JP4661107B2 - Tag creation method, tag creation device, tag, and article management system - Google Patents

Tag creation method, tag creation device, tag, and article management system Download PDF

Info

Publication number
JP4661107B2
JP4661107B2 JP2004194939A JP2004194939A JP4661107B2 JP 4661107 B2 JP4661107 B2 JP 4661107B2 JP 2004194939 A JP2004194939 A JP 2004194939A JP 2004194939 A JP2004194939 A JP 2004194939A JP 4661107 B2 JP4661107 B2 JP 4661107B2
Authority
JP
Japan
Prior art keywords
tag
area
information
image
region
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
JP2004194939A
Other languages
Japanese (ja)
Other versions
JP2006018525A (en
Inventor
健介 伊藤
哲也 木村
正 清水
伸一 矢田
Original Assignee
富士ゼロックス株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 富士ゼロックス株式会社 filed Critical 富士ゼロックス株式会社
Priority to JP2004194939A priority Critical patent/JP4661107B2/en
Publication of JP2006018525A publication Critical patent/JP2006018525A/en
Application granted granted Critical
Publication of JP4661107B2 publication Critical patent/JP4661107B2/en
Application status is Active legal-status Critical
Anticipated expiration legal-status Critical

Links

Images

Description

  The present invention relates to a tag attached to various articles, and more particularly to a tag creation method, a tag creation apparatus, a tag, and an article management system to which the tag is attached.

  In recent years, not only banknotes and securities, but also various documents such as passports, various titles, and various lighting documents have been copied along with improvements in the performance of copying machines and printers and personal computers. The possibility is increasing, and it is desired to establish a technique that can determine the authenticity of various documents with high accuracy.

  Conventionally, in industrial products including so-called brand products, imitation products may be manufactured and distributed, and in such imitation products, tags may be copied using a copying machine or a printer. Done. In addition, in agricultural products, there are an increasing number of cases where tags are forged for the purpose of displaying false information such as production areas.

  From this, a hologram representing the product data is created by a computer, and the authenticity of the product can be determined by embedding the created hologram around the mark that makes this product identifiable. And proposals for preventing imitation have been made (for example, see Patent Document 1).

  In addition, an identification element provided with a memory capable of reading stored information by electromagnetic induction action is provided in the brand mark body of the product, and the original information held by the mark body is stored in the memory, thereby enabling product verification. Thus, there has been proposed a product matching system that prevents counterfeiting (see, for example, Patent Document 2).

  On the other hand, various products are attached with labels and tags that record information about the products at the time of manufacture. From here, for example, the adhesive surface of the adhesive paper forming the label is printed with functional ink. Proposals have been made so that the authenticity of the label can be confirmed when a predetermined instrument is used or in an environment (see, for example, Patent Document 3).

  In addition, erasable and writable rewritable labels are used as purchase forms and shipping forms that cannot be tampered with, and serial numbers cannot be erased on rewritable labels. Has been proposed to prevent false display by writing a part of the contents of the purchase form and new product information and serial number into the shipping form so as not to be tampered (see, for example, Patent Document 4). .)

  However, these proposals require creation of holograms and special printing, and require relatively expensive parts such as IC tags and rewritable labels. Moreover, although cost and special work are required, it cannot always be said that accurate imitation prevention and false display are possible.

  That is, labels and tags attached to merchandise are the lowest cost by using paper, but in comparison with this, any proposal will increase the cost.

When using paper, use the fact that the transparency of the paper changes randomly due to the random nature of the fiber material that forms the paper, and divide the predetermined area of the tag into a number of square areas Of these, the transparency of six rectangular areas selected at random is detected, and the detected transparency is stored as information together with the address of the quadrangular area. When authenticity is determined, individual transparency specified by the recording information is stored. A proposal has been made to detect authenticity by detecting a rectangular area and comparing the detection result with the transparency represented by the recorded information (see, for example, Patent Document 5).
Japanese Patent Laid-Open No. 2001-100533 JP 2002-117165 A JP 2002-103782 A JP 2004-94510 A Japanese Examined Patent Publication No. 6-16312

  However, the proposal of Patent Document 5 has a problem that the authenticity determination must be performed using separately recorded information, and the authenticity determination cannot be performed with a simple operation at an arbitrary timing. That is, the authenticity determination has a problem that the authenticity determination cannot be performed unless specific data exists or the data is not readable.

  The present invention has been made in view of the above facts, a tag creation method, a tag creation device, and a tag creation method that can determine the authenticity of a corresponding article at any timing using tags attached to articles such as various products. The purpose is to propose a tag and a parts management system using the tag.

  The present invention relates to various articles such as industrial products, agricultural products, documents, certificates, etc., for each article, a package in which articles are individually packaged, and a package in which a plurality of articles are packaged together (hereinafter collectively referred to as a collective article). By using the tag attached to the tag, it is determined whether the tag is the original article indicated by the tag. That is, whether a tag is attached to an article, a packaged item, or a packaged item based on whether the tag includes original information or not, and whether the item to which the tag is attached is a so-called genuine item or a so-called fake item It is possible to determine whether it is a counterfeit product or the like.

  At this time, according to the present invention, the random characteristics of the individual such as paper forming the tag are read from the individual and recorded as individual information on the individual. When determining the authenticity of a tag, use the solid information recorded for each individual in advance by judging whether the individual information recorded in the tag is included in the individual forming the tag. In addition, it is possible to accurately determine the authenticity of the tag.

Further, the tag of the present invention is formed by an individual characteristic having randomness along the surface are distributed by a tag attached to an article, comprising a first region set on the solid surface A second area that is larger than the first area is provided as a non-image portion, and an individual information image that enables identification of the individual based on a feature indicating the first area read from the first area is provided It is characterized by being formed.

Such a tag producing apparatus applied to the present invention is a first method for reading a characteristic having randomness distributed along the individual surface used for producing a tag attached to an article over a first region of the individual surface. Area reading means, read information converting means for converting image information indicating the first area read by the first area reading means as individual information that is information specific to the individual, and the first information on the individual surface. A second area set to a predetermined range larger than the first area including the first area is defined as a non-image area, and an individual information image indicating the individual information converted by the read information conversion unit is displayed on the individual surface. And image forming means to be formed.

In such an article management system using a tag to which the present invention is applied, the second area larger than the first area including the first area set on the individual surface where the characteristics having randomness are distributed. An article to which an area is provided as a non-image portion, and a tag on which an individual information image that enables identification of the individual is formed based on a feature indicating the first area read from the first area is attached An article management system to be managed, wherein the feature of the individual surface of the second area, the reading means for reading the individual information image, the feature of the second area read by the reading means, and the individual information said first region specified information converting means for converting the individual information to the comparably information, by the individual information from the information converted by the information converting unit based on the image, before The calculation of the correlation value between the first area extracted from the second area and the third area having the same size is repeated while moving the extraction position of the third area within the second area. The calculation means and the calculated maximum value of the plurality of correlation values are equal to or greater than the first predetermined value, and a value obtained by subtracting the average value of the correlation values from the maximum value of the correlation values is divided by the standard deviation of the correlation values. It is the normalized score of the maximum value of the correlation values obtained by, based on whether the second predetermined value or more, collates whether the first area is included in the second region, matching Determination means for determining the authenticity of the tag based on the result, and the authenticity of the article can be determined based on the determination result of the determination means .

  In this article management system, when the individual information is encrypted and the individual information image is formed on the individual, the conversion unit can include a decryption unit for the encryption.

Further, the article management system includes a tag information image based on tag information that enables the tag to be specified for the individual, and includes registration holding means for registering and holding the individual information together with the tag information. The reading unit reads the tag information image and whether the tag is registered in the holding unit based on the tag information indicated in the tag information image read by the checking unit by the reading unit. Any device may be used as long as it can determine the authenticity of the article, and the collating unit can collate the individual information registered in the registration holding unit with the characteristics of the second region. In such a true / false determination apparatus applied to the present invention, the second region larger than the first region including the first region set on the individual surface on which the random feature is distributed is non- Authenticity determination for determining authenticity of a tag provided with an individual information image that is provided as an image portion and that enables identification of the individual based on a feature indicating the first region read from the first region A device, a feature of the individual surface of the second region, a reading control means for controlling a reading means for reading the individual information image, a feature of the second region read by the reading means, Information conversion means for converting individual information based on the individual information image into comparable information, the first area specified by the individual information from the information converted by the information conversion means, and the second Calculating means for calculating a correlation value between the first area extracted from the area and a third area of the same size while moving the extraction position of the third area within the second area; The maximum value of the plurality of calculated correlation values is equal to or greater than a first predetermined value, and the value obtained by subtracting the average value of the correlation values from the maximum value of the correlation values is divided by the standard deviation of the correlation values. Whether or not the first area is included in the second area based on whether or not the normalized score of the maximum correlation value is greater than or equal to a second predetermined value, and based on the matching result Determining means for determining the authenticity of the tag. The tag management system using the tag creation device, the tag, and the authenticity determination device to which the present invention is applied has a feature having randomness distributed along the individual surface used for creating the tag attached to the article. First area reading means for reading over the first area of the individual surface, and image information indicating the first area read by the first area reading means as individual information which is information specific to the individual Read information conversion means for conversion and a second area set to a predetermined range larger than the first area including the first area on the individual surface is converted as a non-image area by the read information conversion means. Image forming means for forming an individual information image indicating the individual information on the individual surface, a tag created by the tag creating device, and the tag Of including a false determination device according to claim 5 determines authenticity. In such a program of the present invention, a second region larger than the first region including the first region set on the surface of the individual on which random features are distributed is provided as a non-image portion. A computer used as a true / false determination device for determining the authenticity of a tag on which an individual information image that enables identification of the individual is formed based on a feature indicating the first area read from the first area Based on the characteristics of the individual surface of the second area, the reading control means for controlling the reading means for reading the individual information image, the characteristics of the second area read by the reading means, and the individual information image Information conversion means for converting the individual information into comparable information, the first region specified by the individual information from the information converted by the information conversion means, An operation of repeatedly calculating the correlation value between the first region extracted from the second region and the third region having the same size while moving the extraction position of the third region within the second region. The maximum value of the plurality of calculated correlation values is equal to or greater than a first predetermined value, and a value obtained by subtracting the average value of the correlation values from the maximum value of the correlation values is divided by the standard deviation of the correlation values. Based on whether or not the normalized score of the maximum correlation value obtained is greater than or equal to a second predetermined value, it is verified whether or not the first region is included in the second region. Based on this, it is made to function as a determination means for determining the authenticity of the tag.

  As described above, in the present invention, for various articles such as industrial products, agricultural products, documents, certificates, etc., for each article, a package in which articles are individually packaged, and a package in which a plurality of articles are packaged together From the tag attached to the tag, whether or not the attached tag is created in accordance with the original format, the article to which the tag is attached is a so-called real thing or a so-called fake or imitation It is possible to determine whether the product is a product.

  For the determination at this time, whether or not original information different for each tag is recorded in the tag is used. By using unique features with randomness along the surface of the individual such as the paper forming the tag as original information that is different for each tag at this time, it is possible to determine the authenticity with high accuracy. Has an excellent effect.

  Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 shows a schematic configuration of a tag management system 10 applied to the present embodiment. The tag management system 10 includes a tag creation device 12 and a tag authentication device 14. Further, the tag management system 10 can include a database (data server) 16. At this time, the tag creation device 12, the tag authentication device 16, and the data server 16 have a public line network such as the Internet or a dedicated line network. It is only necessary that data exchange is possible between the data server 16 of the tag creation device 12 and between the tag authentication device 14 and the data server 16 by being connected to the network using the network.

  The tag creation device 10 includes a PC 18 that performs various image processing and data processing using, for example, a workstation or a personal computer, and a scanner 20 that serves as an image reading unit that reads an image recorded on a sheet-like medium such as a document. A printer 22 that forms (prints) an image on a predetermined recording medium is used as a print processing unit. The tag authentication device 14 includes at least a PC 24 that performs various image processing and data processing, and a scanner 26 that reads an image.

  In the PCs 18 and 24, a CPU, ROM, RAM, various input / output ports, and an HDD for storing an OS and various application software (programs) are connected by a bus, and together with a monitor (display device), a keyboard, a mouse, etc. An input device is provided, so that a general configuration that enables various image processing and data processing can be applied.

  Further, the scanner 20 and the printer 22 are connected to the PC 18 directly or via a network in the tag creating device 12, and the scanner 26 is connected to the PC 24 directly or via a network in the tag authenticating device 14.

  As a result, the PC 18 can perform various processes on the image data read by the scanner 20 and print processing based on the processing results, and the PC 24 can perform various processes on the image data read by the scanner 26. It has become.

  FIG. 2 shows a schematic configuration of the tag creation device 12 formed by the PC 18, the scanner 20, and the printer 22, and a schematic configuration of the tag authentication device 14 formed by the PC 24 and the scanner 26. 3 shows an example of a tag 30 created by the tag creation device 12, and FIG. 4A shows a sheet 32 used for creating the tag 30. FIG.

  As shown in FIG. 2, the tag creation device 12 includes a registered image input unit 34, an image processing unit 36, and a print processing unit 38. The registered image input unit 34 reads the registration information when creating the tag 30 from the paper 32 (see FIG. 4A) using the scanner 20 and outputs it as image data.

  At this time, the registered image input unit 34 reads the transmitted light or reflected light of the paper 32, and outputs random characteristics distributed along the surface of the paper 32 as image data. Further, as the scanner 20, for example, a scanner capable of obtaining a resolution of 400 dpi is used, and a preset area (for example, 32 × 32 bits (about 2 mm × 2 mm)) is printed on a sheet of paper with gradation of 8 mm bit grace case. Read 32 surfaces. In FIG. 4B, an example of the image data at this time is visualized.

  An image conversion unit 40 and an image encoding unit 42 are formed in the image processing unit 36, and a predetermined process is performed on the image data input from the registered image input unit 34. At the same time, the image processing unit 36 performs image conversion and performs encoding processing to generate an encoded image (image data of the encoded image) as image data.

  At this time, the image encoding unit 42 performs encryption using an encryption key by applying an electronic signature authentication method using PKI (Public Key Infrastructure). The image encoding unit 42 converts the encrypted data into a two-dimensional code such as a QR code. That is, image data that enables formation of an encoded image that becomes a two-dimensional code is generated.

  In addition, the tag creation device 12 includes a tag information input unit 44 for inputting tag information using an input device such as a keyboard, and a code image (image data) of the tag information by converting the input tag information into a predetermined code. ) Is provided.

  In the print processing unit 38, the sheet 32 obtained by reading the registered image includes the encoded image generated by the image processing unit 36 and the code image generated by the code conversion unit 46 in a preset format. The tag 30 (see FIG. 3) is created by performing the printing process.

  At this time, the tag creating device 12 excludes a predetermined range area including the area where the image data is read by the scanner 20 from the print area.

  That is, as shown in FIG. 3, in the tag creation device 12, a code image 48 indicating tag information is printed on the right side above the page for the tag 30 to be created, and a registered image is displayed on the left side above the page. The print format is set so that the encoded image 50 is printed.

  The tag 30 is provided with a predetermined margin between the code image 48 and the encoded image 50, and an item name or the like to which the tag 30 is attached is provided below the space between the code image 48 and the encoded image 50. An area that can be printed is set.

  On the other hand, in the tag creation device 12, a predetermined area in the margin between the code image 48 and the encoded image 50 is used as a registration area 52, and image data read from the registration area 52 is used as image data of the registration image.

  In the tag authenticating device 14 to be described later, a predetermined area including the registration area 52 is read as the authentication area 54. The authentication area 54 is preferably an area of about 64 × 64 dots when the registration area 52 is 32 × 32 dots. Further, the tag creation device 12 may prevent the inside of the authentication area 54 from being soiled by clearly indicating the authentication area 54 using the frame 56 or the like.

  Since the authentication area 54 and the registration area 52 become clear by providing the frame line 56, forgery of the tag 30 may be suppressed without recording the frame line 56.

  As tag information recorded as a code image 48 on such a tag 30, a product name, a model number, a number, a serial number, etc. that specify a product to which the tag 30 is attached can be used. When attaching to the body, it is preferable to include the number of items packed.

  The tag information includes information that enables the tag 30 to be specified. As information for specifying the tag 30, a serial number set for each tag 30 can be used. That is, the tag information includes a serial number set for each tag 30.

  Further, as the tag information, the product or the generation date of the tag 30 can be included. Further, when an expiration date is set for the tag 30, it is preferable that the expiration date can be included as tag information.

  That is, as shown in FIG. 4A, in the tag creation device 12, based on the printing format of the tag 30, transmitted light or reflected light according to the surface state of the paper 32 in the registration area 52 that becomes a non-printing area. As shown in FIG. 3, the print image does not overlap in the authentication area 54 including the registration area 52.

  The tag creation device 12 uses a two-dimensional code when recording such information on the tag 30, thereby allowing a large amount of information to be included and causing a reading error during authentication or the like. Try to prevent. The code image 48 and the encoded image 50 are not limited to the QR code, and any two-dimensional code can be applied. At this time, data may be compressed and encoded.

  As shown in FIG. 2, such a tag creation device 12 can be provided with a data registration unit 58. The data registration unit 50 registers data in the data server 16 or the like by associating a serial number with a registered image for each created tag 30. Thereby, the registered image of the tag 30 can be read from the data server 16 by the tag authentication device 14.

  On the other hand, the tag authentication device 14 is provided with a collation image reading unit 60, an image processing unit 62, an image conversion unit 64, a code conversion unit 66, and a decoding unit 68.

  The collation image reading unit 60 reads the collation area 54 including the registration area 52 together with the code image 48 and the encoded image 50 from the tag 30 using the scanner 26 and outputs image data. At this time, reading is performed with a resolution of 400 dpi and an 8-bit gray scale. That is, reading is performed in accordance with the scanner 20 when the tag creating device 12 creates the tag 30.

  The image processing unit 62 separates the image data of the code image 48, the image data of the encoded image 50, and the image data of the authentication area 54 from the read image data. The image data in the authentication area 54 is converted by the image conversion unit 64.

  The image data of the encoded image 50 is code-converted from the two-dimensional code by the code conversion unit 66, and the decryption unit 68 performs a decryption process using the public key. Thereby, the image data of the registered image (registered area 52) is obtained.

  The image data for the code image is extracted according to the tag information by performing image conversion. Further, the image data of the collation area 54 converted by the image converting unit 64 and the image data of the registered image (registered area 52) decoded by the decoding unit 68 are stored in a memory such as a RAM or an HDD. .

  The tag verification device 14 is provided with a verification unit 70 and a determination unit 72. The collation unit 70 performs collation processing between the image data in the collation area 54 and the image data in the registration area 52 recorded in the tag 30 as the encoded image 50. The determination unit 72 determines whether or not the tag 30 is appropriate based on the collation result, that is, whether the tag 30 is true or false.

  In addition to the image data recorded as the encoded image 50 and the image data in the verification area 54 (tag verification), the verification unit 70 stores the image data recorded as the encoded image 50, Verification (registration verification) of image data of registered images registered in the data server 16 can be performed.

  Next, as operations of the present embodiment, processing in the tag creation device 12 and the tag authentication device 14 in the tag management system 10 will be described.

  First, the effectiveness of authentication of the tag 30 using the image data of the registration area 52 on the paper 32 and the image data of the collation area 54 will be described.

  For example, in the paper such as the paper 32 forming the tag 30, the entanglement of the fibrous material is random, and due to this, the transparency of the paper changes randomly. Further, since the entanglement of the fibrous material also appears in the irregularities on the paper surface, the irregularities on the paper surface also change randomly.

  From this, it can be said that features having randomness along the individual surface, such as paper transparency and surface irregularities, can be applied to an individual's authenticity determination as individual-specific features. Such individual-specific features can be read as transmitted or reflected light on paper using various image reading means such as a scanner.

  On the other hand, individual-specific features such as the above-described paper are likely to cause erroneous determination due to differences in the position and orientation of the reading area. From here, the area of the comparison target area is made wider than the authentication area, and the correlation value is repeated while moving the small area area (authentication area) within the large area area (comparison area). By calculating and obtaining a large number of correlation values, authenticity determination is performed using the obtained correlation values and the feature values obtained from the distribution of the correlation values.

  There are two types of fake determinations: determining whether the real thing is a fake and determining whether the fake is a real thing. The probability of determining the real thing as a fake is FRR (False Rejection Rate), and the fake is determined as the real thing. First, a test result for verifying the validity of the authenticity determination is shown with the probability being FAR (False Acceptance Rate).

  In this test, first, using a flatbed scanner, an unprinted area of paper used as a sample with a resolution of 400 dpi and a gray scale of 8 bits is set to a reference area of 32 × 32 dots (about 2 mm × 2 mm). The image data output from the scanner is stored as reference data.

  In FIG. 5, the reference data at this time is visualized and shown as a reference image. The reference image is subjected to contrast correction so that visual confirmation is easy (clear).

  It is well known that it is impossible to control the entanglement of the fibrous material forming the paper at the time of paper manufacture, and from this, the entanglement of the fibrous material forming the paper can be regarded as random. The entanglement of the fibrous material can be observed by using a transmission light microscope or the like, but the image data (reference image shown in FIG. 5A) read by a 400 dpi scanner has the entanglement of the fibrous material. It cannot be confirmed by condition.

  However, in the reference image, a random light / dark pattern reflecting a random change in the transparency of the paper due to the randomness of the entanglement of the fibrous material is generated. Note that the light / dark pattern may be affected by irregularities on the paper surface caused by various conditions when the paper is rolled, but in any case, it is obvious that the pattern is a random pattern.

  Accordingly, it can be confirmed that the reference data corresponding to the reference image is information indicating a characteristic unique to the paper in the reference area on the paper, that is, information indicating a random change in transparency in the reference area.

  Next, as a comparison target, a 64 × 64 dot (approximately 4 mm × 4 mm) collation region (corresponding to the authentication region 54 of the present embodiment) including the reference region described above is read by a scanner among the paper used as a sample. The read image data is stored as first verification data.

  The first collation data represents a random change in the transparency of the paper in the collation area, and FIG. 5B visually shows the first collation data as a collation image.

  On the other hand, as a case where the probability that the true article is erroneously determined to be fake (FRR) is high, the paper used as the sample is slightly shifted in position and slightly rotated with respect to the time when the first collation data is acquired. While being placed on the document table, a 64 × 64 dot collation area is read, and image data output from the scanner is stored as second collation data. That is, the image data read from the area including the reference area is stored as the second verification data, although the position and orientation are slightly different from the reading area of the first verification data.

  As another comparison object, a 64 × 64 dot collation area was read from paper different from the paper used as the sample, and the image data output from the scanner was stored as third collation data.

  When the reference data and the first to third matching data are acquired in this way, the correlation between each of the first to third matching images represented by the first to third matching data and the reference image represented by the reference data. The value was calculated.

  Specifically, as shown in FIG. 6 as an example, a partial area having the same size as the reference image (in FIG. 6, expressed as a correlation calculation range surrounded by a solid line) is extracted from the collation image to be calculated. The correlation value between the (partial image) and the reference image is calculated by the normalized correlation method (see equation (1)). This was repeated while shifting the position of the partial area on the collation image by one dot (one pixel) in the X and Y directions.

Where F is a reference image (a set of reference data), fi is a brightness value of each pixel of the reference image, N is the total number of pixels of the reference image (and a partial area of the collation image), and G is a partial area of the collation image ( ), Gi is the lightness value of each pixel in the partial basin of the collation image, f AVE is the average value of the lightness values of each pixel in the reference image, and g AVE is the lightness value of each pixel in the partial region of the collation image Is the average value.

  Here, by performing the above calculation using the first to third collation images as the collation images to be computed, assuming that the number of dots in the reference image is m × n and the number of dots in the collation image is M × N, one collation (M−m + 1) × (N−n + 1) correlation values are obtained for the image.

  Subsequently, the normalized score of the maximum value of the correlation value was calculated according to the equation (2) as a feature representing the distribution degree of the correlation value for each of the first to third matching images.

Normalized score =
(Maximum correlation value−average correlation value) ÷ standard deviation of correlation values (2)
7A and 7C show the correlation value maximum value and the normalized score calculation result of the correlation value, the position of the partial region on the collation image, and the correlation value. Shown with a chart visually showing the relationship.

  As shown in FIG. 7A, when a collation area including a reference area on the same paper is read with respect to the reference area without positional and orientation deviation (first collation image), the maximum correlation value Indicates a very high value. In addition, the distribution of correlation values also shows values that are very low compared to the maximum values in areas other than the peak where the correlation values are maximum. The normalized score of the value is also very high.

  On the other hand, as shown in FIG. 7C, in the case of a paper different from the paper from which the reference image is read (paper not including the reference image) (third collation image), the maximum correlation value is very high. The correlation value distribution shows a low correlation value overall including the peak part, and the normalized score of the maximum correlation value is also very low. .

  On the other hand, as a case where there is a high probability that a real object is erroneously determined to be a fake, when a collation area that includes a reference area and is slightly changed in position and orientation (second collation image) is read, the maximum correlation value and correlation As shown in FIG. 7B, the normalized score of the maximum value is an intermediate value between the case where the same paper is read without positional and orientation deviation and the case where different paper is read. become.

  Therefore, an intermediate value between the value shown in FIG. 7 (B) and the value shown in FIG. 7 (C) is employed as the maximum correlation value and the normalized score threshold value of the maximum correlation value. For example, by setting the threshold value of the maximum correlation value ≈ 0.3 and the threshold value of the normalized score at the maximum position of the correlation value ≈ 5.0, the maximum correlation value is compared with the threshold value, and the correlation value If true / false judgment is made by comparing with the threshold value of the maximum normalized score, the true position of the paper at the time of collation area reading and misorientation may be misidentified as being counterfeit. It can be understood that there is a possibility that the determination accuracy of the true / false determination may be improved when the determination is performed using only the maximum correlation value when the probability of the determination is high.

  As another test, an area of 32 × 32 dots (approximately 2 mm × 2 mm) of A4 size white paper with the same resolution and gradation is read as a reference area using the same scanner as the above test. As a first comparative example, substantially the entire surface of the paper from which the reference data is acquired is read, and 64 × 64 dot collation area data is extracted from the image data obtained by the reading. Extracting the partial area data from the extracted collation data and calculating the correlation value with the reference data according to equation (1) was repeated while shifting the position of the partial area within the collation area by one dot (by this More than 10 million correlation values were obtained).

  Further, as a second comparative example, the reading of substantially the entire surface of the paper from which the reference data has been acquired is performed again after slightly shifting the position and rotating the direction slightly, and in the same manner as in the first comparative example described above, Extracting 64 × 64 dot collation area data from the obtained image data, and further calculating the correlation value between the partial area data extracted from the extracted collation data and the reference data according to equation (1), The position of the partial area in the verification area was repeated while shifting by one dot. Further, as a third comparative example, a paper different from the paper from which the reference data was acquired was used, and a correlation value was calculated from the collation data read and acquired in the same manner as in the first and second comparative examples.

  Then, as a case where there is a high probability that a fake is erroneously determined to be genuine, the reference area of the paper used as the original is intentionally read with an excessive amount of light, and the change in transparency in the reference area is partially whitened. The second reference data representing the image that has been captured is acquired, the entire surface of the paper used in the third comparative example is read, and the data of the collation area of 64 × 64 dots is extracted from the image data obtained by the reading. The correlation value between the partial region data further extracted from the extracted collation data and the second reference data is calculated by the normalized correlation method according to the equation (1). Repeated while shifting one dot at a time.

  FIG. 8 to FIG. 11 show the distribution of correlation values obtained by the above test (chart with the correlation value on the horizontal axis and the logarithm of frequency on the vertical axis). FIG. 8 shows the distribution of correlation values obtained in the first comparative example, and FIG. 9 shows the distribution of correlation values obtained in the second comparative example. In any distribution, the majority of the many correlation values are 0 or a value close to 0. However, data indicating a high correlation value of a predetermined value or more (for example, 0.3 or more) is also included, and the maximum correlation value in the first comparative example is 1.00, Since the maximum value of the correlation value in the comparative example is 0.657, which indicates a high value, it can be understood that the real object can be determined as the true object even if only the maximum correlation value is used.

  FIG. 10 shows the distribution of correlation values obtained in the third comparative example. All correlation values are less than a predetermined value (for example, 0.3), and the maximum correlation value is as low as 0.254. Since the values are shown, even if only the maximum correlation value is used in the same manner as described above, it is possible to determine a fake as a fake.

  On the other hand, FIG. 11 shows a correlation value distribution obtained by an experiment assuming that the probability that a fake is erroneously determined to be true is high. A high correlation value greater than or equal to a predetermined value (for example, 0.3 or more) is shown. The illustrated data is also included (the maximum correlation value is 0.348), and if the authenticity determination is performed using only the maximum correlation value, there is a possibility that a fake is erroneously determined to be a real object. On the other hand, as apparent from the comparison of the distribution of FIG. 11 with the distribution of FIG. 10, the correlation value distribution shown in FIG. The standard deviation of the correlation value in the distribution is larger than the distribution in FIG. 10, and the normalized score value of the maximum correlation value in the distribution in FIG. 10 (the normalized score of the maximum correlation value in the distribution of FIG. 10 is 5.32 and the normalized score of the maximum correlation value in the distribution of FIG. 11 is 4.91). It can be understood that it can be avoided that a fake is erroneously determined to be a real one.

  As described above, even in a case where the probability that a fake is erroneously determined to be true is high (the case of FIG. 11), the authenticity determination is performed using the maximum correlation value and the normalized score of the maximum correlation value. For example, since it is possible to avoid erroneous determination, in addition to the maximum correlation value, a true / false determination is performed by adding a feature amount indicating the distribution degree of the correlation value, such as a normalized score of the maximum correlation value. It is confirmed that the determination accuracy of the true / false determination can be improved.

  Next, test results for confirming the determination system for authenticity determination will be described. In this test, continuous 10 sheets were extracted from an A4 size 500-sheet office paper (Fuji Xerox Office Supply Co., Ltd. C2 paper product code V436) and used as a sample.

[FRR confirmation test]
In this test, 40 reading areas were set on the entire surface of the A4 sample at substantially equal intervals (see FIG. 12).

The center coordinates of each reading area when the upper left corner is set to the origin (0, 0) toward the reading surface of each sample in the state where the longitudinal direction of the sample is the vertical direction, is converted into a dot number of 400 dpi. It is as follows.
(500,500), (500,1000), (500,1500), (500,2000), (500,2500), (500,3000), (500,3500), (500,4000), (1000 , 500), (1000, 1000), (1000, 1500), (1000, 2000), (1000, 2500), (1000, 3000), (1000, 3500), (1000, 4000), (1500, 500 ), (1500, 1000), (1500, 1500), (1500, 2000), (1500, 2500), (1500, 3000), (1500, 3500), (1500, 4000), (2000, 500), (2000, 1000), (2000, 1500), (2000, 2000), (2000, 250 ), (2000, 3000), (2000, 3500), (2000, 4000), (2500, 500), (2500, 1000), (2500, 1500), (2500, 2000), (2500, 2500), (2500, 3000), (2500, 3500), (2500, 4000)
Each sample was read using a FUJITSU fi-4010CU (flatbed scanner) with a resolution of 400 dpi and an 8-bit gray scale gradation.

  The size of the reading area is 16 × 16 dots (about 1 mm × 1 mm), 32 × 32 dots (about 2 mm × 2 mm), 64 × 64 dots (about 4 mm × 4 mm), 128 × 128 dots (about 8 mm × 8 mm). Four types were set. In this test, each reading area is used as both a reference area and a collation area, the entire surface of the sample is read by a scanner in order to reduce the number of readings, and each reading area is corresponded from image data obtained by reading. Data (data used as reference area data and collation area data) was cut out and used for authenticity determination. Further, the combinations shown in the following Table 1 are used as combinations of the sizes of the reference area and the collation area so that the size of the collation area with respect to the reference area is double or quadruple in the ratio of the side lengths. It was.

  Also, taking advantage of the fact that the scanner's platen is slightly larger than the A4 size, samples can be placed on the platen using the upper right butting (normal placement) and the lower left butting (upper right The sample position is about 2 mm in the longitudinal direction and about 10 mm in the short direction with respect to the contact), clockwise rotation right alignment (clockwise rotation about 1 degree), counterclockwise rotation left alignment (counterclockwise rotation about 1 degree) 4 were determined, and each sample was read with each sample placed on the document table.

  In this test, the combination of the data obtained by reading the samples in different states as a combination of the reference area data and the collation area data used for the authenticity determination was performed by combining the data obtained from each other. . Since there are three different placement methods that can be combined for one placement method, a single sample can be used in a single combination of the reference region and collation region size combinations shown in Table 1. 4 × 3 = 12 true / false judgments are performed for a single reading area, and there are 40 reading areas in a single sample, and the number of samples is 10, so that the reference area In addition, 12 × 40 × 10 = 4800 times of authenticity determination was performed for each combination of the size of the collation area.

  As mentioned above, the data of the reference area and verification area used for authenticity determination is combined with the data obtained by reading the samples in different ways, so it corresponds to the reading area from the image data. When the data to be extracted is cut out, the position of the reading area is corrected so that the center position of the reference area and the center position of the collation area substantially coincide.

  That is, when the image data for cutting out the data in the reading area is data obtained by reading the sample placed on the “upper right abutment”, the position correction of the reading area is not particularly performed. In the case of “bottom left abutment”, based on the image data obtained by reading with the scanner, the amount of positional deviation at the end of the sample was calculated to correct the position of the reading area. As for “clockwise right justification” and “counterclockwise left justification”, the position of the corner of the sample is detected based on the image data, and the actual position after rotating and moving the sample based on the detected position of the corner. The position of the reading area was calculated, and the position of the reading area cut out as data from the image data was corrected (only the center position was corrected, and the rotational distortion was not corrected).

  As in the previous description, the true / false determination is performed by calculating a correlation value between the reference area and the reference area in the reference area and the reference area using the normalized correlation method. By repeating while moving one dot at a time, (m−n + 1) × (m−n + 1) correlation values are obtained (however, the reference area is m × m dots and the matching area is n × n dots). By determining the normalized score of the maximum value and the maximum value of the correlation value, and determining whether the maximum value of the correlation value is 0.3 or more and the normalized score of the maximum value of the correlation value is 5.0 or more went.

  Table 2 shows the test results.

  As can be seen from Table 2, under the conditions of 400 dpi resolution and 8-bit gray scale reading, if the size of the reference area is 32 × 32 dots and the size of the collation area is 64 × 64 dots, it is practical. It can be understood that the FRR is low enough to cause no problem. It is also clear that the above reading conditions are sufficiently realizable with a commercially available inexpensive scanner, and it is not necessary to use an expensive reading device such as a microscope for reading.

  In addition, in the above test, as a result of analyzing a case in which an erroneous determination (an erroneous determination that a genuine article is a fake) occurred in the authenticity determination, an erroneous determination is made particularly when the sample is rotated clockwise or counterclockwise. It became clear that there is a tendency to occur. Therefore, for example, the rotation distortion is detected and corrected. When placing the paper to be read on the scanner platen, care should be taken not to rotate the paper. It is considered that the improvement of FRR can be easily achieved by taking measures for preventing or reducing the rotational distortion such as.

[FAR confirmation test]
Similar to the FRR test, the data corresponding to the reference area and the data corresponding to the matching area are cut out from the image data obtained by reading the entire surface of the A4 size sample at a resolution of 400 dpi and an 8-bit gray scale. It was.

  Since the FAR is a probability that a fake is erroneously determined to be a real one, in the test for confirming the FAR, all areas on the sample can be used as collation areas. In this experiment, if the correlation value with the reference area is calculated for all areas except the reference area on the entire surface of A4, it is the same if it is determined as a fake from the normalized score of the maximum correlation value and the maximum correlation value. Since it is self-evident that an arbitrary collation area on the sample is determined to be fake, the collation area is an area of 3307 × 4676 dots obtained by reading the entire scanning area of the scanner including the entire surface of the A4 sample at 400 dpi. .

  In this test, the number of samples was five, and four reading areas were set on the entire surface at approximately equal intervals. The center coordinates of each reading area are (500, 500), (500, 3500), (2500, 500), (2500, 3500) in terms of the number of dots of 400 dpi. In addition, the reference area has four sizes of 16 × 16 dots, 32 × 32 dots, 64 × 64 dots, and 128 × 128 dots.

  For four reference areas per sample, the authenticity is determined over the entire surface of the other four samples. Therefore, four locations x 4 per sample = 16 times authenticity determination. become. Since this is carried out for five samples, the total number of true / false determinations is 5 × 16 = 80. Although it seems that the number of times for the experiment for FRR confirmation is small, as described above, since the entire reading area of the scanner including the entire surface of the A4 sample is set as the collation area, it is only seen so. If it is divided into areas, it is equivalent to having made the authenticity judgment 10 million times or more.

  Table 3 shows the test results.

  As is apparent from Table 3, since the FAR = 0.0000% when the size of the reference area is other than 16 × 16 dots, the verification area is divided into small areas of any size. Even if it is performed, it is guaranteed that the FAR is 0.0000%.

  On the other hand, when the size of the reference area is 16 × 16 dots, FAR = 31.250%, which is an unsuitable value. This is the worst value, and there is a possibility that FAR can be improved if the collation area is divided into small areas. However, even in the test for FRR confirmation described above, when the size of the reference area is 16 × 16 dots, The determination accuracy of authenticity determination is lower than that in the case where the size of the region is made larger. Therefore, it has become clear that the size of the reference area should be 32 × 32 dots as the lower limit at a resolution of 400 dpi.

  As described above, when the resolution is 400 dpi and the gradation is 8-bit gray scale, it is possible to make a true / false determination with a high determination system by setting an area of 32 × 32 bits or more as a reference area.

  Next, creation of the tag 30 and authentication of the tag 30 in the tag management system 10 will be described. FIG. 13 shows an outline of processing (tag creation processing) in the tag creation device 12.

  This flowchart is executed when the tag 30 is created. In the first step 100, a display prompting the user to set the paper 32 used for creating the tag 30 on the mounting table of the scanner 20 is displayed on the display (display device). In 102, it is confirmed whether or not the paper 32 is set in the scanner 20.

  When the paper 32 is set in the scanner 20 and reading of the registered image is instructed, an affirmative determination is made in step 102 and the process proceeds to step 104 where the scanner 20 reads a predetermined area of the paper 32. At this time, the format of the tag 30 is set in the PC 18, and based on this, the registration area 52 (see FIG. 4A) is read. At this time, the scanner 20 reads the reflected light of the light irradiated on the surface of the paper 32, and as a feature having randomness along the surface of the paper 32, image data corresponding to the unevenness along the surface of the paper 32. Will be output.

  The scanner 20 reads a 32-bit × 32-bit (approximately 2 mm × 2 mm) area with a resolution of 400 dpi and a gray scale of 8 bits, so that the data size becomes 1024 bytes and the gray scale of each dot. The value is an integer value in the range of 0 to 255. FIG. 4B shows an example of the visualized image at this time (image subjected to contrast correction so that clear vision is easy).

  The registration area 52 on the paper 32 can be specified when the paper 32 is loaded at a fixed position by using the origin set according to this position as a reference, and the size of the paper 32 is fixed. In this case, an arbitrary method can be applied such as detecting the edge of the paper 32 and specifying the registration area based on the edge.

  Further, since the registration area 52 is a non-image area on the tag 30, it is possible to prevent erroneous determination at the time of authentication due to adhesion of toner or the like when the tag 30 is created. I am doing so.

  Accordingly, when the image data output from the scanner 20 is read as image data of a registered image in step 106, the process proceeds to step 108 and image conversion processing is performed. At this time, data compression is performed by applying discrete cosine transform or the like to the image data. Further, a secret key and a public key are set in the tag management system 10, and in step 110, encryption processing is performed on the compressed data using the secret key.

  Thereafter, in step 112, the encrypted data is encoded in a format that can be automatically read using a reading unit such as a scanner. It should be noted that a two-dimensional code such as a QR code is used for encoding, and an encoded image 50 of the two-dimensional code corresponding to the encrypted data is obtained.

  In step 110, the data is encrypted using a secret key. This encryption process is not essential, but the encryption process may be performed to suppress duplication of the tag 30. preferable.

  In addition, there is a method of encrypting data using a public key for encryption and a secret key for decryption. In this case, since it is necessary to use a secret key for authentication of the tag 30, A method using a secret key is more preferable.

  On the other hand, in parallel with the processing for the image data read from the registration area 52 of the paper 32, in step 114, the display for prompting the input of the tag information is performed on the display, etc., and the input of the tag information is prompted. Check if the tag information has been entered.

  As a result, when an input device such as a keyboard is used and tag information is input based on a UI (user interface) displayed on the display and the input of the tag information is confirmed, an affirmative determination is made in step 116. To step 118.

  The tag information input at this time includes the product name, model number, and serial number of the product to which the tag 30 is attached, and when attaching a plurality of products to a package (packing body) that is packaged (packed). The number is also entered. In addition to the information related to the product, a serial number set for each tag 30 is input to the tag 30 as information about the tag 30 itself. Furthermore, time information on the tag 30 or a product to which the tag 30 is attached, such as the creation time and expiration date of the tag 30, can be added to the tag information.

  In step 118, the input tag information is encoded in a format that can be automatically read using a reading unit such as a scanner (two-dimensional encoding such as a QR code), and a code image 48 indicating the tag information is displayed. To be obtained.

  When the encoding of the image in the registration area 52 and the encoding of the tag information are completed in this way, in step 120, the code image 48 in which the tag information is encoded and the encoding according to the image data in the registration area 52 are performed. Bitmap data is generated so that the image 50 or the like is printed on the paper 32 in a predetermined format. At this time, the bitmap data is generated so that a frame line 56 defining the authentication area 54 including the registration area 52 is printed.

  Thereafter, in step 122, a display requesting that the paper 32 from which the registration area 52 has been read is loaded into the printer 22 is displayed on the display. In step 124, the corresponding paper 32 is loaded into the printer 22 and printing processing is performed. Check if execution is instructed.

  Here, when the paper 32 is loaded in the printer 22 and a print process on the paper 32 is instructed, an affirmative determination is made in step 124, and the process proceeds to step 126 to execute the print process.

  As a result, the encoded image 50 corresponding to the image data in the registration area 52 is printed together with the code image 48 indicating the tag information, and the tag 30 in which the authentication area 54 including the registration area 52 is vacated in a non-printing state. Is output.

  At the same time, in step 128, registration processing of the image data read from the registration area 52 is performed. In this registration process, the image data read from the registration area 52, the data obtained by encrypting the image data, or the data obtained by further encoding the encrypted data, the information of the tag 30 itself such as the serial number of the tag 30, the tag 30 is registered in the data server 16 in association with tag information such as product information attached.

  The tag 30 thus created is attached to each product, or is attached to a package in which products are packaged, a package in which a plurality of products are packaged together, or a package in which packages are packaged.

  In addition, when the tag 30 is attached to the product, the package, or the package, for example, when the product is for sale, the purchaser cuts the string material that connects the tag and the product or breaks the tag 30. What is necessary is just to be removed so that it cannot be reused, and to be removed by tearing the exterior and the tag 30 by attaching the tag 30 to the exterior of the package and the package. It ’s fine.

  In the tag creation device 12 applied to the present embodiment, the scanner 20 that reads the registration area 52 from the paper 32 and the printer 22 that performs printing processing on the paper 32 are separated. It is also possible to use a print processing apparatus with a scanner function that allows the printing process to be executed on the paper 32 that has the same function and that has been scanned by the scanner function, whereby an image read from the registration area 52 can be used. The encoded image 50 corresponding to the data can be definitely printed on the corresponding paper 32, which is more preferable.

  Next, authentication of the tag 30 using the tag authentication device 14 will be described with reference to FIG. In the first step 140 of the flowchart, the scanner 26 is requested to load the tag 30 to be authenticated, for example, by displaying on the display (display device) of the PC 24. Further, in step 142, it is confirmed whether or not the loading of the tag 30 into the scanner 26 is completed and the execution of the tag 30 authentication process is instructed.

  Here, if the execution of the authentication process is instructed in a state where the tag 30 is placed on the document table of the scanner 26, an affirmative determination is made in step 142 and the process proceeds to step 144. As a result, the scanner 26 is instructed to read the tag 30, and the scanner 30 reads the tag 30 and outputs image data. In step 146, the image data is read.

  At this time, the entire region of the tag 30 may be read, but at least the code image 48 and the encoded image 50 printed on the tag 30 are provided between the code image 48 and the encoded image 50. An area in a predetermined range including the collation area 54 may be read. Alternatively, the code image 48, the encoded image 50, and the authentication area 54 may be read separately.

  In the next step 148, the image data input from the scanner 26 is subjected to image processing to separate and extract the image data of the code image 48, the image data of the encoded image 50, and the image data in the collation area 54. .

  Thereafter, in step 150, tag information is extracted from the two-dimensional code by performing code conversion processing on the image data of the code image 48. In step 152, predetermined image conversion is performed on the image data in the collation area 54.

  At the same time, in step 154, the data converted into the two-dimensional code is extracted from the image data of the encoded image 50. Thereafter, in step 156, the image data recorded as the image data in the registration area 52 is obtained by decrypting the data converted from the two-dimensional code using the public key.

  When the image data corresponding to the registration area 52 and the image data of the collation area 54 including the registration area 52 are obtained in this way, the process proceeds to step 158 and collation processing is performed.

  That is, when the registration image data in the registration area 52 of 32 bits × 32 bits and the image data of the authentication area 54 set to 64 bits × 64 bits are obtained, in step 158, the registration image data is used as reference data, and authentication is performed. By performing the collation process using the image data in the region 54 as the collation data, the maximum correlation value and the normalized score of the maximum correlation value are calculated.

  In the next step 160, the maximum correlation value between the registered image data and the authentication image data obtained by the collation process (calculation process) and the normalized score of the maximum correlation value are set to a preset threshold value ( For example, the true / false determination is performed by comparing the threshold value with respect to the maximum correlation value≈5.0 and the threshold value with respect to the normalized score normalization score≈0.3). The determination result is output on a display or the like.

  On the other hand, in step 164, whether or not registration confirmation is to be performed is displayed on the display or the like to prompt the input of necessity of registration confirmation of the tag 30, and when the registration confirmation is instructed, an affirmative determination is made in step 166. To step 168.

  In step 168, the data server 16 is requested to output the registered image data of the tag 30 based on the serial number (tag 30 serial number) recorded as tag information of the tag 30, and in step 170, It is confirmed whether there is corresponding data (registered image data).

  Here, when there is no corresponding registered image data, that is, if the tag 30 is not registered in the data server 16, a negative determination is made in step 170 and the process proceeds to step 172, and the corresponding tag information and registration are registered. The fact that there is no image data in the data server 16 and there is a high possibility that the corresponding tag 30 is a fake is output on the display.

  On the other hand, when there is registered image data corresponding to the serial number recorded as the tag information, an affirmative determination is made in step 170 and the process proceeds to step 174, where the corresponding registered image data is read from the data server 16 and read. 176.

  In step 176, the read registered image data is collated with the image data in the collation area 54. Also in the collation at this time, the registration image data read from the data server 16 is used as reference data, and the image data in the authentication area 54 of the tag 30 to be authenticated is used as collation data, so that the maximum correlation value and the maximum correlation value are normalized. In step 178, authenticity determination is performed based on the calculation result, and the determination result is output.

  The paper 32 is provided with unique features having randomness along the surface. In the tag creation device 12, image data read from the registration area 52 set on the paper 32 is recorded as an encoded image 50 on the tag 30 created using the paper 32.

  The tag authentication device 14 collates the image data indicated by the encoded image 50 with the image data in the authentication area 54 of the tag 30, so that the tag 30 is the original object (true) created by the tag creation device 12. If the tag 30 is not genuine, the product, packaged product, or packaged product to which the tag 30 is attached can be determined. It is not a real similar product or a counterfeit product, nor is it a product of a production factory or production company that is supposed to be manufactured (hereinafter referred to as a fake).

  That is, if the tag to be attached to the fake is simply a copy of the genuine tag 30 (hereinafter referred to as “fake tag”), the paper 32 is different, and the tag authentication device 14 is not authenticated. .

  Therefore, it is possible to determine whether the product, packaged product, or packaged product to which the tag 30 is attached is genuine depending on whether the tag 30 is authenticated.

  On the other hand, when creating a fake tag, it is assumed that the feature of a predetermined area set on the paper 32 is read and printed on the paper 32 as an encoded image, as in the case of the tag 30. A fake tag with surface specific features is obtained.

  In order to prevent the creation of such a fake tag, the tag creation device 12 performs encryption using a secret key. In the tag management system 10, the created tag 30 is registered in the data server 16.

  When data is encrypted using a secret key and decrypted using a public key, the decryption can be easily performed, but encryption that enables accurate decryption using this public key becomes difficult. As a result, even if the encrypted encoded image 50 is printed on the paper 32, the tag authentication device 14 does not authenticate.

  As encryption, there is a method that uses a secret key when decrypting, but in this case, authentication is limited (only those with a secret key can be authenticated), so a false tag is created. It is preferable to use a public key on the authentication side, since the effect of suppressing the above becomes low.

  On the other hand, by registering the genuine tag 30 in the data server 16, even if it is determined that the encoded image 50 and the authentication area 54 on the paper 32 are compared with the false tag, Is not registered on the data server 16, the collation area 54 of the paper 32 and the registered image data registered in the data server 16 cannot be collated, or the tag is determined to be a fake tag. become.

  Therefore, by executing at least one of encryption using a secret key and registration with the data server 16, accurate authenticity determination can be performed even if it is imitated finely.

  In addition, it is possible to perform only registration in the data server 16 without performing encryption using the secret key. In this case, however, the security of the data server 16 is increased and data rewriting by a third party is performed. It is preferable that no registration is performed.

  As described above, the tag management system 10 uses the characteristic having randomness along the surface of the paper 32 forming the tag 30 to prevent the tag 30 from being counterfeited and the like. By making a false determination, it is possible to accurately determine the authenticity of a product to which the corresponding tag 30 is attached.

  In addition, when using such a tag 30, it is necessary to confirm that the tag 30 has not been replaced or replaced prior to authentication of the tag 30 from the packaging state, packaging state, etc. of the item. Since the genuine tag 30 is reused, it is possible to prevent the authenticity of the product from being determined because the genuine tag 30 is attached to the counterfeit product.

  For this reason, as the tag 30, it is possible to add a tag that cannot be rewritten or a structure that appears clearly when characters are rewritten.

  In addition, time information such as an expiration date of the tag 30 may be added as tag information of the tag 30, and the tag 30 may be authenticated including the time information. It is possible to prevent reuse, and at least prevent a large amount of counterfeits from circulating.

  Furthermore, in the product manufacturing process, the primary processed product may be further subjected to secondary processing in another factory or company. In such a case, the tag 30 is created and attached when manufactured as a primary processed product, and the tag 30 is authenticated at the time of shipment or delivery to the secondary processing factory. It is possible to prevent the primary processed product from being carried in.

  At this time, the newly created tag 30 may be attached to the secondary processed product. At this time, the tag attached to the primary processed product is accurately collected, broken, or ink is used. It is preferable that at least the encoded image 50 and the authentication area 54 be crushed (soiled) so that proper information reading becomes difficult.

  Further, when the tag 30 attached to the primary processed product is used when shipped as a secondary processed product, information related to the secondary processing is included in the tag 30 as tag information, and a management database (data server 16). It is preferable to update the registered information.

  Further, in the tag management system 10, authentication may be performed unconditionally in the distribution process or storage process of the product, or verification with the registration information with the data server 16 may be performed. Distribution management is possible, and it is possible to prevent the fake from being mixed in the distribution process.

  The present embodiment described above does not limit the present invention. For example, in the present embodiment, the scanners 20 and 26 are used for reading the registered image data from the paper 32 for creating the tag 30 and reading the code image 48 and the encoded image 50 or the authentication area 52 from the tag 30. However, the scanners 20 and 26 may be a flat bed type, an auto feed type that performs reading while automatically feeding paper, or a handy scanner. Furthermore, not only a scanner but also a digital camera can be applied.

  That is, the image reading can be performed by an appropriate combination of an arbitrary imaging unit having a predetermined resolution such as a CCD line sensor or a CCD area sensor and a light source used for image reading.

  In the present embodiment, paper (paper 32) is applied as an individual forming the tag 30, but the material and shape of the tag of the present invention are not limited to this. Due to the improved printing technology, it is possible to print on the resin plate as well as high quality on block-like solids. As a tag, the surface is controlled to have irregularities with randomness that cannot be controlled and the distribution of transmitted light. Any material can be used as long as it has randomness that cannot be achieved.

It is a schematic block diagram of the tag management system applied as an article management system to this Embodiment. It is a block diagram which shows schematic structure of the tag production apparatus and tag authentication apparatus which form a tag management system. It is the schematic which shows an example of the tag to which this invention is applied. (A) is a schematic diagram of a sheet on which a tag is formed, and (B) is a schematic image diagram showing an example of a registered image read from a registration area of the sheet. (A) And (B) is a schematic image figure used for description of the test of authenticity determination, (A) shows the registration image, (B) has shown the collation image. It is an image figure explaining the calculation of the correlation value of the registration image and collation image in the test of authenticity determination. (A)-(C) is an image figure which shows the outline of distribution of a correlation value as the maximum value of a correlation value, and the normalized score. It is a diagram which shows distribution of the correlation value of a 1st collation image. It is a diagram which shows distribution of the correlation value of a 2nd collation image. It is a diagram which shows distribution of the correlation value of a 3rd collation image. It is a diagram which shows an example of distribution of the correlation value of a case with a high probability that a fake is determined to be true. It is the schematic which shows the position of the reading area | region in the test of FRR confirmation. It is a flowchart which shows an example of a tag creation process in this Embodiment. It is a flowchart which shows an example of a tag authentication process in this Embodiment.

Explanation of symbols

10 Tag management system (article management system)
12 Tag creation device 14 Tag authentication device 16 Data server 18 PC
20 Scanner 22 Printer 24 PC
26 Scanner 30 Tag 32 Paper 34 Registered Image Input Unit 38 Print Processing Unit 40 Image Conversion Unit 42 Image Encoding Unit 44 Tag Information Input Unit 48 Code Image 50 Encoded Image 52 Registration Area (First Area)
54 Authentication area (second area)
58 data registration unit 60 collation image reading unit 68 decoding unit 70 collation unit 72 determination unit

Claims (7)

  1. A second region larger than the first region including the first region set on the individual surface on which the random features are distributed is provided as a non-image portion, and is read from the first region. An article management system for managing an article to which a tag on which an individual information image that enables identification of the individual is formed based on a feature indicating the first region is attached,
    A feature of the individual surface of the second region and reading means for reading the individual information image;
    Information conversion means for converting the characteristics of the second region read by the reading means and the individual information based on the individual information image into comparable information;
    A correlation value between the first area specified by the individual information from the information converted by the information conversion means and a third area having the same size as the first area extracted from the second area Computing means for repeating the computation while moving the extraction position of the third region within the second region;
    The maximum value of the plurality of calculated correlation values is equal to or greater than a first predetermined value, and the value obtained by subtracting the average value of the correlation values from the maximum value of the correlation values is obtained by dividing by the standard deviation of the correlation values. normalized score of the maximum value of the correlation value based on whether the second predetermined value or more, collates whether the first area is included in the second region, on the basis of the comparison result Determining means for determining the authenticity of the tag;
    Hints, article management system, characterized in that to enable determining authenticity of the article based on a determination result of said determining means.
  2. Wherein when said individual information image individual information by encrypting is formed on the individual, article management system of claim 1, wherein the converting means is characterized in that it comprises decryption means for the encryption.
  3. When a tag information image based on tag information that makes it possible to specify the tag to the individual is formed, and includes registration holding means for registering and holding the individual information together with the tag information,
    The reading means reads the tag information image,
    The authenticity of the article is determined based on whether the tag is registered in the holding unit based on tag information indicated by the tag information image read by the reading unit by the collating unit. The article management system according to claim 1 or 2 .
  4. 4. The article management system according to claim 3 , wherein the collating unit collates the individual information registered in the registration holding unit with the characteristics of the second area.
  5.   A second region larger than the first region including the first region set on the individual surface on which the random features are distributed is provided as a non-image portion, and is read from the first region. A true / false determination device that determines the authenticity of a tag on which an individual information image that enables identification of the individual based on a feature indicating the first region is formed,
      A feature of the individual surface of the second region and a reading control means for controlling a reading means for reading the individual information image;
      Information conversion means for converting the characteristics of the second region read by the reading means and the individual information based on the individual information image into comparable information;
      A correlation value between the first area specified by the individual information from the information converted by the information conversion means and a third area having the same size as the first area extracted from the second area Computing means for repeating the computation while moving the extraction position of the third region within the second region;
      The maximum value of the plurality of calculated correlation values is equal to or greater than a first predetermined value, and the value obtained by subtracting the average value of the correlation values from the maximum value of the correlation values is obtained by dividing by the standard deviation of the correlation values Whether or not the first area is included in the second area is checked based on whether or not the normalized score of the maximum correlation value is equal to or greater than a second predetermined value. Determining means for determining the authenticity of the tag;
      A true / false determination device.
  6.   First region reading means for reading a random feature distributed along the individual surface used for creating a tag attached to an article over a first region of the individual surface, and the first region reading unit Read information conversion means for converting the read image information indicating the first area as individual information that is information specific to the individual, and a predetermined larger than the first area including the first area on the individual surface Image forming means for forming, on the individual surface, an individual information image indicating the individual information converted by the read information conversion means, with the second area set as a range as a non-image area A tag creation device;
      A tag created by the tag creation device;
      The authenticity determination device according to claim 5, wherein the authenticity of the tag is determined.
      Tag management system including.
  7. A second region larger than the first region including the first region set on the individual surface on which the random features are distributed is provided as a non-image portion, and is read from the first region. A computer used as a true / false determination device for determining the authenticity of a tag on which an individual information image capable of specifying the individual based on the characteristics indicating the first region is formed,
      A reading control means for controlling characteristics of the individual surface of the second region and a reading means for reading the individual information image;
      Information conversion means for converting the characteristics of the second region read by the reading means and the individual information based on the individual information image into comparable information;
      A correlation value between the first area specified by the individual information from the information converted by the information conversion means and a third area having the same size as the first area extracted from the second area Computing means for repeating the computation while moving the extraction position of the third region within the second region;
      The maximum value of the plurality of calculated correlation values is equal to or greater than a first predetermined value, and the value obtained by subtracting the average value of the correlation values from the maximum value of the correlation values is obtained by dividing by the standard deviation of the correlation values. Whether or not the first area is included in the second area is checked based on whether or not the normalized score of the maximum correlation value is equal to or greater than a second predetermined value. Determination means for determining the authenticity of the tag;
      Program to function as.
JP2004194939A 2004-06-30 2004-06-30 Tag creation method, tag creation device, tag, and article management system Active JP4661107B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2004194939A JP4661107B2 (en) 2004-06-30 2004-06-30 Tag creation method, tag creation device, tag, and article management system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2004194939A JP4661107B2 (en) 2004-06-30 2004-06-30 Tag creation method, tag creation device, tag, and article management system

Publications (2)

Publication Number Publication Date
JP2006018525A JP2006018525A (en) 2006-01-19
JP4661107B2 true JP4661107B2 (en) 2011-03-30

Family

ID=35792747

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2004194939A Active JP4661107B2 (en) 2004-06-30 2004-06-30 Tag creation method, tag creation device, tag, and article management system

Country Status (1)

Country Link
JP (1) JP4661107B2 (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4706574B2 (en) 2006-06-30 2011-06-22 富士ゼロックス株式会社 Printing system and program
FR2916678A1 (en) * 2007-06-01 2008-12-05 Advanced Track And Trace Sa Document/product e.g. bank card, securing method, involves representing information by varying cells appearance, and printing form by applying printing conditions, where form detects document copy that modifies cells appearance
DE102009016194A1 (en) * 2008-04-23 2009-10-29 Heidelberger Druckmaschinen Ag Method for producing a security feature on a flat substrate
JP5019183B2 (en) * 2008-05-30 2012-09-05 富士ゼロックス株式会社 Original collation apparatus, original collation method, and original collation program
US9473303B2 (en) * 2013-05-23 2016-10-18 Rosemount Inc. Method and system for product authentication
JP6247111B2 (en) * 2014-02-17 2017-12-13 株式会社日立システムズ Color code authentication device, color code authentication system, color code authentication program, and color code authentication method
JP2017083915A (en) * 2014-02-19 2017-05-18 アイコンコード株式会社 Two-dimensional code, two-dimensional code system, two-dimensional code imaging terminal and information processing method using two-dimensional code

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002103782A (en) * 2000-09-28 2002-04-09 Miyake:Kk Antifalsifying label with printed pasting surface
JP2002117165A (en) * 2000-10-06 2002-04-19 Big Alpha Co Ltd Brand mark and commodity collation system using the same
JP2004102562A (en) * 2002-09-09 2004-04-02 Fuji Xerox Co Ltd Paper identifying and collating device and paper identifying and collating method
JP2004112644A (en) * 2002-09-20 2004-04-08 Fuji Xerox Co Ltd Original-registering device, original-confirming device, and mark for collating original

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002103782A (en) * 2000-09-28 2002-04-09 Miyake:Kk Antifalsifying label with printed pasting surface
JP2002117165A (en) * 2000-10-06 2002-04-19 Big Alpha Co Ltd Brand mark and commodity collation system using the same
JP2004102562A (en) * 2002-09-09 2004-04-02 Fuji Xerox Co Ltd Paper identifying and collating device and paper identifying and collating method
JP2004112644A (en) * 2002-09-20 2004-04-08 Fuji Xerox Co Ltd Original-registering device, original-confirming device, and mark for collating original

Also Published As

Publication number Publication date
JP2006018525A (en) 2006-01-19

Similar Documents

Publication Publication Date Title
JP4965277B2 (en) An improved technique for detecting, analyzing and using visible authentication patterns
US7497379B2 (en) Counterfeit and tamper resistant labels with randomly occurring features
US7251347B2 (en) System and method for authentication of a workpiece using three dimensional shape recovery
US8144368B2 (en) Automated methods for distinguishing copies from original printed objects
EP0889448B1 (en) Method for preventing counterfeiting of articles of manufacture
US9412143B2 (en) Active images through digital watermarking
US8280101B2 (en) Identification documents and authentication of such documents
DE69908425T2 (en) Method and system for authenticating items
EP0730243B1 (en) Identification card verification system and method
US20060157559A1 (en) Systems and methods for document verification
JP5174151B2 (en) Method and apparatus for securing a document
US20030138128A1 (en) Personal document authentication system using watermarking
KR100405828B1 (en) Apparatus and method for producing a document which is capable of preventing a forgery or an alteration of itself, and apparatus and method for authenticating the document
US7766241B2 (en) Barcode for two-way verification of a document
US20040065739A1 (en) Barcode having enhanced visual quality and systems and methods thereof
US7152786B2 (en) Identification document including embedded data
US7025269B2 (en) Barcodes including embedded security features and space saving interleaved text
DE60225385T2 (en) Autentisches Document and its production process
US6940995B2 (en) Method for embedding and extracting text into/from electronic documents
US6980654B2 (en) System and method for authenticating an article
US7080041B2 (en) System and method for production and authentication of original documents
US20020170966A1 (en) Identification document including embedded data
JP3373811B2 (en) Method and apparatus for embedding and detecting watermark information in black and white binary document image
US6292092B1 (en) Secure personal identification instrument and method for creating same
EP2036002B1 (en) Method and device for making documents secure

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20070517

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20100226

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20100309

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20100510

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20101207

A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20101220

R150 Certificate of patent or registration of utility model

Ref document number: 4661107

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150

Free format text: JAPANESE INTERMEDIATE CODE: R150

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20140114

Year of fee payment: 3