unit 16 for performing various data processing, and the base paper ST. A certificate issuing unit 17 that is issued as a certificate WRT and a physical property measuring device 18 that measures the whiteness and diffuse reflectance of paper are connected to each other.

  The control unit 11 includes a CPU (Central Processing Unit), a ROM (Read Only Memory) storing various information such as programs and setting information, and a RAM (Random Access Memory) as a work memory. When a certificate issuance command is given from the operation unit 12 in response to a user operation, an input screen for personally specified characters such as name, date of birth, and address is displayed on the display unit 13.

  Then, when the personal identification character data D1 representing the personal identification character is given from the operation unit 12, the control unit 11 sends the personal identification character data D1 to the certificate issuing unit 17, and stores the program stored in the ROM and Based on the setting information and the like, the certificate issuing process is executed by appropriately controlling the input interface 14, the pattern obtaining unit 15, the data processing unit 16, the certificate issuing unit 17, and the physical property measuring device 18.

  In this case, the input interface 14 reads, for example, data of the photo PT (hereinafter referred to as photo data) D2 corresponding to the personally specified character stored in the memory stick (Sony registered trademark), and this is read out by the data processing unit 16. And sent to the certificate issuing unit 17.

  On the other hand, the pattern acquisition unit 15 irradiates the base paper ST placed on the document table with light, and forms pattern projection light obtained by passing through the base paper ST on the solid-state image sensor via the optical system. Then, the pattern acquisition unit 15 performs various processes such as A / D (Analog / Digital) conversion processing on the pattern image signal output from the solid-state imaging device, and the pattern image data D3 obtained as a result thereof is a data processing unit. 16 to send.

  The pattern obtaining unit 15 sets the base paper ST placed on the document table at the print position in the certificate issuing unit 17 by the feeding mechanism.

  The data processing unit 16 uses, for example, the kurtosis, the average value, and the distortion of the luminance distribution as a luminance value distribution pattern for each pixel in the photographic data D2 supplied from the input interface 14 (hereinafter referred to as a luminance distribution pattern). The degree, the variance value, or a combination thereof is detected, and the detection result is sent to the certificate issuing unit 17 as the photograph feature data D4.

  In addition, the data processing unit 16 performs a predetermined pattern extraction process on the pattern image data D2 supplied from the pattern acquisition unit 14, thereby extracting a pattern (hereinafter referred to as a pattern pattern). This pattern pattern is extracted by, for example, a pattern extraction process described later. Then, the data processing unit 16 generates this pattern pattern as pattern feature data D5 and sends it to the certificate issuing unit 17.

  The certificate issuing unit 17 temporarily stores and holds the pattern feature data D5 and the photograph feature data D4 supplied from the data processing unit 16 in an internal memory (not shown). Further, the certificate issuing unit 17 is based on the personal identification character data D1 supplied from the control unit 11 and the photograph data D2 supplied from the input interface unit 14, and the paper surface of the base paper ST set at a predetermined printing position. The personal identification character PR and the photograph PT (FIG. 1) are respectively printed at predetermined positions, and the certificate WRT (FIG. 1) created as a result of the printing is set at the measurement position in the physical property measuring instrument 18 by the feeding mechanism. To do.

  The physical property measuring device 18 measures the whiteness and diffuse reflectance of a predetermined area in the certificate WRT set at the measurement position, and uses the measured whiteness and diffuse reflectance as certificate feature data D6 to issue a certificate issuing unit. 17 to send. Thereafter, the physical property measuring device 18 sets the certificate WRT set at the measurement position again at the print position in the certificate issuing unit 17 by the feeding mechanism.

  Upon receiving the certificate feature data D6 from the physical property measuring instrument 18, the certificate issuing unit 17 reads the pattern feature data D5 and the photograph feature data D4 temporarily stored in an internal memory (not shown), and the photograph A digital watermarking process for embedding the feature data D4 and the certificate feature data D6 at a predetermined embedding position in the pattern feature data D5 is performed.

  Then, the certificate issuing unit 17 performs two-dimensional barcode conversion processing on the pattern feature data in which the photograph feature data D4 and the certificate feature data D6 are embedded by the digital watermark processing (hereinafter referred to as feature data). To generate identification code data, and an identification code DS (FIG. 1) based on the identification code data is printed at a predetermined position on the paper surface of the certificate WRT set at the printing position.

  In this way, the control unit 11 executes the certificate issuance process, thereby creating a certificate WRT in which the personal specific character PR and the photograph PT are printed on the base paper ST (FIG. 1) and identifying the certificate WRT. The code DS can be attached.

(3) Specific Processing of Pattern Extraction Processing Here, an example of pattern extraction processing by the data processing unit 16 will be described in detail. In the pattern extraction process, when the contents are functionally classified, as shown in FIG. 3, a low-frequency component that extracts a low-frequency component pattern image (hereinafter referred to as a low-frequency pattern image) from the pattern image. An image that separates the low-frequency pattern image into an image with a low luminance component (hereinafter referred to as a black component pattern image) and an image with a high luminance component (hereinafter referred to as a white component pattern image). A separation unit 16B, a region division unit 16C that divides the pattern included in the black component pattern image and the white component pattern image into a plurality of regions, and a pattern pattern extraction unit 16D that extracts the feature amount of each region as a pattern pattern And can be divided into

(3-1) Low-frequency component extraction process The low-frequency component extractor 16A, for example, as shown in FIG. 4, generates a low-frequency component pattern from the pattern image IM1 (FIG. 4A) of the base paper ST (FIG. 4). An image IM2 (FIG. 4B) is extracted.

  Specifically, the low frequency component extraction unit 16A cuts out a pattern image at a position based on the region position information stored in the internal memory from the pattern image of the pattern image data D2 supplied from the pattern acquisition unit 14, and extracts the pattern image. The frequency component data is generated by subjecting the data of the pattern image IM1 to Fourier transform processing.

  Then, the low-frequency component extraction unit 16A performs an inverse Fourier transform process on the data of the frequency component after setting the data value of the high-frequency component equal to or greater than a predetermined threshold to “0”, thereby generating the low-frequency component pattern image IM2. Data (hereinafter referred to as low-band pattern image data) D11 is generated and sent to the image separation unit 16B.

  In this way, the low frequency component extraction unit 16A extracts the low frequency component pattern image IM2, and thus various noise components generally included in the high frequency components of the image, such as noise of the solid-state image sensor in the pattern acquisition unit 14, for example. Has been made so that it can be removed.

  As a result, the low frequency component extraction unit 16A can avoid a decrease in pattern pattern (feature amount) extraction accuracy in the pattern pattern extraction unit 16D due to various noise components.

(3-2) Image Separation Processing As shown in FIG. 5, for example, the image separation unit 16B converts the low-frequency component pattern image IM2 (FIG. 5A) into a white component pattern image WIM (FIG. 5B). The black component pattern image BIM (FIG. 5C) is separated.

  Specifically, the image separation unit 16B sequentially detects the luminance value of the low frequency component pattern image IM2 of the low frequency pattern image data D11 supplied from the low frequency component extraction unit 16A for each pixel, and the detection result is a predetermined value. A white component pattern image WIM (in which a pixel other than a pixel having a luminance value equal to or lower than a high luminance threshold (hereinafter referred to as a white threshold) (hereinafter referred to as a white pixel) is converted to the lowest luminance level. 5B) is extracted, and is sent to the area dividing unit 16C as white component pattern image data D12.

  The image separation unit 16B also detects a pixel (hereinafter referred to as a pixel) having a luminance value at which the luminance value detection result of each pixel in the low-frequency component pattern image IM2 is equal to or higher than a predetermined low luminance threshold (hereinafter referred to as a black threshold). The black component pattern image BIM (FIG. 5C) is extracted by converting the pixels other than (referred to as black pixels) to the highest luminance level, and this is extracted as the black component pattern image data D13 and the area dividing unit 16C. To be sent to.

  In this way, the image separation unit 16B separates the low-frequency component pattern image IM2 into the white component pattern image WIM (FIG. 5B) and the black component pattern image BIM (FIG. 5C), thereby providing a pattern. The degree of complexity can be reduced.

  As a result, the image separation unit 16B can avoid a decrease in the pattern pattern (feature amount) extraction accuracy in the pattern pattern extraction unit 16D due to the high degree of complexity.

(3-3) Area division processing As shown in FIG. 5, the area division unit 16C uses the pattern of the white component pattern image WIM (FIG. 5B) as a unit of a set of adjacent white pixels. Area (hereinafter referred to as a white dama) to be divided, and a pattern having a black component pattern image BIM (FIG. 5C) in units of a set of adjacent black pixels (hereinafter referred to as this). It is divided into black dama).

  Specifically, the area dividing unit 16C detects all white pixels from the white component pattern image WIM (FIG. 5B) of the white component pattern image data D12 supplied from the image separation unit 16B, and then detects the white pixels shown in FIG. As shown in A), a total of 8 pixels (hereinafter referred to as 8 neighboring pixels) of 4 pixels vertically and horizontally adjacent to an arbitrary pixel of interest AP and 4 pixels diagonally are connected sequentially. Go.

Then, for example, as shown in FIG. 6B, the area dividing unit 16C associates the identification information with the white pixel group that has been connected so far when the white pixel is no longer detected in the 8 neighboring pixels, and the white dama WD. ₁ , WD ₂ ..., And WD _n . As a result, as shown in FIG. 7A, for example, the pattern included in the white component pattern image WIM (FIG. 5B) is divided into a plurality of white damascene WDs (WD _{1 to} WD _n ).

Next, as shown in FIG. 7B, the area dividing unit 16C removes a dama that is equal to or less than a predetermined number of connections from each white dama WD (hereinafter referred to as a small dama), and removes the dama. The obtained white dama WD (WD _{1 to} WD _n ) is sent to the pattern pattern extraction unit 16D as data (hereinafter referred to as white dama data) D14.

Further, the area division unit 16C also sets the black component pattern image BIM (FIG. 5C) of the black component pattern image data D13 supplied from the image separation unit 16B as the white component pattern image WIM (FIG. 5B). Similarly, after forming a plurality of black dams BD (BD _{1 to} BD _n ), the small dams are removed, and the black dams BD (BD _{1 to} BD _n ) obtained as a result of the removal are used as data (hereinafter referred to as black). The data is sent to the pattern pattern extraction unit 16D as D15).

In this way, the area dividing unit 16C divides the pattern included in the white component pattern image WIM (FIG. 5B) into a plurality of white damascene WDs (WD _{1 to} WD _n ) and the black component pattern image BIM ( By dividing the pattern shown in FIG. 5C into a plurality of black dams BD (BD _{1 to} BD _n ), the pattern can be subdivided.

  As a result, the area dividing unit 16C can avoid a decrease in pattern pattern (feature amount) extraction accuracy in the pattern pattern extracting unit 16D.

(3-4) Pattern Pattern Extraction Processing The pattern pattern extraction unit 16D extracts feature amounts representing shapes in the white dama WD (WD _{1 to} WD _n ) and the black dama BD (BD _{1 to} BD _n ) as a pattern pattern. To do.

  In practice, in the pattern pattern extraction unit 16D, it is difficult to make the white dama WD and the black dama BD as they are as they are because the shapes of the white dama WD and the black dama BD are complicated. Each of the white dama WD and the black dama BD is approximated to a rectangle, for example.

That is, as shown in FIG. 8, the pattern pattern extraction unit 16D, for each white dama WD (WD _{1 to} WD _n ) of the white dama data D14 supplied from the area division unit 16C, the center coordinates (x _c ) in the white dama , y _c ), the long side l, the short side w, and the angle θ between the long side l and the horizontal axis are calculated as feature quantities.

Similarly, the pattern pattern extraction unit 16D also features the black dama data BD (BD _{1 to} BD _n ) of the black dama data D15 supplied from the area division unit 16C in the same manner as the white dama WD (WD _{1 to} WD _n ). Is calculated.

Then, the pattern pattern extraction unit 16D uses, as the pattern feature data D5, the feature amounts of the white dama WD (WD _{1 to} WD _n ) and the black dama BD (BD _{1 to} BD _n ) (hereinafter referred to as pattern feature amounts). The certificate is issued to the certificate issuing unit 17 (FIG. 2).

  In this way, the data processing unit 16 executes the pattern extraction process, and can specify the characteristic pattern of the pattern included in the pattern image IM1 (FIG. 4A) as the shape value.

(4) Configuration of Verification Device Next, the configuration of the verification device 3 will be described. As shown in FIG. 9, the verification device 3 has an operation unit 32 and a physical property measuring device 33 that measures the whiteness and diffuse reflectance of the paper with respect to the control unit 31 that controls the verification device 3 as a whole. A certificate imaging unit 34 that images the certificate WRT, and a restoration processing unit 35 that restores feature data (data in which the photographic feature data D4 is embedded in the pattern feature data D5) from the captured identification code DS. The feature extraction unit 36 that extracts the photographed photograph PT and pattern features and the synthesis unit 37 that synthesizes the extracted features are connected to each other.

  The control unit 31 includes a CPU, a ROM that stores various information such as programs and setting information, and a RAM as a work memory. A verification command is given from the operation unit 32 in response to a user operation. Based on the program and setting information, the physical property measuring device 33, the certificate imaging unit 34, the restoration processing unit 35, the feature extraction unit 36, and the synthesis unit 37 are appropriately controlled to execute verification processing.

  In this case, the physical property measuring device 33 measures the whiteness and diffuse reflectance of a predetermined area in the certificate WRT set at the measurement position, and synthesizes the measured whiteness and diffuse reflectance as the certificate feature data D21. To the unit 37. Thereafter, the physical property measuring device 33 sets the certificate WRT set at the measurement position at the imaging position in the certificate imaging unit 34 by the feeding mechanism.

  The certificate imaging unit 34 images the surface layer and the inner layer in the certificate WRT set at the imaging position.

  Specifically, for example, as shown in FIG. 10, the certificate imaging unit 34 includes a first light source 34A for transmission (hereinafter referred to as a light source for transmission) provided at different positions, and a reflection light source 34A. A second light source (hereinafter referred to as a reflection light source) 34B, and irradiates light from a transmission light source 34A to a certificate WRT placed on a document table (not shown). The pattern projection light obtained by passing through the book WRT is imaged on the solid-state imaging device 34C via the optical system. The certificate imaging unit 34 performs various processes such as an A / D (Analog / Digital) conversion process on the pattern image signal obtained from the solid-state image sensor 34C, and features the pattern image data D22 obtained as a result. The data is sent to the extraction unit 36.

  On the other hand, the certificate imaging unit 34 irradiates the certificate WRT placed on the document table with light from the reflection light source 34B, and the personal specific characters PR, the photograph PT, and the identification code DS on the surface of the certificate WRT. Is reflected on the solid-state image sensor 34C via an optical system. Then, the certificate imaging unit 34 performs A / D conversion processing or the like on the surface layer image signal obtained from the solid-state imaging device 34C, and sends the surface layer image data D23 obtained as a result to the data restoration processing unit 35.

  The restoration processing unit 35 (FIG. 10) cuts out the data of the photo PT and the data of the identification code DS from the surface layer image data D23, and uses the cut out photo PT data as photo data D24 to the feature extraction unit 36. Send it out.

  Further, the restoration processing unit 35 performs feature data (pattern feature data D5 (FIG. 2), photo feature data D4 (FIG. 2), and certificate feature) by performing two-dimensional barcode restoration processing on the data of the identification code DS. Data D6 (data in which data D6 (FIG. 2) is embedded) D25 is generated and sent to the control unit 31.

  The feature extraction unit 36 performs the same process as the pattern extraction process in the data processing unit 16 (FIG. 2) on the pattern image data D22 supplied from the certificate imaging unit 34, thereby expressing the feature of the pattern. The pattern feature data D26 is generated and sent to the synthesis unit 37.

  The feature extraction unit 36 generates a luminance distribution pattern in the photographic data D24 as photographic feature data D27 based on the photographic data D24 supplied from the restoration processing unit 35, similarly to the data processing unit 16 (FIG. 2). This is sent to the synthesis unit 37.

  Then, the synthesizer 37 embeds the photograph feature data D27 and the certificate feature data D21 supplied from the physical property measuring device 33 in a predetermined embedding position in the pattern feature data D26 in the same manner as the certificate issuer 17. The pattern feature data D26 in which the photograph feature data D27 and the certificate feature data D21 are embedded is generated as data to be compared with the feature data D25 (hereinafter referred to as comparison feature data) D28, and this is generated as a control unit. 31.

  In this way, the control unit 31 controls the physical property measuring device 33, the certificate imaging unit 34, the restoration processing unit 35, and the feature extraction unit 36, thereby receiving the feature data D25 from the restoration processing unit 35 and the combining unit 37. When the comparison feature data D28 is received from these, they are collated.

  Here, when a value lower than the predetermined matching degree is obtained as a result of this collation, this means that the photo PT at the time of issuance is replaced with another photo, or the certificate WRT at the time of issuance is duplicated. This means that the certificate WRT has been altered.

  Therefore, the control unit 31 determines that the certificate WRT has not been tampered with when the collation result is obtained as a value equal to or greater than the predetermined matching degree, and the collation result is a predetermined match. If it is obtained as a value less than the degree, it is determined that the certificate WRT has been altered.

  In this way, the verification device 3 can detect the presence / absence of alteration in the certificate WRT based on the identification code DS of the certificate WRT.

(5) Operation and Effect In the above configuration, the verification device 3 includes the photograph PT (FIG. 10) printed on the surface of the certificate WRT (FIG. 1) and the pattern on the inner surface of the certificate WRT. Photograph feature data D27 (FIG. 9) representing a luminance distribution pattern in the photographed photograph PT data is generated, and pattern feature data D26 (FIG. 9) representing a pattern pattern in the photographed pattern data. Is generated.

  Then, the verification device 3 collates these two feature data D26 and D27 with information obtained from the identification code DS added in advance to the certificate WRT in order to identify the certificate WRT.

  Therefore, since this verification apparatus 3 can detect the property change of the base paper ST (FIG. 1) of the photograph PT and the certificate WRT, the photograph PT of the certificate WRT at the time of issuance is replaced with another photograph. It is also possible to detect a wide variety of alterations such as copying the certificate WRT to another paper.

  Further, the verification device 3 in this embodiment combines the two feature data D26 and D27 as the comparison feature data D28. Specifically, the photographic feature data is placed at a predetermined embedding position in the pattern feature data D26. Comparison feature data D28 is generated by embedding D27.

  Therefore, in the verification device 3, since the data change is emphasized by combining the pattern feature data D26 and the photograph feature data D27, for example, the photograph PT of the certificate WRT is one of the twins, and the photograph PT is the other of the twins. Even if it is a clever alteration that does not appear as a change in the photographic feature data D27 even if the replacement is performed, such as a replacement, this can be detected.

  Further, the verification device 3 in this embodiment generates physical property data D21 (FIG. 9) representing the whiteness and diffuse reflectance in the certificate WRT, and this is combined with the predetermined feature embedding in the pattern feature data D26 together with the photographic feature data D27. Embed in the position.

  Therefore, the verification device 3 can detect not only the property change of the photograph PT and the paper itself, but also the property change of the certificate WRT as a whole on which the photo PT is printed. be able to.

  According to the above configuration, the photograph feature data D27 (FIG. 9) in the photograph PT printed on the surface of the certificate WRT and the pattern feature data D26 in the pattern on the inner surface of the certificate WRT are generated, and these are generated. In order to identify the certificate WRT, the property of the base paper ST (FIG. 1) of the photograph PT and the certificate WRT is obtained by collating with the information obtained from the identification code DS added in advance to the certificate WRT. Therefore, a wide variety of alterations can be detected, and thus the reliability of the certificate WRT can be improved.

(6) Other Embodiments In the above-described embodiment, the certificate WRT in which the photograph PT and the personal identification character PR are printed on the base paper ST is applied as the photographic paper on which the predetermined printing content is printed. However, the present invention is not limited to this, and money, a license, an event ticket, a picture, a check, or the like can be applied. In short, various photographic papers used as various media such as merchandise exchange media, content certification media, or information storage media can be widely applied.

  In the above-described embodiment, the case where the photograph PT is simply printed on the base paper ST has been described. However, the present invention is not limited to this, and the photograph PT printed on the base paper ST reflects the visible light. It may be concealed with a dye.

  Specifically, for example, as shown in FIG. 11A, predetermined dyes Dy1 and Dy2 are further printed on the photograph PT printed on the certificate WRT. In this case, since the dyes Dy1 and Dy2 reflect visible light in a normal state such as a room, the certificate WRT is a photograph PT printed on the base paper ST as shown in FIG. 11B. Will not be visible. On the other hand, the certificate image pickup unit 34 (FIG. 9) of the verification apparatus 3 can be used on the photograph PT by irradiating infrared light from the reflection light source 34B (FIG. 10) as shown in FIG. 11C. Even if the dyes Dy1 and Dy2 are printed on the photo PT, the photograph PT can be taken.

  In this way, if the photo PT is concealed with a dye that reflects visible light, it is possible to prevent alteration of the certificate WRT, such as replacing the photo PT, thus further preventing impersonation. Can do.

  Furthermore, in the above-described embodiment, as shown in FIG. 10, as the imaging means for imaging the printing layer printed on the surface of the printing paper and the pattern layer on the inner surface of the printing paper, the reflection light source 34B The surface layer reflected light obtained by reflecting the personal identification character PR, photograph PT and identification code DS on the surface of the certificate WRT is imaged as surface layer image data D23, and the certificate WRT is transmitted from the transmission light source 34A. However, the present invention is not limited to this, and the pattern layer may be divided into two layers for imaging.

  Specifically, instead of the transmission light source 34A, a first light source and a second light source that irradiate light having wavelengths with different reach depths are provided, and the first light source has a first reach depth. The reflected pattern projection light and the pattern projection light reflected from the second light source at the second arrival depth are respectively imaged as data. If a pattern pattern is extracted from each data and used as a collation target, spoofing can be further prevented.

  Further, in the above-described embodiment, the case where the physical property measuring device 33 for measuring the whiteness and the diffuse reflectance is applied as the physical property measuring means for measuring the physical property of the photographic paper has been described. For example, a physical property measuring instrument that measures various other physical properties such as weight, smoothness, air permeability, thickness, color, basis weight, drawing property or friction, or a combination thereof can be applied. .

  Further, in the above-described embodiment, the case where the kurtosis, average value, skewness, variance value, or combination thereof of the luminance distribution is extracted as the characteristics of the print layer has been described. Statistical elements such as color difference distribution and power spectrum distribution may be extracted instead of the luminance distribution.

  Furthermore, in the above-described embodiment, as a feature of the pattern layer, a case where extraction is performed by sequentially performing low frequency component processing, image separation processing, area division processing, and pattern pattern extraction processing has been described. The present invention is not limited to this, and the processing can be appropriately selected and a new processing may be added.

  Also, instead of such image separation processing, region division processing, and pattern pattern extraction processing, the remaining pixels other than the minimum and maximum points are closest among all the pixels of the pattern image obtained as a result of the low frequency component processing. The features of the pattern layer may be extracted by performing a Voronoi division process that divides the pattern image into a plurality of regions by assigning them as belonging to the minimum point and the maximum point existing in the distance. For details of this Voronoi division processing, refer to PCT / JP2005 / 001176.

  Further, in the above-described embodiment, as the synthesizer for synthesizing the first feature information and the second feature information, the photographic feature data D27 (and the certificate feature data D21) at a predetermined embedding position in the pattern feature data D26. However, the present invention is not limited to this. For example, the photograph feature data D27 (and certificate feature data D21) is added to the head portion of the pattern feature data D26. May be. In the present invention, for example, the pattern feature data D26 and the photograph feature data D27 (and the certificate feature data D21) are cut out at a predetermined interval, and the cut out pattern feature data D26 and the photograph feature data D27 (and the certificate feature data D21) are extracted. And may be connected alternately. In short, it is only necessary that the pattern feature data D26 and the photographic feature data D27 can be synthesized according to a predetermined rule.

  Further, in the above-described embodiment, the certificate WRT uses the information (pattern feature data D5, photo feature data D4, and certificate feature data D6) collated with the first feature information and the second feature information as an identification code DS. Although the case of printing and registering (FIG. 1) has been described, the present invention is not limited to this, and a hole or Braille corresponding to the information may be provided in the certificate WRT, or the information May be directly described in the certificate WRT.

  Further, in the above-described embodiment, the case where the certificate WRT is printed and registered as the registration target has been described. However, the present invention is not limited to this, and an EEPROM (Electrically Erasable Programmable Read-Only Memory). Or you may make it register by memorize | storing in storage media, such as HDD (Hard Disk Drive).

  The present invention can be used when paper is used as various media such as commodity exchange media such as money, content certification media such as certificates, or information storage media such as personal works.

It is a basic diagram which shows the whole structure of the identification system by this Embodiment. It is a block diagram which shows the structure of an issuing apparatus. It is a functional block diagram which shows the pattern extraction process. It is a basic diagram with which it uses for description of extraction of a low frequency component. It is an approximate line figure used for explanation of separation of an image. It is an approximate line figure used for explanation of the division of white dama (black dama). It is a basic diagram with which it uses for description of the removal of small lumps. It is an approximate line figure used for explanation of calculation of a feature-value. It is a block diagram which shows the structure of a verification apparatus. It is a basic diagram with which it uses for description of imaging of a surface layer and an inner layer. It is a basic diagram used for description of concealment of a photograph.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Identification system, 2 ... Issuing device, 3 ... Verification device, 11, 31 ... Control part, 12, 32 ... Operation part, 13 ... Display part, 14 ... Input interface, 15 ... Pattern Acquiring unit, 16 ... Data processing unit, 17 ... Certificate issuing unit, 18, 33 ... Physical property measuring device, 34 ... Certificate imaging unit, 35 ... Restoration processing unit, 36 ... Feature extraction unit, 37 ...... Compositing unit, D1 ... Personal character data, D2, D24 ... Photo data, D3, D22 ... Pattern image data, D4, D27 ... Photo feature data, D5, D26 ... Pattern feature data, D6, D21 …… Certificate feature data, D23 …… Surface image data, D25 …… Feature data, D28 …… Comparison feature data, PR …… Personal character, PT …… Photo, ST …… Base paper, WRT …… Certificate , DS …… Identification code.

Claims (8)

Imaging means for imaging a print layer printed on the surface of the photographic paper on which predetermined print content is printed, and a pattern layer on the inner surface of the photographic paper;
Extraction means for extracting the features of the print layer imaged by the imaging means as first feature information, and extracting the features of the pattern layer imaged by the imaging means as second feature information;
A verification apparatus comprising: a verification unit that collates the first characteristic information and the second characteristic information with information registered as a reference for identifying the photographic paper. A synthesis means for synthesizing the first feature information and the second feature information;
The verification means is
The verification apparatus according to claim 1, wherein the combined information combined by the combining unit is collated with information registered as a reference for identifying the photographic paper. Comprising physical property measuring means for measuring physical properties of the photographic paper,
The verification means is
The first characteristic information, the second characteristic information, and the physical property information representing the physical properties are collated with information registered as a reference for identifying the photographic paper. Verification device. The imaging means is
The verification apparatus according to claim 1, wherein a first pattern layer and a second pattern layer that are different from each other are imaged as the pattern layer on the inner surface of the photographic paper. The verification apparatus according to claim 1, wherein the information collated with the first feature information and the second feature information is registered in the photographic paper. The verification apparatus according to claim 1, wherein the print layer is concealed with a dye that reflects visible light. A first step of imaging a print layer printed on the surface of a photographic paper on which a predetermined print content is printed, and a pattern layer on the inner surface of the photographic paper;
Extracting a feature of the imaged print layer as first feature information and extracting a feature of the imaged pattern layer as second feature information;
A verification method comprising: a third step of collating the first feature information and the second feature information with information registered as a reference for identifying the photographic paper. Against the computer,
Imaging a print layer printed on the surface of a photographic paper on which a predetermined print content is printed, and a pattern layer on the inner surface of the photographic paper;
Extracting the imaged feature of the print layer as first feature information and extracting the imaged feature of the pattern layer as second feature information;
A program for causing the first feature information and the second feature information to be collated with information registered as a reference for identifying the photographic paper.