JP2006164180A - Solid identification apparatus and method - Google Patents

Solid identification apparatus and method Download PDF

Info

Publication number
JP2006164180A
JP2006164180A JP2004358692A JP2004358692A JP2006164180A JP 2006164180 A JP2006164180 A JP 2006164180A JP 2004358692 A JP2004358692 A JP 2004358692A JP 2004358692 A JP2004358692 A JP 2004358692A JP 2006164180 A JP2006164180 A JP 2006164180A
Authority
JP
Japan
Prior art keywords
information
solid
image
registration
identification
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.)
Granted
Application number
JP2004358692A
Other languages
Japanese (ja)
Other versions
JP4655615B2 (en
Inventor
Tetsuya Kimura
Tadashi Shimizu
哲也 木村
正 清水
Original Assignee
Fuji Xerox Co Ltd
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 Fuji Xerox Co Ltd, 富士ゼロックス株式会社 filed Critical Fuji Xerox Co Ltd
Priority to JP2004358692A priority Critical patent/JP4655615B2/en
Publication of JP2006164180A publication Critical patent/JP2006164180A/en
Application granted granted Critical
Publication of JP4655615B2 publication Critical patent/JP4655615B2/en
Application status is Active legal-status Critical
Anticipated expiration legal-status Critical

Links

Abstract

To identify a solid in a short time without using information other than information obtained by reading the solid.
A random change pattern of irregularities on a paper surface caused by the entanglement of a fibrous material in a predetermined area on paper to be registered is read, divided into a plurality of small areas, and an average in units of each small area Registered image classification data in which the brightness is arranged in a certain order is generated. A predetermined area on the paper to be collated is read, collation image classification data similar to the registered image classification data is generated, and among the registered image data stored and registered, the corresponding registered image classification data is the collation image classification data. Only the matching data is collated with the collation image data.
[Selection] Figure 1

Description

  The present invention relates to a solid identification device and method, and more particularly, to a solid identification device that identifies a solid having a random and optically readable characteristic distributed on a surface, and the solid identification device. The present invention relates to an applicable solid identification method.

  In recent years, as the performance of copying machines and printers has improved, there have been an increasing number of cases where copies of banknotes, securities, etc., have been abused by copying machines and printers. As a technique that can also be used for deterrence, individual papers can be used by utilizing the fact that the transparency of the paper or the unevenness of the paper surface changes randomly due to the random nature of the entanglement of the fibrous material that forms the paper. A technique for distinguishing has been proposed (see, for example, Patent Document 1). This technology uses various types of paper documents (in addition to banknotes and securities as described above, such as passports, various rights documents, resident's cards, birth certificates, insurance certificates, guarantees, confidential documents, books, etc.) Therefore, it can be used not only for authenticity determination of a paper document and confirmation of originality but also for management of a paper document (for example, a book).

  In the above-described technology, paper documents are identified by reading in advance a random change pattern of paper transparency or paper surface irregularities in an authentic paper document (original or managed paper document), and using the read result as information on a paper document, for example. This is done by recording and reading a random change pattern of paper transparency or paper surface irregularities in the paper document to be identified, and comparing the read result with the information recorded in the paper document. When it is not desirable or difficult to record new information on the paper document to be performed, the reading result for the genuine paper document is stored as image information in another storage medium, and the reading result for the document to be identified Is compared with the image information stored in the storage medium to identify the paper document. However, in this case, as the number of image information stored in the storage medium increases, there is a problem that the time required for collating the read result with respect to the document to be identified increases. The above technique can be applied not only to the identification of paper documents, but also to solids that have random and optically readable unique features appearing on the surface. The same problem occurs in

  By the way, in fingerprint collation, when a large number of fingerprints are registered in the fingerprint database, it takes a long time for the collation process to sequentially collate the fingerprints to be collated with the many fingerprints registered in the fingerprint database. There is the same problem as described above. In order to solve this problem, Patent Document 2 discloses a technique for registering a fingerprint together with a personal identification number in a fingerprint database and shortening the time required for collation processing by shortening and grouping the personal identification numbers to prevent an input error. Has been proposed.

Further, Patent Document 3 stores additional information such as a finger number, gender, race, pattern type, 10 fingerprint type combination, birth year, and region type corresponding to each fingerprint image, and When a mismatch between each item of the additional information and each item of the additional information of the specific fingerprint image is detected, the time required for the verification process is shortened by omitting the verification between the fingerprint image to be verified and the specific fingerprint image. Techniques to do this are disclosed.
Japanese Examined Patent Publication No. 6-16312 JP-A-2-005130 JP-A-7-29003

  However, the techniques described in Patent Documents 2 and 3 each register fingerprint attribute information (other information that can be used for fingerprint identification) together with the fingerprint, and use this attribute information to shorten the verification time. When this technology is applied to identification of a solid, it is necessary to input solid attribute information when registering a reading result for the solid as image information in a storage medium and collating a solid to be collated. As a result, the processing cannot be automated, and there is a problem that the operator is burdened and the processing takes time. Further, since an input device is required, there is a problem that the cost of the device increases. Further, when the solid to be identified is a solid having almost no features that can be used for identification other than the image information (reading result), such as unprinted printing paper, it is described in Patent Documents 2 and 3. It is difficult to apply the technology.

  The present invention has been made in consideration of the above facts, and an object thereof is to provide a solid identification device and a solid identification method capable of identifying a solid in a short time without using information other than information obtained by reading the solid. It is.

  In order to achieve the above object, a solid identification device according to the invention described in claim 1 has a randomness distributed on the surface of the solid to be registered and is optically readable and unique to the solid to be registered. Registration information including first image information obtained by optically reading a feature and first classification information representing a predetermined feature amount of the first image generated from the first image information is registered as a plurality of registration targets. Storage means for storing each of the solids; reading means for optically reading the unique characteristics of the solids to be identified that are randomly distributed and optically readable on the surface of the solids to be identified; and Generating means for generating second classification information representing the predetermined feature amount of the second image from second image information obtained by reading by the reading means; and a plurality of registration information stored in the storage means. Of the first Searching for registration information whose type information is the same as or similar to the second classification information generated by the generating means, and comparing the first image information included in the registration information extracted by the search with the second image information And an identification means for identifying the identification object solid.

  The storage means according to the first aspect of the present invention optically reads the characteristics unique to the registration target solid having randomness distributed on the surface of the registration target solid. Registration information including the obtained first image information and first classification information representing a predetermined feature amount of the first image (image represented by the first image information) generated from the first image information is a plurality of registration target solids. Is stored for each. The solid according to the present invention may be a solid having randomness and optically readable solid-specific features distributed on the surface, and may be the paper described in claim 5 or the above-mentioned Other solids that meet the requirements may be used. In addition, when the identification of the solid according to the present invention is used for the determination of authenticity of the solid or the confirmation of the originality, the real solid or the solid used as the original becomes a solid to be registered. When used for solid management, the solid to be managed becomes the solid to be registered.

  Further, in the first aspect of the invention, the randomness distributed on the surface of the identification target solid (for example, the authenticity determination target, the originality confirmation target, or the management target solid) is optically readable. The characteristic unique to the individual to be identified is optically read by the reading means, and the generating means is configured to obtain a predetermined second image (an image represented by the second image information) from the second image information obtained by reading by the reading means. Second classification information representing the feature amount is generated. Then, the identification unit searches for registration information that is the same as or similar to the second classification information generated by the generation unit from among the plurality of registration information stored in the storage unit, and is extracted by the search The identification target solid is identified by collating the first image information included in the registration information with the second image information.

  Thus, in the first aspect of the invention, only the first image information whose corresponding first classification information is the same as or similar to the second classification information is compared with the second image information. Even when the registered information (first image information) is stored, the first image information to be collated with the second image information is narrowed down based on the first classification information and the first classification information. Can be identified in a short time. The second classification information (and the first classification information) according to the first aspect of the invention is information generated from the second image information (or the first image information), and the first aspect of the invention is the second classification information. Since the identification time of the solid is reduced by narrowing down the first image information to be collated with the second image information using the information (and the first classification information), the identification target solid can be identified in a short time. In addition, it is not necessary to use attribute information other than information obtained by reading a solid. Therefore, the invention described in claim 1 can be applied to a solid having almost no features that can be used for identification other than image information (reading result), and it is not necessary to input attribute information. (Registration information generation / storage) can be automated, and it is possible to avoid a burden on the operator and a time for processing such as identification of a solid.

  In the first aspect of the present invention, since the unique features distributed on the surface of the solid are optically readable features, the first image information and the second image information are, for example, claims. As described in 2, the reflected light or transmitted light for each minute unit region in the predetermined region of the registration target solid or identification target solid when the predetermined region on the surface of the registration target solid or identification target solid is irradiated with light. It is possible to apply information representing the brightness of In this case, for example, as described in claim 2, the reading unit irradiates a predetermined area on the surface of the identification target solid with light, and determines the brightness of the reflected light or the transmitted light within the predetermined area of the identification target solid. By detecting each area, the second image information can be obtained.

  In the present invention, as the first classification information and the second classification information, any information representing a predetermined feature amount of the first image or the second image can be applied, but the first image information and the second image As information, when applying the information indicating the brightness of reflected light or transmitted light for each minute unit area in the predetermined area of the registration target solid or identification target solid as described above, the first classification information and the second classification information, For example, as described in claim 3, as a predetermined feature amount, a small area having a larger area than a minute unit area when a predetermined area on the surface of the registration target solid or the identification target solid is irradiated as a unit. It is preferable to apply information indicating the magnitude relation of the average brightness of reflected light or transmitted light in the predetermined area of the registration target solid or identification target solid.

  Although depending on the type of solid to which the present invention is applied, for example, a solid such as paper may cause discoloration such as yellowing on the surface due to the influence over time or the storage environment. The brightness of reflected light or transmitted light for each minute unit region also changes. However, since the discoloration in the solid such as paper occurs substantially uniformly on the entire surface of the solid, even if the discoloration occurs on the surface of the solid, the brightness of the reflected light or transmitted light in each minute unit area within the predetermined area is small or large. In most cases, the relationship does not change. In the invention according to claim 3, as the first classification information and the second classification information, information indicating the magnitude relation of the average brightness of the reflected light or transmitted light with a small area larger than the minute unit area as a unit is used. Therefore, compared to the case where information representing the average brightness of reflected light or transmitted light in units of small areas is used, it is less affected by discoloration, etc. on the surface of the solid. It can suppress that a precision falls.

  In addition, since the small area is an area larger than the minute unit area, the average brightness in units of the small area is reflected or transmitted light in a plurality of corresponding minute unit areas for each small area. Can be obtained by calculating the average value of the brightness. Therefore, the calculation for generating the second classification information (and the first classification information) is simplified, and the data amount of the second classification information (and the first classification information) itself is reduced.

  Further, in the above-described invention according to claim 3, as the first classification information and the second classification information, specifically, as described in claim 4, for example, the average brightness in units of small areas is large or small. It is possible to apply information in which rank information given to individual small areas according to the relationship is arranged in a fixed order (for example, raster order or other order) according to the positional relation of the individual small areas within the predetermined area. it can. In this case, the generation means calculates the average value of the brightness of the plurality of minute unit regions corresponding to the specific small region based on the second image information, and exists in a predetermined region on the surface of the identification target solid. Each sub-region is performed for each sub-region, and rank information is assigned to each sub-region according to the magnitude relationship of average brightness in units of sub-regions, and the rank information assigned to the individual sub-regions according to a certain order By rearranging, the second classification information can be generated.

  By using the above information as the first classification information and the second classification information, the ranking information given to each small area will be arranged in the same order on the first classification information and the second classification information, By simply comparing the first classification information and the second classification information, it is possible to determine whether the magnitude relation of the average brightness for each small area is the same or similar. Accordingly, it is not necessary to add information for identifying which small region corresponds to the individual rank information constituting the first classification information and the second classification information to the individual rank information. The data amount of the classification information and the second classification information can be further reduced.

  In the invention according to any one of claims 1 to 4, for example, the paper described in claim 5 can be applied as the registration target solid and the identification target solid. In this case, as a characteristic unique to the registration target solid or the identification target solid solid, a random change pattern of paper transparency or paper surface unevenness due to the randomness of the entanglement of the fibrous material forming the paper is used. Can do.

  According to a sixth aspect of the present invention, there is provided a solid identification method for optically reading a characteristic unique to a registration target solid having randomness distributed on the surface of the registration target solid. First classification information representing a predetermined feature amount of the first image is generated from the first image information obtained by the reading, and registration information including the first image information and the first classification information is stored in a storage unit. The plurality of registration target solids are respectively performed, and the unique characteristics of the identification target solids that are optically readable and have randomness distributed on the surface of the identification target solids are optically determined. Reading, generating second classification information representing the predetermined feature amount of the second image from the second image information obtained by the reading, and among the plurality of registration information stored in the storage unit, The first classification information is the above The registered information that is the same as or similar to the formed second classification information is searched, and the first image information included in the registered information extracted by the search is compared with the second image information, thereby identifying the identification target solid. Therefore, similarly to the first aspect of the invention, the solid can be identified in a short time without using information other than the information obtained by reading the solid.

  As described above, the present invention is obtained by optically reading the characteristics unique to the registration target solid having randomness distributed on the surface of the registration target solid. Registration information including one image information and first classification information indicating a predetermined feature amount of the first image generated from the first image information is stored for each of a plurality of registration target solids, and the identification target solids are stored. The predetermined characteristic amount of the second image is optically read from the second image information obtained by optically reading the unique characteristic of the identification target having randomness distributed on the surface and optically readable. The second classification information representing the second classification information is generated, the registration information that is the same as or similar to the second classification information generated by the first classification information is searched, and the first image information included in the registration information extracted by the search is the second image. Identification target by collating with information Since so as to identify the body, the solid can be identified in a short time without using information other than the information obtained by reading the solid has an excellent effect that.

  Hereinafter, an example of an embodiment of the present invention will be described in detail with reference to the drawings. FIG. 1 shows a solid identification system 10 according to the present embodiment. In the solid identification system 10, a registration device 12, a verification device 14, and a storage device 16 (corresponding to storage means according to the present invention) for storing an image database 18 are connected to each other via a communication line 20 (for example, a network such as a LAN). It is configured.

  The registration device 12 optically uses, as a registered image, characteristics unique to the registration target solid (light-dark change pattern) that are distributed on the surface of the registration target solid (for example, paper) and are optically readable. Image reading unit 12A, a storage unit 12B for storing image data (registered image data) obtained by reading by the image reading unit 12A, and a registration obtained by reading by the image reading unit 12A A classification data generation unit 12C that generates registration image classification data representing predetermined characteristics of a registration image from image data, and a registration control unit 12D that registers registration image data and registration image classification data in the image database 18 are configured. Yes.

  In addition, the collation device 14 collates the characteristics (intensity change pattern) specific to the solid to be collated and optically readable with randomness distributed on the surface of the solid (for example, paper) to be collated. Obtained by reading by the image reading unit 14A, an image reading unit 14A that is optically read, a storage unit 14B that includes a memory or the like and that stores image data (collation image data) obtained by reading by the image reading unit 14A, and the like. A classification data generation unit 14C that generates collation image classification data representing a predetermined feature of the collation image from the collation image data, and registered image data and registration image in which the collation image data and the collation image classification data are registered in the image database 18. A collation control unit 14D that collates with the classification data is included.

  In addition, when applying paper as a solid subject of registration and verification, the registration device 12 can be incorporated in, for example, the color printer 24 shown in FIG. The color printer 24 includes a photosensitive drum 26 as an image carrier, and the photosensitive drum 26 is charged by a charger 28. A light beam scanning device that emits a light beam that is modulated in accordance with the image to be formed and deflected along the main scanning direction (direction parallel to the axis of the photosensitive drum 26) above the photosensitive drum 26. 30 is arranged. The light beam emitted from the light beam scanning device 30 scans the circumferential surface of the photosensitive drum 26 in the main scanning direction, and at the same time, the photosensitive drum 26 is rotated to perform sub-scanning. An electrostatic latent image is formed on the peripheral surface.

  Further, a multicolor developing device 32 is arranged on the right side of the photosensitive drum 26 in FIG. The multicolor developing device 32 includes developing devices 32A to 32D loaded with toners of any one of C (cyan), M (magenta), Y (yellow), and K (black). The electrostatic latent image formed in (1) is developed into one of C, M, Y, and K colors. In the formation of a full-color image in the color printer 24, an electrostatic latent image is formed on the same area on the photosensitive drum 26 and developed in different colors, and each color is formed on the area. The toner images are sequentially superimposed.

  An endless transfer belt 34 is disposed in the vicinity of the photosensitive drum 26, and a sheet tray 38 for storing the recording sheet 36 is disposed below the position where the transfer belt 34 is disposed. The peripheral surface of the transfer belt 34 is in contact with the peripheral surface of the photosensitive drum 26 on the downstream side of the developing position by the multicolor developing device 32 along the rotation direction of the photosensitive drum 26, and is formed on the photosensitive drum 26. The toner image thus transferred is temporarily transferred to the transfer belt 34, and is then transferred again to the recording paper 36 that is pulled out from the paper tray 38 and conveyed to the position where the transfer belt 34 is disposed. A fixing device 40 is disposed in the middle of the conveyance path of the recording paper 36 toward the outside of the machine to the color printer 24, and the toner image is fixed on the recording paper 36 to which the toner image is transferred by the fixing device 40. Later, it is discharged out of the machine to the color printer 24.

  In addition, a reading unit 42 is provided in the middle of a conveyance path (indicated by an imaginary line in FIG. 2) of the recording paper 36 from the paper tray 38 to the arrangement position of the transfer belt 34. The reading unit 42 includes a light emitter 42A for irradiating the recording paper 36 with light and a plurality of light receiving elements arranged in a two-dimensional manner, and a light receiver for receiving the light emitted from the light emitter 42A and reflected from the recording paper 36. (Area sensor) 42 </ b> B and a signal processing circuit (not shown) for converting the signal output from the light receiver 42 </ b> B into digital data and outputting it (not shown), and the fibrous material forming the recording paper 36. A random change in the light reflectance distributed along the surface of the recording paper 36 due to the randomness of the entanglement can be read at a predetermined resolution (for example, 400 dpi) and a predetermined gradation (for example, 8-bit gray scale). Has been.

  A printer controller 44 is connected to the light beam scanning device 30. The printer controller 44 is connected to an operation unit (not shown) including a keyboard and a display, and a reading unit 42, and further a personal computer (not shown) for inputting data to be printed on the recording paper 36. Are omitted) or connected via a network such as a LAN. The printer controller 44 includes a microcomputer, and controls the operation of each unit of the color printer 24 including the light beam scanning device 30.

  Incorporating the registration device 12 in the color printer 24 having the above configuration uses the reading unit 42 as the image reading unit 12A, the built-in memory of the printer controller 44 as the storage unit 12B, and the printer controller 44 as the classification data generation unit. 12C and the registration control unit 12D can be configured to function (store a registration program for performing a registration process, which will be described later, in a nonvolatile built-in memory and execute the registration program as necessary). .

  In addition, when paper is applied as a registration target and a verification target, the verification device 14 can be realized by, for example, a personal computer (PC) 50 and a scanner 52 shown in FIG. Although not shown, the PC 50 includes a CPU, a ROM, a RAM, and an input / output port, which are connected to each other via a bus. In addition, a display, a keyboard, a mouse, and a hard disk drive (HDD) are connected to the input / output ports. The HDD stores an OS and various application software programs. The functioning of the PC 50 and the scanner 52 as the collating device 14 is that the scanner 52 is used as the image reading unit 14A (reading unit according to the present invention), the internal memory of the PC 50 is also used as the storage unit 14B, and the PC 50 generates classification data. This can be realized by functioning also as the unit 14C and the collation control unit 14D (a collation program for performing collation processing described later is stored in the HDD and the collation program is executed as necessary). Note that the PC 50 and the scanner 52 can function as the registration device 12, and can also function as the registration device 12 and the verification device 14.

  Next, the operation of this embodiment will be described by taking an example in which the registration device 12 is built in the color printer 24 and the PC 50 and the scanner 52 function as the verification device 14. When the registration of information for identifying the recording paper 36 is instructed when the document is printed on the recording paper 36, the color printer 24 incorporating the registration device 12 performs the registration processing shown in FIG. In the present embodiment, the information registration described above is performed when, for example, a document printed on the recording paper 36 is an original, and there is a possibility that the document is confirmed to be the original, or when the document is printed on the recording paper 36. It is instructed when it is desired to manage the distribution of When registration of information for identifying the recording paper 36 is instructed, the printer controller 44 of the color printer 24 executes the registration process shown in FIG. 4 by executing the above-described registration program.

  In this registration process, first, in step 80, the recording paper 36 (paper to be registered) for printing a document is taken out from the paper tray 38 and conveyed to the arrangement position (reading position) of the reading unit 42. When the recording paper 36 reaches the reading position, the conveyance of the recording paper 36 is temporarily stopped, and the reading unit 42 causes the reading paper 42 to move on the recording paper 36 with a predetermined resolution (for example, 400 dpi) and a predetermined gradation (for example, 8-bit gray scale). A predetermined area (for example, an area having a size of 32 × 32 dots (about 2 mm × about 2 mm)) is read. As a result, the reading unit 42 causes random irregularities on the surface of the paper in a predetermined area of the recording paper 36 to be read due to the randomness of the entanglement of the fibrous material forming the recording paper 36 to be read. Digital image data representing changes (referred to as registered image data) is output. In this embodiment, since the reading unit 42 is configured to detect the light reflected from the recording paper 36, the registered image data is data representing a random change in the unevenness of the paper surface in a predetermined area of the recording paper 36. However, when the reading unit 42 is configured to detect light transmitted through the recording paper 36, the registered image data is data representing a random change in the transparency of the paper within a predetermined area of the recording paper 36. The registered image data corresponds to the first image information according to the present invention, and in the next step 82, the registered image data output from the reading unit 42 is temporarily stored in the built-in memory (storage unit 12B).

  When the reading resolution is 400 dpi, the reading gradation is 8-bit gray scale, and the predetermined area to be read is 32 × 32 dots, the data amount of the registered image data is 1024 bytes, and the level of each pixel (dot) The tone value (brightness value) is an integer value in the range of 0 to 255. FIG. 5 shows an example of an image obtained by visualizing the image represented by the reference data (contrast correction for easy visual observation) based on the reference data obtained by the above reading. The light receiver 42B of the reading unit 42 may be a line sensor. In this case, the reading of the recording paper 36 passing through the reading position without temporarily stopping the conveyance of the recording paper 36, A predetermined area can be read by performing reading while moving the reading unit 42 while the recording paper 36 is temporarily stopped, or by moving both. Further, the reading unit 42 may be provided on the paper tray 38.

  In the present embodiment, the position of the predetermined area on the recording paper 36 is preferably fixed, but the position of the predetermined area on the recording paper 36 may be changed depending on the document. However, when toner (or ink) adheres to a predetermined area on the recording paper 36 by printing after reading the predetermined area, there is a very high possibility that erroneous identification will occur in the collation process described later. Therefore, when the position of the predetermined area is fixed, the position of the recording paper 36 where the toner is not likely to adhere (for example, a position corresponding to a position outside the printable range of the color printer 24) is set. When changing according to the document, it is desirable to determine a range of the recording paper 36 where toner or the like is not attached by printing based on the print data, and set a predetermined region within the determined range. The predetermined area can be read after printing on the recording paper 36. In this case, the predetermined area is set within a range where the toner or the like on the recording paper 36 is not attached. Can be realized easily.

  The next steps 84 to 90 are processes corresponding to the classification data generation unit 12C, and generate registration image classification data from the registration image data stored in the built-in memory. That is, in step 84, the registered image represented by the registered image data temporarily stored in the built-in memory is divided into a plurality of small areas as shown in FIG. FIG. 6 shows an example in which a registered image of 32 × 32 dots is divided into four square regions each having 8 × 8 dots by dividing the registered image into 32 × 32 dots in the vertical direction and the horizontal direction. Yes. In FIG. 6, the individual small areas are distinguished from each other by giving the symbols 1A, 1B, 1C, 1D, 2A, 2B,..., 4C, 4D.

  In the next step 86, the average brightness for each small area is calculated. Each small area is composed of 8 × 8 = 64 dots, and the brightness value of each dot is an integer value (8 bits) in the range of 0 to 255. Therefore, the average brightness of a single small area is 64 It is obtained by calculating the average value of 64 8-bit data representing the brightness value of each dot. An example of the calculation result of the average brightness for each small area is shown in FIG. In FIG. 7, the vertical axis represents the lightness value, and the horizontal axes 1 to 4 and A to D represent codes for distinguishing individual small regions. The difference in the brightness value of each dot in the registered image data reflects a random change pattern of the unevenness of the paper surface in a predetermined area of the recording paper 36. Therefore, the average brightness for each small area calculated in step 86. In addition, as shown in FIG. 7 as an example, there are differences for each small area according to a random change pattern of the unevenness of the paper surface within a predetermined area of the recording paper 36.

  In the next step 88, the average brightness for each small area calculated in step 86 is compared with each other, thereby recognizing the magnitude relationship of the average brightness for each small area (for example, increasing the average brightness for each small area in ascending order). (Or sort in descending order, etc.), and ranks 1 to 16 are assigned to each small area as rank information in accordance with the magnitude relation of average brightness (see FIG. 8 (A) as an example). In order to make the number of bits of information uniform, ranks 10 to 16 among ranks 1 to 16 are replaced with ranks A to G (see FIG. 8B as an example). In step 90, the registered image classification data is generated by arranging the rank information assigned to each small area in a predetermined order, and the generated registered image classification data is temporarily stored in the built-in memory. Accordingly, assuming that the predetermined order is 1A, 1B, 1C, 1D, 2A, 2B,..., 4C, 4D, the registered image classification data “D53194627EB8AFCG” is obtained from the rank information shown in FIG. "Is generated.

  The registered image classification data described above corresponds to the first classification information according to the present invention (specifically, the first classification information described in claims 3 and 4). By using the registered image classification data described above as the first classification information, even if a color change or the like occurs on the surface of the recording paper 36 until the collation process described later is performed, the collation process accuracy is improved. It can suppress that it falls.

  If the difference in average brightness of some of the small areas is small, the collation target paper is the same as the registration target paper depending on the reading conditions of the predetermined area in the collation process described later. However, the magnitude relationship of the average brightness for each small area may be switched. In consideration of this, in the previous step 88, it is also determined whether or not the difference in average brightness for each small area is larger than a predetermined value. May be given. As an example, FIG. 8C shows the difference in average brightness with respect to the calculation result of average brightness for each small area to which the rank shown in FIG. 8A is assigned unless the magnitude of the difference in average brightness is considered. If it is 3 or less, the result when the same ranking is given is shown. When the ranks 10 to 16 in the ranks shown in FIG. 8C are replaced with the ranks A to G, the rank information given to each small area changes as shown in FIG. When arranged in order, data “D52172627DB7AFBF” is obtained as registered image classification data.

  Also, the rank for each small area can be expressed by 4 bits. When the rank information for each small area is 4 bits, the data amount of the registered image classification data is 4 × 16 = 64 bits = 8 bytes. Therefore, from the 1024 bytes of registered image data, registered image classification data that roughly represents the brightness change pattern in the registered image with a data amount of 1/128 is obtained.

  In step 92, the registered image data and the registered image classification data temporarily stored in the built-in memory are read from the built-in memory and transferred to the storage device 16 via the communication line 20, thereby identifying the recording sheet 36 to be registered. The registered image data and the registered image classification data (registration information according to the present invention) are stored and registered in the image database 18 as the information of the registration information, and the registration process is terminated. This step 92 corresponds to the registration control unit 12D. Since the registration process described above is executed each time registration of information for identifying the recording sheet 36 to be registered is instructed, as shown in FIG. Registered image classification data is stored and registered for each of a large number of recording sheets 36.

  Note that the image database 18 is not limited to storing and registering only registered image data and registered image classification data. The contents printed on the recording paper 36 to be registered by the color printer 24 and registered in the image database 18 are not limited. Information that can be automatically registered in the image database 18, such as date and time, device number of the registration device 12 (color printer 24), status information indicating the status of the document (for example, print completion status), etc. (requires manual input) May be stored and registered in the image database 18 together. Further, storing and registering registered image data and registered image classification data in the image database 18 is not limited to printing at the time of printing a document on the recording paper 36 by the color printer 24. For example, the PC 50 and the scanner 52 are registered. The registered image data and registered image classification data may be stored and registered for a document printed on the recording paper 36 as a target. Specifically, for example, when the purpose of information registration is management of distribution of books and the like, registered image data and registered image classification data are stored and registered in the image database 18 at the bookstore when selling books and the like to customers. You may do it.

Further, when an instruction to execute document printing and registration processing is given, registration image data and registration image classification data are stored and registered in the image database 18 for all the recording sheets 36 on which the document is printed. It may be. Further, the registered image data and registered image classification data in the image database 18 are stored and registered, and the recording paper 36 that has been printed is automatically arranged, and further output in a bundle with registered bands. Next, collation processing realized by the PC 50 and the scanner 52 functioning as the collation device 14 will be described with reference to the flowchart of FIG. The collation process is instructed to be executed, for example, when it is desired to confirm that the document printed on the recording paper 36 is the original document. In addition, in order to manage the distribution of books, when purchasing used books (secondhand books), etc., execution is instructed if it is desired to confirm whether the used books to be purchased are properly purchased at bookstores, etc. Sometimes. When the execution of the collation process is instructed, the collation program is read from the HDD of the PC 50, and the collation process is realized by the read collation program being executed by the CPU of the PC 50.

  In step 100, first, a message for requesting that the document to be collated is set on the scanner 52 (placed on the document table of the scanner 52) is displayed on the display of the PC 50, so that the document to be collated is set on the scanner 52. When it is confirmed that the document to be collated is set on the scanner 52, the scanner 52 is instructed to read the document placed on the platen, and the document on which the document to be collated is printed. A predetermined area is read by the scanner 52. As a result, a predetermined area on the paper (collation target paper) on which the document to be collated is printed is read by the scanner 52 at a predetermined resolution (for example, 400 dpi) and a predetermined gradation (for example, 8-bit gray scale). From the scanner 52, digital image data representing a random change in the unevenness of the paper surface in a predetermined area on the paper to be collated due to the randomness of the entanglement of the fibrous material forming the paper to be collated. (Referred to as collation image data) is output. The collation image data corresponds to the second image information according to the present invention, and in the next step 102, the collation image data output from the scanner 52 is temporarily stored in the built-in memory (storage unit 14B) of the PC 50.

  The next steps 104 to 110 are processes corresponding to the classification data generation unit 14C (generation means according to the present invention), and the built-in memory is similar to the steps 84 to 90 of the registration process (FIG. 4) described above. The collation image classification data is generated from the collation image data stored in (1). That is, in step 104, the collation image represented by the collation image data temporarily stored in the built-in memory is divided into a plurality of small areas as in step 84 described above. In step 106, the average brightness for each small area is calculated as in step 86 described above. The difference in the brightness value of each dot in the collation image data reflects a random change pattern of the irregularities on the paper surface in the predetermined area on the paper to be collated, so the average for each small area calculated in step 106 The brightness is also different for each small area according to a random change pattern of the unevenness of the paper surface in a predetermined area on the paper to be verified.

  In the next step 108, as in the above-described step 88, the average brightness of each small area calculated in step 106 is compared with each other to recognize the magnitude relation of the average brightness for each small area. On the other hand, ranks 1 to 16 are assigned as rank information in accordance with the magnitude relation of average brightness, and ranks 10 to 16 are replaced with ranks A to G among the assigned ranks 1 to 16. In step 108, as in step 88 described above, it is also determined whether the difference in average brightness for each small area is larger than a predetermined value. Alternatively, the same order may be given. In step 110, as in step 90 described above, collation image classification data is generated by arranging the rank information assigned to each small area in a predetermined order, and the generated collation image classification data is stored in the built-in memory. To temporarily store.

  As a result, the same data as the registered image classification data (data that roughly represents the lightness change pattern in the verification image with a data amount significantly smaller than that of the verification image data) is generated as the verification image classification data. The collation image classification data described above corresponds to the second classification information according to the present invention (specifically, the second classification information described in claims 3 and 4). Use of the collation image classification data as the second classification information also affects the case where discoloration or the like occurs on the surface of the paper to be collated between the registration process described above and the collation process. It is difficult to receive, and it can suppress that the precision of collation processing falls.

  The next step 112 and subsequent steps are processing corresponding to the collation control unit 14D (identification means according to the present invention). First, in step 112, a single registered image classification data is obtained from the image database 18 stored in the storage device 16. In step 114, the collation image classification data temporarily stored in the built-in memory is collated with the registered image classification data obtained in step 112, and it is determined whether or not they match. If the determination is negative, the process proceeds to step 120, where it is determined whether the collated image classification data temporarily stored in the built-in memory has been collated with all the registered image classification data stored in the image database 18. When determination is denied, it returns to step 112 and repeats the process after step 112. FIG. The registered image classification data is data that roughly represents the lightness change pattern in the registered image with a significantly smaller amount of data than the registered image data, and the collation image classification data also represents the lightness change pattern in the collation image from the collation image data. Therefore, the above-described collation processing in steps 112, 114, and 120 is performed at a very high speed as compared with the case where the registered image data itself and the collation image data itself are collated. be able to.

  Here, if the collation image classification data temporarily stored in the built-in memory matches the registered image classification data acquired from the image database 18, the corresponding collation image data may also coincide with the corresponding registration image data. Judgment is high. For this reason, when the determination in step 114 is affirmed, the process proceeds to step 116, and registered image data corresponding to the registered image classification data used for collation is acquired from the image database 18. In step 118, the collation image data temporarily stored in the built-in memory is collated with the registered image data acquired in step 116, and it is determined whether or not they match. When determination is denied, it transfers to step 120 and collation with collation image classification data and registration image classification data is continued.

  If the determination in step 120 is affirmed without the determination in step 118 being affirmed, it is possible to determine that the paper to be collated is paper in which the registered image data and the registered image classification data are not registered in the image database 18. Therefore, in step 124, a predetermined message is displayed on the display of the PC 50, for example, to notify that the corresponding data is not stored / registered in the image database 18, and the collation process is terminated. Accordingly, for example, if the purpose of the above-described collation processing is confirmation of the originality of the document to be collated, it is possible to identify that the document to be collated is not the original based on the above processing result. If the purpose of is to confirm whether the second-hand books to be purchased are properly purchased at a bookstore, the second-hand books to be purchased are purchased at a bookstore based on the above processing results It can be identified that it is not.

  On the other hand, if the determination in step 118 is affirmed, the process proceeds to step 122 to notify that the corresponding data is stored / registered in the image database 18 by displaying a predetermined message on the display of the PC 50. The verification process ends. Thus, for example, if the purpose of the above-described collation processing is confirmation of the originality of the document to be collated, the document to be collated can be identified as the original based on the above processing result. If the purpose of the processing is to confirm whether the second-hand books to be purchased are properly purchased at a bookstore, the second-hand books to be purchased have been properly purchased at a bookstore based on the above processing results. Can be identified.

  As described above, in the collation processing according to the present embodiment, only the registered image data whose corresponding registered image classification data is the same as the collation image classification data is collated with the collation image data. The image data is narrowed down based on the registered image classification data and the collation image classification data, and it is possible to identify in a short time whether or not the registration image data corresponding to the document to be collated is registered in the image database 18. it can. Also, since the registered image data to be collated with the collation image data is narrowed down using the registered image classification data generated from the registered image data and the collation image classification data generated from the collation image data, It is not necessary to use any other attribute information, and it can be applied to solids (unprinted recording paper 36, etc.) having almost no features that can be used for identification other than image information (reading results), and the processing is automated. be able to.

  In the above description, the storage device 16 that stores the image database 18 is described as an example of the solid identification system 10 having a configuration in which the storage device 16 is connected to the registration device 12 and the verification device 14 via the communication line 20. Instead, the storage device 16 may be built in the registration device 12 or the verification device 14.

  In the above description, the example in which the corresponding registered image data is collated with the collation image data only when the registered image classification data matches the collation image classification data has been described. However, the present invention is not limited to this. Even when registered image classification data having a high similarity to the data (for example, classification data in which the number of different rank information among the rank information constituting each classification data is a predetermined number or less) is found, the corresponding registered image data May be collated with collation image data.

It is a block diagram which shows schematic structure of the solid identification system which concerns on this embodiment. It is a schematic block diagram of the color printer which can incorporate a registration apparatus. It is a perspective view which shows the external appearance of PC and the scanner which can be functioned as a collation apparatus. It is a flowchart which shows the content of the registration process. It is the image figure which visualized an example of the registration image. It is an image figure which shows the division | segmentation of a registration image. It is an image figure which shows an example of the calculation result of the average brightness for every small area | region. It is an image figure explaining classification data generation processing. It is a flowchart which shows the content of collation processing. It is a chart which shows an example of the contents of an image database.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Solid identification system 12 Registration apparatus 14 Collation apparatus 16 Storage apparatus 18 Image database 24 Color printer 42 Reading part 50 PC
52 Scanner

Claims (6)

  1. First image information obtained by optically reading the unique characteristics of the solid to be registered, which is optically readable and has randomness distributed on the surface of the solid to be registered, and the first Storage means for storing, for each of a plurality of registration target solids, registration information including first classification information representing a predetermined feature amount of the first image generated from image information;
    Reading means for optically reading the unique characteristics of the solid to be identified, which are distributed on the surface of the solid to be identified and optically readable;
    Generating means for generating second classification information representing the predetermined feature amount of the second image from second image information obtained by reading by the reading means;
    Of the plurality of registration information stored in the storage means, the first classification information is searched for registration information that is the same as or similar to the second classification information generated by the generation means, and the registration extracted by the search Identification means for identifying the identification target solid by comparing the first image information included in the information with the second image information;
    A solid identification device.
  2. The first image information and the second image information are included in the predetermined area of the registration target solid or the identification target solid when light is irradiated to the predetermined area on the surface of the registration target solid or the identification target solid. It is information representing the brightness of the reflected light or transmitted light for each minute unit area of
    The reading means irradiates a predetermined region on the surface of the identification target solid with light, and detects the brightness of reflected light or transmitted light for each minute unit region in the predetermined region of the identification target solid. 2. The solid identification device according to claim 1, wherein second image information is acquired.
  3.   The first classification information and the second classification information are larger than the minute unit region when the predetermined feature on the surface of the registration target solid or the identification target solid is irradiated with light. The information representing the magnitude relation of the average brightness of reflected light or transmitted light in the predetermined area of the registration target solid or the identification target solid in a unit of a small area. Solid identification device.
  4. In the first classification information and the second classification information, the rank information given to each small area according to the magnitude relation of the average brightness with the small area as a unit, the rank information of the individual small areas in the predetermined area Information arranged in a certain order according to the positional relationship,
    The generation means calculates the average value of the brightness of a plurality of minute unit regions corresponding to a specific small region based on the second image information, and exists in a predetermined region on the surface of the identification target solid. Performing for all small areas, and assigning rank information to each small area according to the magnitude relation of the average brightness with the small area as a unit, and ranking information assigned to each small area in the fixed order The solid identification device according to claim 3, wherein the second classification information is generated by rearranging in response.
  5.   The registration target solid and the identification target solid are paper, and the characteristic unique to the registration target solid or the identification target solid is the transparency of the paper due to the randomness of the entanglement of the fibrous material forming the paper or The solid identification device according to any one of claims 1 to 4, wherein the solid surface is a random change pattern of irregularities on the paper surface.
  6. The unique characteristics of the registration target solid that are optically readable and randomly distributed on the surface of the registration target solid are optically read, and the first image information obtained by the reading is optically read. First classification information representing a predetermined feature amount of one image is generated, and registration information including the first image information and the first classification information is stored in a storage unit for each of a plurality of registration target solids. Every
    Optically reading the solid-specific features of the identification object having randomness and optically readable distribution on the surface of the identification object;
    Generating second classification information representing the predetermined feature amount of the second image from the second image information obtained by the reading;
    Among the plurality of registration information stored in the storage means, the first classification information is searched for the same or similar registration information as the generated second classification information, and is included in the registration information extracted by the search A solid identification method for identifying an identification target solid by comparing first image information with the second image information.
JP2004358692A 2004-12-10 2004-12-10 Solid identification device and program Active JP4655615B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2004358692A JP4655615B2 (en) 2004-12-10 2004-12-10 Solid identification device and program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2004358692A JP4655615B2 (en) 2004-12-10 2004-12-10 Solid identification device and program

Publications (2)

Publication Number Publication Date
JP2006164180A true JP2006164180A (en) 2006-06-22
JP4655615B2 JP4655615B2 (en) 2011-03-23

Family

ID=36666099

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2004358692A Active JP4655615B2 (en) 2004-12-10 2004-12-10 Solid identification device and program

Country Status (1)

Country Link
JP (1) JP4655615B2 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008034944A (en) * 2006-07-26 2008-02-14 Canon Inc Image processing apparatus, and control method and program for image processing apparatus, and storage medium
JP2008060721A (en) * 2006-08-29 2008-03-13 Fuji Xerox Co Ltd Information processing apparatus and program
EP2455890A2 (en) 2010-11-18 2012-05-23 Fuji Xerox Co., Ltd. Image processing system, image processing apparatus and image processing program
JP2017064979A (en) * 2015-09-29 2017-04-06 富士フイルム株式会社 Ink jet printing device and ink jet printing control method

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS6375989A (en) * 1986-09-19 1988-04-06 Alps Electric Co Ltd Picture recognizing system
JP2004334448A (en) * 2003-05-06 2004-11-25 Sony Corp Data processing method and device

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS6375989A (en) * 1986-09-19 1988-04-06 Alps Electric Co Ltd Picture recognizing system
JP2004334448A (en) * 2003-05-06 2004-11-25 Sony Corp Data processing method and device

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008034944A (en) * 2006-07-26 2008-02-14 Canon Inc Image processing apparatus, and control method and program for image processing apparatus, and storage medium
JP4709090B2 (en) * 2006-07-26 2011-06-22 キヤノン株式会社 Image processing apparatus, image processing apparatus control method, and program
US8077342B2 (en) 2006-07-26 2011-12-13 Canon Kabushiki Kaisha Image processing apparatus, method of controlling image processing apparatus, program, and storage medium
JP2008060721A (en) * 2006-08-29 2008-03-13 Fuji Xerox Co Ltd Information processing apparatus and program
US8102576B2 (en) 2006-08-29 2012-01-24 Fuji Xerox Co., Ltd. Method, apparatus, and system of detecting duplicated scanned data of a document
EP2455890A2 (en) 2010-11-18 2012-05-23 Fuji Xerox Co., Ltd. Image processing system, image processing apparatus and image processing program
US8761508B2 (en) 2010-11-18 2014-06-24 Fuji Xerox Co., Ltd. Image processing system, image processing apparatus and computer readable medium
JP2017064979A (en) * 2015-09-29 2017-04-06 富士フイルム株式会社 Ink jet printing device and ink jet printing control method
US10099497B2 (en) 2015-09-29 2018-10-16 Fujifilm Corporation Inkjet printer and method of controlling inkjet printing

Also Published As

Publication number Publication date
JP4655615B2 (en) 2011-03-23

Similar Documents

Publication Publication Date Title
JP3101363B2 (en) User pursuant capable font replacement device including equality indicator
US6873435B1 (en) Print having encoded metadata coupled thereto
EP0940780B1 (en) Image processing device and method for detecting a reference pattern
CA1118108A (en) System for processing documents having written indicia thereon
US5604596A (en) Copying apparatus having determination unit for special original and for controlling copying and marking based on determination
CA2128583C (en) Source verification using images
KR0145763B1 (en) Image forming apparatus
JP4169053B2 (en) Image processing apparatus and image processing method
US9465349B2 (en) Document administration system and document administration method
JP3590812B2 (en) High-speed document confirmation system, confirmation document and document confirmation method
CN100483313C (en) Method and device for processing of information
JP3852234B2 (en) Image processing apparatus and image processing method
JP4103826B2 (en) Authenticity determination method, apparatus and program
JP2003175661A (en) System used in forming test image in digital printer
DE10225700B4 (en) Printer and printing process
US8271864B2 (en) Electronic representations of position-coded products in digital pen systems
WO2007072048A1 (en) Cartridges for reprographics devices
CN102404478B (en) Image forming apparatus and system, information processing apparatus, and image forming method
US8888010B2 (en) Detection of security marks simulating natural defects for embedding information in documents
US7865124B2 (en) Pre-scanning printer with paper fingerprinting
KR100865292B1 (en) Authenticity determination method, apparatus, and computer readable recording medium recording a program
JP2006123505A (en) Apparatus, method and system for forming image
US8335342B2 (en) Protecting printed items intended for public exchange with information embedded in blank document borders
JP2005205797A (en) Printed matter inspection controller, printed matter inspection control method, and printed matter inspection control program
US7624928B2 (en) Method and apparatus for making tags, tag, and system for managing articles

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20071120

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20100802

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20100810

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20101001

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: 20101130

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: 20101213

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

Free format text: PAYMENT UNTIL: 20140107

Year of fee payment: 3

R150 Certificate of patent or registration of utility model

Ref document number: 4655615

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150

Free format text: JAPANESE INTERMEDIATE CODE: R150