JP2019139640A - Authentication system and authentication method - Google Patents

Abstract

To provide an authentication system that enables authentication of originality of an object having a mark and the like attached, is quite difficult to fake even if a mechanism of an authenticity determination is unveiled, and is achievable by a readily device configuration.SOLUTION: An authentication method is configured to: execute template matching to a reading image including an authentication object with a master image as a reference, and acquire an authentication image with the reading image erected; acquire chromatic information for each prescribed region composed of one or a plurality of pixels in the authentication image; determine a differential between chromatic information on one or a plurality of prescribed regions located around each prescribed region for each of the plurality of prescribed regions included in the authentication image, and decide the region serving a plurality of characteristic points from the plurality of prescribed regions included in the authentication image; and conduct matching of a plurality of characteristic points of a storage unit to a plurality of characteristic points of the authentication image on the basis of a differential between chromatic information on each characteristic point in the storage unit and a differential between chromatic information on the plurality of characteristic points of the authentication image.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an authentication technique for authenticating the originality of an object to which all the signs, which are flat objects or three-dimensional objects to which a material constituting the color is fixed, is attached or can be regarded as a sign.

  Conventionally, various authentication technologies have been used to determine whether or not a legitimate subject is legitimate in every aspect of human activity, and more advanced authentication technologies have been demanded from the progress of computerization of the Internet and information. Yes. As a classic authentication technology, it has been done to mark unique shapes such as seals and signatures, but due to counterfeiting, it is now a hologram, crease (watermark), latent image pattern, pearl ink, micro characters In addition to anti-counterfeiting using technologies such as special light-emitting ink and intaglio printing, along with the progress of computerization, certain information such as passwords is currently kept secret by encrypting it. By checking, we try to prevent forgery. In addition, biometric information unique to an individual human body, such as a fingerprint, is registered in advance, and when authentication is required, various biometrics that perform authentication based on whether the biometric information matches the registered biometric information by reading the actual biometric information Authentication technology is also used (for example, Patent Document 1).

JP 2009-205393 A

  However, among the above authentication techniques, a technique using a password has a problem that since the password must be determined in advance and the user itself must be stored, the amount of information is extremely small, and theft and forgery are easy. In the technique using biological information, only a human can determine whether or not it is a legitimate object, and basically it cannot be used for other objects, animals and plants. In recent years, an act of forging the biometric information itself has also occurred, and there is a problem that it is not necessarily a completely secure authentication technique.

  Furthermore, many advanced authentication techniques often add authentication information to an object in advance physically or electronically, and processing to the object is necessary, which hinders the spread of the authentication technique. There is a problem.

  Further, in general authentication technology, registration information as a model (for example, a registered shadow) is compared with authentication information to be authenticated (for example, a shadow to be authenticated). At this time, Usually, the direction of the registration information and the direction of the authentication information do not match, which causes a problem that the authentication accuracy deteriorates.

  The present invention has been made in view of the above-described problems, and does not require processing for an authentication target, and specific information is obtained from image data acquired using a digital imaging device having a simple configuration for individual features of the authentication target. An object of the present invention is to provide an authentication system and an authentication method that extract and determine whether or not an authentication target is valid based on the extracted unique information.

  In order to solve the above-described problem, according to one aspect of the present invention, a read image acquisition unit that acquires a read image that is an image including an authentication target and a master image of the read image by template matching on the basis of the master image. A template matching execution unit that acquires an authentication image obtained by erecting the read image by detecting a shift in the rotation direction from the position, and a predetermined number of pixels included in the authentication image. The color information for each predetermined area that is a size area is acquired, and for each of the plurality of predetermined areas included in the authentication image, the difference in the color information from one or more predetermined areas located around each predetermined area Based on the determination result, a plurality of features indicating the characteristics of the authentication target are selected from the plurality of predetermined areas included in the authentication image. Refer to a storage unit that stores a feature point determination unit that determines a region to be a point, a plurality of feature points of a registered image, and color information differences of each feature point in association with each other. The storage unit based on the difference between the color information of each feature point stored in the storage unit and the difference between the color information of the plurality of feature points of the authentication image determined by the feature point determination unit. And a matching unit that performs matching between the plurality of feature points stored in the image and the plurality of feature points of the authentication image.

  According to another aspect of the present invention, a read image acquisition unit that acquires a read image that is an image including an authentication target for registration, and a position of the master image of the read image by template matching on the basis of the master image. A template matching execution unit that acquires a registered image in which the read image is erected by detecting a shift in the rotation direction of the image, and a predetermined size that includes one or a plurality of pixels in the registered image Color information for each predetermined area is obtained, and for each of the plurality of predetermined areas included in the registered image, the difference in the color information with one or more predetermined areas located around each predetermined area is determined. Then, based on the determination result, a plurality of feature points indicating the feature of the authentication target are selected from the plurality of predetermined regions included in the registered image. A feature point determination unit that determines a region; and a storage unit that stores each feature point and the difference in color information of each feature point in association with each other for the plurality of feature points of the registered image. Registration device.

  According to another aspect of the present invention, there is provided an authentication method executed by a computer apparatus, the step of obtaining a read image that is an image including an authentication target, and the matching of the read image by template matching on the basis of a master image. A step of obtaining an authentication image obtained by erecting the read image by detecting a shift in a rotation direction from the position of the master image; and a predetermined number of pixels included in the authentication image. The color information for each predetermined area that is a size area is acquired, and for each of the plurality of predetermined areas included in the authentication image, the difference in the color information from one or more predetermined areas located around each predetermined area Based on the determination result, a plurality of features indicating the characteristics of the authentication target are selected from the plurality of predetermined areas included in the authentication image. Referring to a storage unit in which a step of determining a region to be a point, a plurality of feature points of an image registered in advance, and a difference in color information of each feature point are stored in association with each other, the storage The plurality of feature points stored in the storage unit based on the difference between the color information of the feature points stored in the unit and the difference in color information of the plurality of feature points of the determined authentication image. An authentication method comprising: matching a feature point with the plurality of feature points of the authentication image.

  According to another aspect of the present invention, there is provided a registration method executed by a computer apparatus, the step of obtaining a read image that is an image including an authentication target for registration, and the reading by template matching on the basis of a master image. Acquiring a registered image in which the read image is erected by detecting a shift in the rotation direction of the image from the position of the master image; and in advance, the registered image is configured by one or more pixels. The color information for each predetermined area that is an area of a predetermined size is acquired, and the color of one or more predetermined areas located around each predetermined area for each of the plurality of predetermined areas included in the registered image A difference in information is determined, and based on the determination result, a feature of the authentication target is indicated from among the plurality of predetermined areas included in the registered image. Determining a region to be a number of feature points; and storing each feature point and the difference of the color information of each feature point in association with each other for the plurality of feature points of the registered image. It is a registration method.

  Moreover, the other aspect of this invention is a computer program for making a computer perform the said method.

  Another aspect of the present invention is a computer-readable recording medium storing a computer program for causing a computer to execute the above method.

It is a figure which shows an example of a structure of the authentication system which concerns on one Embodiment of this invention. It is a flowchart which shows an example of the pre-processing in the authentication method which concerns on one Embodiment of this invention. It is a figure explaining an example of the production | generation method of a template image. It is a figure explaining an example of the production | generation procedure of an edge mask image. It is a flowchart which shows an example of the registration process in the authentication method which concerns on one Embodiment of this invention. It is a figure explaining template matching. It is a figure which shows the specific example of the feature point extraction by the difference calculation in the registration process which concerns on one Embodiment of this invention. It is a figure which shows the image of the difference calculation process in the registration process which concerns on one Embodiment of this invention. It is a figure which shows an example of the determination of the brightness | luminance vector in the registration process which concerns on one Embodiment of this invention. It is a flowchart which shows an example of the authentication process in the authentication method which concerns on one Embodiment of this invention. It is a figure which shows an example of the functional block of the registration apparatus and authentication apparatus which concern on one Embodiment of this invention.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In each drawing referred to in the following description, parts equivalent to those in other drawings are denoted by the same reference numerals.

(Configuration of authentication system)
The authentication system according to this embodiment includes seal stamps, signatures, trademarks, logo marks, brand marks, identification marks printed on banknotes, marks attached to solid objects by transfer paper, magnetic cards and ICs. Identification marks on cards, such as paper, wood, cloth, resin, metal, etc., or the surface of solid objects, printed or drawn with inks such as pigments and dyes, paint, etc. Authenticate objects that are subject to authentication such as flat objects or solid objects such as solid objects that are fixed in some color, such as being applied with paint or molded with resin containing color materials It is an authentication system that can.

  FIG. 1 is a diagram illustrating an example of a configuration of an authentication system according to the present embodiment. An authentication system 1 shown in FIG. 1 includes a scanner 2, a computer 3, a printer 4, a display 5, and an input device 6 such as a keyboard and a mouse.

  The scanner 2 is a reading unit for reading an authentication target as color information for each mesh section. The computer 3 includes a control unit 3a composed of a CPU and a storage unit 3b composed of a storage device such as a hard disk, a ROM, and a RAM, and the storage unit 3b stores various programs for executing each process described later. Is saved. The CPU constituting the control unit 3a can read out various programs from the storage unit 3b as necessary to control the entire system.

  In addition, this structure is an example to the last, and is not limited to this. For example, the authentication system 1 shown in FIG. 1 is configured using a computer and a scanner. For example, instead of the scanner, a reading unit such as a digital camera, a control unit such as a CPU, and a storage unit such as a memory or a hard disk In addition, display means such as a liquid crystal display and input means such as a keyboard, a mouse, or a touch panel may be provided. The authentication system 1 can be realized by various computer devices typified by mobile terminals such as smartphones and PDAs, mobile phones, and the like.

  Next, an authentication method in the authentication system according to the present embodiment will be described.

(Authentication method)
In the authentication method according to the present embodiment, registration processing of an image of an authentication source such as a sign to be authenticated (an image such as a sign registered in advance; hereinafter referred to as “registered image”) is performed in advance. Based on this registered data, an authentication process such as a sign to be authenticated is performed. As will be described later, in this registration process and authentication process, a template matching process and an edge removal process are executed. In the present embodiment, a template image and an edge mask image are generated in advance for the template matching process and the edge removal process. First, this pre-processing will be described.

(Pre-processing)
FIG. 2 is a flowchart showing an example of pre-processing in the authentication method according to the present embodiment. First, a template image is generated (step S102). As will be described later, the template matching process is a process for correcting a deviation in the rotation direction when a sign or the like to be registered and a sign or the like to be authenticated are read by a reading unit such as the scanner 2 ( Details will be described later). A template image used for detecting the deviation in the rotation direction is generated in advance.

  FIG. 3 is a diagram illustrating an example of a template image generation method. The template image is generated from a master image including a sign or the like uniquely selected as an image serving as a reference for a position of the sign or the like. As shown in FIG. 3, a plurality of template images 31 are generated by rotating the master image 10 by a predetermined angle within a predetermined rotation angle range. In the example of FIG. 3, five template images 11 are generated by being rotated by 10 ° in the range of the rotation angle + 20 ° to −20 °. Each template image 11 generated in this manner is compared with a read image obtained by reading a sign or the like at the time of registration or authentication with the scanner 2 or the like, thereby correcting the deviation in the rotation direction (details of the template matching process are Will be described later).

Returning to FIG. 2, next, an edge mask image for executing the edge removal processing is generated (step S104). The edge mask image can be generated using a template image (image 12 in FIG. 3) having a rotation angle of 0 ° among the plurality of generated template images 11. FIG. 4 is a diagram for explaining an example of an edge mask image generation procedure. The edge mask image is generated by the following procedure using, for example, a graphic editing tool. That is,
1. The image 12 having a rotation angle of 0 ° is converted into a gray scale (FIG. 4 (a) → (b)).
2. Noise is removed by applying a Gaussian filter to the generated grayscale image. In an actual image, there are cases where minute black dots (noise) are scattered in the margin part to be removed, but this noise can be removed by this processing. In this example, the image is converted to gray scale. However, the noise may be removed by applying a Gaussian filter while maintaining the color image.
3. Next, the image is binarized. The binarized image is saved in an appropriate file format such as BMP format, PNG format, or JPEG format (FIG. 4C). The threshold for binarization can be set as appropriate.
4). The binarized image is traced, and the mask width of the edge, the edge corner and the edge drawing are set and output (FIG. 4D). Various settings for edge width and edge corner and edge drawing at this time can be appropriately set. The output image becomes an edge mask image used for edge removal. The edge mask image is regarded as a pixel that masks a color portion other than black. In edge removal processing at the time of registration and authentication described later, the edge of the registered image or the authentication image can be removed by image processing using the edge mask image that can be generated in this way.

(registration process)
Next, registration processing of a registered image will be described.

  FIG. 5 is a flowchart showing an example of registration processing in the authentication method according to the present embodiment.

  First, an authentication target such as a sign to be registered is set in the scanner 2, and a printing surface or the like to which the mark or the like to be authenticated is attached once by the scanner 2 in order to acquire color information for each pixel. Read (or multiple times) (step S202). Here, in the present embodiment, color information for each mesh section may be acquired as in the authentication method disclosed in Japanese Patent No. 4951564. And in each process demonstrated below, it may replace with every pixel and may perform each process for every mesh division. For example, the computer 3 acquires the color information with an optical resolution corresponding to the size of the mesh section by using the photoreactive elements partitioned by the mesh of the XY array, and stores the acquired color information in the storage unit 3b. It may be. The color material particles of the printing ink to be authenticated may be assumed to be smaller than the size of the mesh section (for example, when the reading unit such as the scanner 2 acquires color information with a resolution of 600 dpi, The mesh section has a side of 42.3 μm and is larger than the colorant particles). In this case, the color composition of some colorant particles in the mesh section is pixel-colored as a single monochrome RGB value.

  Next, template matching is performed (step S204). In the present embodiment, the scanner 2 reads the area including the sign of the authentication target to be registered in step S202, and the scanner 2 reads the area including the sign to be authenticated during the authentication process. Positioning the authentication target exactly the same at the time of registration and at the time of authentication, and it cannot be expected to be erect correctly (not rotating), and the position of the scanned image may be misaligned between the time of registration and the time of authentication. Usually, it is rotating. Therefore, in the present embodiment, in order to erect an image obtained by reading the area including the authentication target with the scanner 2 and to cut out the image including the authentication target (in this specification, this is referred to as “normalization”), Template matching is performed during registration and authentication.

(Template matching)
Hereinafter, template matching will be described in detail. In advance, as described in FIG. 3, the master image 10 is rotated at predetermined angles to generate a plurality of template images 11. Then, these template images 11 are compared with a read image when a marker or the like to be registered is read by the scanner 2 by a template matching technique. At this time, the template image 11 and the read image may be reduced and collated at the same rate. As a result, the size of the processing data can be reduced, the processing load can be reduced, and the processing speed can be improved.

  Then, the rotation angle of the template image 11 having the highest collation value (value indicating the degree of matching) is the rotation angle of the read image. For example, when the template image with the rotation angle of −10 ° has the highest collation value, as shown in FIG. 6, the read image 20 is rotated by + 10 ° in order to restore the deviation of −10 °. The erect read image 21 is generated. Further, a normalized image 22 is obtained by cutting out an image to be registered from the erected read image 21.

  In the template matching described in this example, the template image 11 is generated by rotating the master image 10 by 10 degrees within the range of the rotation angle + 20 ° to −20 °. However, the present invention is not limited to this. Depending on the pixel size (width and height) of the read image, the number of matching radii, the processing capability of the computer executing the authentication method according to the present embodiment, and the like, the angle of the master image 10 is determined several times. It is possible to determine whether to generate a template image by rotating within the rotation range.

  Furthermore, in order to further shorten the template matching processing time, template matching may be performed step by step in a plurality of steps.

  For example, in the first step, a template image is generated by rotating the master image for each larger angle in a wider rotation angle range. Then, template matching is performed by reducing the read image and the template image, and the angle with the highest matching degree and its matching position are determined.

  In the second step, a range obtained by adding a margin for absorbing an error at the time of enlargement / reduction to a matching position such as a label in the read image obtained in the first step is cut out from the read image as a search range in this step. , The image is reduced at a predetermined reduction rate. Further, a plurality of template images and templates obtained by rotating the master image for each smaller angle in a smaller rotation angle range around the angle obtained in the first step and reducing the same at the same reduction rate as the search range. Matching is performed to determine the angle with the highest matching level and the matching position.

  Further, in the third step, a read image obtained by adding a margin for absorbing an error at the time of enlargement / reduction to a matching position such as a label in the read image obtained in the second step is used as a search range in this step. And cut at a predetermined reduction rate. Further, a plurality of template images and templates that are reduced at the same reduction rate as the search range by rotating the master image in smaller rotation angle ranges at smaller angles around the angle obtained in the second step. Matching is performed to determine the angle with the highest matching level and the matching position. Thereafter, this is repeated as many times as necessary.

  By repeating template matching step by step as described above, the matching area (number of pixels) is reduced for each step, and template matching for the next step is performed, so the template matching processing time can be reduced. It becomes.

  As described above, a registered image normalized by template matching can be acquired. Similarly, at the time of authentication, template matching is performed on a read image including a sign or the like to be authenticated to obtain a normalized image, thereby correcting the position and rotation misalignment between the registered image and the authentication image. Accuracy can be improved.

  Returning to FIG. 5, the edge (contour) of the normalized registered image acquired in step S204 is removed by image processing (step S206). When performing the edge removal, the edge mask image generated as described with reference to FIG. 4 is used. The width for removing the edge may be set, for example, by a user input.

  Next, feature points of the registered image are extracted by calculating the difference (step S208). Feature point extraction of a registered image by difference calculation is to obtain a difference in RGB color information between each pixel constituting the registered image and its surrounding pixels, and to determine a pixel having a large difference value as a feature of this registered image (authentication target). This is a method of extracting as feature points indicating. Hereinafter, a feature point extraction method based on difference calculation will be described in detail.

(Feature point extraction by difference calculation)
FIG. 7 is a diagram illustrating a specific example of feature point extraction by difference calculation.

  The pixel that is the target of the difference calculation is a pixel P (hereinafter referred to as “target pixel”) 300, and its surrounding eight pixels are A301 (left), pixel B302 (upper), pixel C303 (right), and pixel D304 (lower), respectively. ), Pixel E305 (upper left), pixel F306 (upper right), pixel G307 (lower right), and pixel H308 (lower left), the difference in RGB color information between the pixel P and each of the pixels A to H is obtained. Here, if the upper left corner of the image is the origin (0, 0), the right direction is x, and the lower direction is y, the coordinates (x, y) of the pixel of interest P300 are the coordinates of the surrounding pixels A301 to H308. Are (x-1, y), (x, y-1), (x + 1, y), (x, y + 1), (x-1, y-1), (x + 1, y-1), (x + 1, y + 1), and (x-1, y + 1).

Further, the RGB value of the pixel of interest P300 is represented as R _P , G _P , and B _P , the RGB value of the pixel A301 is represented as R _A , G _A , B _A , and the RGB value of the pixel B 302 is represented as R _B , G _B , When the RGB values of B _B ,..., The pixel H308 are expressed as R _H , G _H , and B _H , the difference between the RGB values of the pixel of interest P and the surrounding pixels A to H is expressed by the following equation: The
Difference = | A−P | + | B−P | + | C−P | + | D−P | + | E−P | + | G−P | + | H−P |
_{= (| R A -R P |} + | G A -G P | + | B A -B P |) +
_{(| R B -R P | +} | G B -G P | + | B B -B P |) +
_{(| R C -R P | +} | G C -G P | + | B C -B P |) +
_{(| R D -R P | +} | G D -G P | + | B D -B P |) +
_{(| R E -R P | +} | G E -G P | + | B E -B P |) +
(| R _F −R _P | + | G _F −G _P | + | B _F −B _P |) +
_{(| R G -R P | +} | G G -G P | + | B G -B P |) +
_{(| R H -R P | +} | G H -G P | + | B H -B P |)

  In this example, the difference value of the RGB color information between the pixel of interest and its surrounding 8 pixels is calculated. However, some peripheral pixels are selected depending on the directionality of printing such as a sign to be authenticated. The difference may be calculated. For example, the difference between the target pixel P and the left pixel A and the upper pixel B may be calculated.

  Moreover, the calculation method of the RGB difference value by the above formula is an example, and the present invention is not limited to this. For example, the average value may be calculated by dividing the total value calculated by the above formula by the number of surrounding pixels (8 in the above example), and this may be used as the RGB difference value for each pixel of interest. That is, the RGB difference value is information that can compare a plurality of pixels in the registered image and determine which pixel has a larger (smaller) difference in RGB color information from the surrounding pixels. Good.

  As described above, when the sum of the RGB difference values between the pixel P and its surrounding pixels is calculated, the same processing is performed with the next pixel on the right as the target pixel. When the processing is completed, the same processing is performed with the pixel on the right as the target pixel, and so on, and so on. The origin (x, y) = upper left of the registered image acquired in step S206 in FIG. Perform the above processing for each pixel from (0, 0) to the lower right (x, y) = (width-1, height-1) (width: image width, height: image height) (The range of x and y of the coordinates (x, y) of the pixel to be a pixel is x = 1 to width-2, y = 1 to height-2). FIG. 8 is a diagram showing an image of processing. Each time the RGB difference value is calculated for each pixel in the registered image by the process as described above, the (x, y) coordinates of the pixel P and the calculated RGB difference value are associated and stored in a format such as array data. Stored in section 3b.

  Returning to FIG. 5, after calculating the difference for all the pixels of the registered image in step S208, the top 30 to 5000 pixels of the calculated difference value are determined as final feature points of the registered image (step S210). . Then, the data (hereinafter referred to as “human decoding”) in which the feature points (the coordinates thereof) are sorted in descending order of the RGB difference values is stored. In other words, the human decoding is also data indicating a connecting line that connects the feature points in descending order of RGB difference values. Further, the human decoding may be, for example, a set of data of position vectors (positions and distances) of connecting lines. Note that the processing in step S210 is not essential, and not only the top 100 to 1000 pixels of the difference value but also all the target pixels may be stored together with the difference value to be stored as feature points. .

  Further, the number of feature points extracted in step S210 may be determined by the design of the registered image and the number of pixels. In addition, a predetermined number of feature points are not extracted, but pixels whose difference values of pixels belong to a predetermined range may be extracted as feature points. Further, a pixel whose luminance falls within a predetermined range may be determined as a feature point. Further, for example, when a plurality of determined feature points are located at a predetermined distance or less (concentrated) in the registered image, some feature points are excluded based on a rule. Also good.

  By the way, in this embodiment, the edge of the registered image is removed in step S206 described above. This is because when the feature points are determined by the difference calculation, the difference in the edge portion of the image is remarkably large, and the edge portion is ranked higher than the subtle gradation difference of the authentication target to be originally extracted. As a result, there is a high possibility that an erroneous determination will occur at the time of authentication of the authentication target (described later). Therefore, erroneous determination can be reduced by removing the edge portion of the registered image (and the authentication image).

  Further, the continuation of the flow of FIG. 5 will be described. In step S212, the luminance vector at each feature point is determined. This process is executed to further improve the authentication accuracy. In the authentication method according to the present embodiment, the coordinates of the human decoding decoded in advance by the registration process (the processing result of step S210) are collated with the coordinates of the human decoding generated by reading the authentication target in the authentication processing described later. For example, the number of features whose coordinates coincide with each other or within a predetermined range is counted. When the count value satisfies a predetermined condition (for example, a predetermined ratio or more), the two are authenticated as the same. However, since the registered feature point and the feature point when reading a sign etc. at the time of authentication existed near by chance, it may be determined that the coordinates of both coincide, etc. Such feature points are called “spoofing points”). In order to eliminate this spoofing point, in the present embodiment, the luminance vector is further considered for each of the pixels for which the difference of the RGB color information from the surrounding pixels is calculated in the authentication process, as in step S208. By determining the final feature points, the authentication is made more precise. In step S212, in order to perform such processing at the time of authentication, processing for determining and storing a luminance vector for each feature point determined in advance in step S210 for the registered image is executed. Here, the luminance vector at each feature point is data indicating a comparison result between the luminance of the feature point and the luminance of the surrounding pixels.

(Determination of luminance vector)
Hereinafter, a method for determining the luminance vector will be described in detail.

  As described above, the brightness vector is data indicating a comparison result between the brightness of each feature point determined in step S210 and the brightness of the surrounding pixels. The peripheral pixels for calculating the luminance may be pixels in the eight directions around each feature point or pixels in the four directions (for example, up, down, left, and right) as in the calculation of the RGB difference values in step S208. . Further, it may be a pixel in two peripheral directions such as left and top.

  FIG. 9 is a diagram showing an image of determination of the luminance vector. In addition, in FIG. 9, the image in the case of calculating the brightness | luminance about the feature point P and the surrounding pixels AH of the surrounding 8 directions is shown as an example.

  First, the brightness value of the feature point P and the brightness values of the surrounding pixels A to H are calculated. The luminance value is calculated from the RGB value of each pixel by the following formula.

Luminance value = 0.299 x R + 0.587 x G + 0.114 x B
Then, the calculated luminance value of the feature point P is compared with the luminance values of the peripheral pixels A to H, and each comparison result is expressed as a numeric string. For example, when the luminance value of the left pixel A−the luminance value of the pixel P = a positive value (when the pixel A is brighter than the feature point P), this comparison result is indicated as “0”. When the luminance value of the left pixel A−the luminance value of the pixel P = 0 (when both luminance values are the same), this comparison result is indicated as “1”. Further, when the luminance value of the left pixel A−the luminance value of the pixel P = negative value (when the feature point P is brighter), this comparison result is indicated as “2”. Similarly, the other peripheral pixels B to H are encrypted by comparing the feature point P with the luminance value. For example, if the comparison result as shown in FIG. 9 is obtained for the feature point P, the luminance vector is determined to be “01200021”. This result is stored in association with the coordinates of the human decoding (each feature point) stored in step S210 (step S214), and the registration process ends.

  In this example, the luminance vector is represented by a number string using three numbers, but is merely an example, and the present invention is not limited to this. For example, the luminance vector may be expressed by other symbols, alphanumeric characters, and the like. In the above example, the difference in luminance value between the feature point P and the surrounding pixels is classified into three (bright / dark / identical), but may be classified more finely (or roughly). For example, the difference between the two luminance values may be classified into a plurality of predetermined ranges, and different alphanumeric characters may be assigned to the difference between the luminance values depending on which range they belong to.

  Further, the order of the processes in step S210 and step S212 may be reversed. That is, for all the target pixels whose coordinates are stored in the storage unit 3b in step S208, the brightness vector is determined and stored in the storage unit 3b, and then the final feature point of the registered image is determined in step S210. May be.

  Further, in the authentication method according to the present embodiment, feature points are extracted in units of pixels. However, a feature point is defined with an area having a predetermined size composed of a plurality of pixels (for example, 3 × 3 pixels) as one unit. Extraction may be performed.

  Note that the authentication method according to the present embodiment is an authentication method mainly including feature point extraction by difference calculation (mainly step S208) and luminance vector determination (mainly step S212). For specific methods other than these, the methods described in Japanese Patent No. 4951564 and Japanese Patent No. 5280386 can be applied. (The same applies to the authentication processing described later.)

(Authentication process)
Next, an authentication process for authenticating whether an authentication target, which is a sign or the like to which a material constituting some color is fixed, is valid will be described. FIG. 10 is a flowchart showing an example of authentication processing in the authentication method according to the present embodiment.

  The authentication process is similar to the registration process described with reference to FIG. That is, the area including the authentication target is read once (or a plurality of times) by the scanner 2 on the printing surface to which the mark or the like as the authentication target is attached (step S302).

  Next, template matching is performed to obtain a normalized image (authentication image) (step S304). Template matching is performed in the same manner as in the registration process. Next, the edge of the normalized image acquired in step S304 is removed by image processing (step S306). The method for removing the edge is performed in the same manner as in the registration process.

  Next, similarly to step S208 at the time of registration processing, the difference between the RGB color information is calculated for the acquired authentication image (step S308), and the top 30 to 5000 pixels of the calculated difference value are converted to the authentication image. And the human decoding is obtained (step S310). Then, similarly to step S212 during the registration process, the luminance vector at each feature point is determined (step S312).

  The human decode decoded in advance in the storage unit 3b of the authentication system 1 and the luminance vector of each feature point constituting the human decode are read from the storage unit 3b and acquired in step S310. And matching is performed by a technique such as vector matching (step S314). At this time, it is determined whether or not the luminance vector at each feature point such as the sign to be authenticated calculated in step S312 is the same as the luminance vector at each feature point of the human decoding read from the storage unit 3b of the authentication system 1. To do. If the two brightness vectors are not the same, it is determined that the feature point is a spoofing point, and the spoofing point is excluded from the human decoding acquired in step S310 (step S316).

  In the state where the impersonation point is excluded, matching between both human decoding is performed (step S318). As a matching method, for example, the feature points having the same coordinates or a distance within a predetermined range are counted, and if the count value is equal to or greater than a predetermined ratio, they are authenticated as the same.

(Function block)
FIG. 11 is a diagram illustrating an example of functional blocks of the registration device and the authentication device in the authentication system according to the present embodiment. In the following description, the registration device and the authentication device are shown as separate blocks. However, as in the configuration example shown in FIG. 1, both devices have a registration device and an authentication device. It may also serve as a separate device.

(1) Registration Device The registration device 100 is a device that executes processing for registering human decoding in advance (processing in the flowchart of FIG. 5) for authentication of an authentication target. The registration apparatus 100 includes a first read image acquisition unit 101, a first template matching execution unit 102, a first edge removal unit 103, a first feature point determination unit 104, a first luminance vector determination unit 105, and a storage Unit 106.

  The first read image acquisition unit 101 acquires a read image that is an image including a sign or the like to be authenticated. The first read image acquisition unit 101 mainly executes the process of step S202 of FIG.

  The first template matching execution unit 102 performs template matching on the master image and the read image acquired by the first read image acquisition unit 101, and normalizes the cut image by erecting the read image. (Registered image) is acquired. The first template matching execution unit 102 mainly executes the process of step S204 in FIG.

  The first edge removing unit 103 removes an edge such as a sign (authentication object) included in the registered image acquired by the first template matching execution unit 102. The first edge removal unit 103 mainly executes the process of step S206 in FIG.

  The first feature point determination unit 104 obtains color information for each predetermined area, which is an area of a predetermined size composed of one or a plurality of pixels in the registered image, and a plurality of predetermined points included in the registered image. For each region, a difference in color information from one or more predetermined regions located around each predetermined region is determined, and based on the determination result, an authentication target is selected from the plurality of predetermined regions included in the registered image. A region to be a plurality of feature points indicating the features is determined. The first feature point determination unit 104 mainly executes the process of step S208 (and step S210) in FIG.

  The first brightness vector determination unit 105 acquires brightness information for each predetermined area in the registered image, and for each feature point determined by the first feature point determination unit 104, the brightness information of each feature point and each feature A luminance vector that is information indicating a result of comparison with luminance information of one or more predetermined regions located around the point is determined. The first luminance vector determination unit 105 mainly executes the process of step S212 in FIG.

  The storage unit 106 stores, for each of a plurality of feature points of the registered image, each feature point, a difference in color information of each feature point, and a luminance vector of each feature point in association with each other.

(2) Authentication Device The authentication device 200 is a device that executes processing for authenticating whether the authentication target is valid (the processing in the flowchart in FIG. 10). The authentication apparatus 200 includes a second read image acquisition unit 201, a second template matching execution unit 202, a second edge removal unit 203, a second feature point determination unit 204, a second luminance vector determination unit 205, a matching Unit 206.

  The second read image acquisition unit 201 acquires a read image that is an image including a sign or the like to be authenticated. The second read image acquisition unit 201 mainly executes the process of step S302 in FIG.

  The second template matching execution unit 202 performs template matching on the master image and the read image acquired by the second read image acquisition unit 201, and normalizes the cut image by erecting the read image. Acquire (authentication image). The second template matching execution unit 202 mainly executes the process of step S304 in FIG.

  The second edge removing unit 203 removes an edge of a sign or the like (authentication target) included in the authentication image acquired by the second template matching execution unit 202. The second edge removal unit 203 mainly executes the process of step S306 in FIG.

  The second feature point determination unit 204 obtains color information for each predetermined area, which is an area having a predetermined size composed of one or a plurality of pixels, in the authentication image, and a plurality of predetermined points included in the authentication image. For each region, a difference in color information from one or more predetermined regions located around each predetermined region is determined, and based on the determination result, an authentication target is selected from a plurality of predetermined regions included in the authentication image. A region to be a plurality of feature points indicating the features is determined. The second feature point determination unit 204 mainly executes the process of step S308 (and step S310) in FIG.

  The second brightness vector determination unit 205 acquires brightness information for each predetermined area in the authentication image, and for each feature point determined by the second feature determination unit 204, the brightness information of each feature point and each feature point A luminance vector that is information indicating a result of comparison with luminance information of one or more predetermined areas located around the area is determined. The second luminance vector determination unit 205 mainly executes the process of step S312 in FIG.

  The matching unit 206 refers to the storage unit 106 in which a plurality of feature points of the registered image, the difference in color information of each feature point, and the luminance vector of each feature point are stored in advance. 106, based on the difference between the color information of each feature point stored in 106 and the difference between the color information of the plurality of feature points of the authentication image determined by the second feature point determination unit 204. The plurality of feature points are matched with the plurality of feature points of the authentication image. Further, the matching unit 206 determines the feature point of the authentication image when the brightness vector of the feature point stored in the storage unit 106 and the brightness vector of the feature point of the authentication image do not satisfy a predetermined condition. The matching is performed by excluding the determined feature points. The matching unit 206 mainly executes the processes of step S314, step S316, and step S318 in FIG.

  Note that each function of the registration device 100 and the authentication device 200 is realized by hardware, software, or a combination of hardware and software. For example, in the hardware configuration shown in FIG. 1, each function can be realized by the controller 3 a reading and executing various programs corresponding to each function from the storage unit 3 b.

  Up to this point, one embodiment of the present invention has been described. However, the present invention is not limited to the above-described embodiment, and it is needless to say that the present invention may be implemented in various forms within the scope of the technical idea.

  The scope of the present invention is not limited to the illustrated and described exemplary embodiments, but includes all embodiments that provide the same effects as those intended by the present invention. Further, the scope of the invention is not limited to the combinations of features of the invention defined by the claims, but may be defined by any desired combination of particular features among all the disclosed features. .

DESCRIPTION OF SYMBOLS 1 Authentication system 2 Scanner 3 Computer 3a Control part 3b Storage part 4 Printer 5 Display 6 Input device 10 Master image 11 Template image 20 Read image 22 Normalized image 100 Registration apparatus 101 First read image acquisition part 102 First template matching execution part 103 first edge removal unit 104 first feature point determination unit 105 first luminance vector determination unit 106 storage unit 200 authentication device 201 second read image acquisition unit 202 second template matching execution unit 203 second edge removal unit 204 second feature Point determination unit 205 Second luminance vector determination unit 206 Matching unit 202 Second template matching execution unit 300 Pixels of interest 301 to 308 Neighboring pixels

Claims (12)

A read image acquisition unit that acquires a read image that is an image including an authentication target;
A template matching execution unit that acquires an authentication image in which the read image is erected by detecting a shift in the rotation direction of the read image from the position of the master image by template matching with reference to the master image;
In the authentication image, color information is acquired for each predetermined area that is an area of a predetermined size composed of one or a plurality of pixels, and each predetermined area is included in each of the predetermined areas included in the authentication image. A difference of the color information with one or a plurality of predetermined areas located in the periphery of the image, and based on the determination result, the feature of the authentication target is selected from the plurality of the predetermined areas included in the authentication image. A feature point determination unit for determining a region to be a plurality of feature points to be shown;
A plurality of feature points of an image registered in advance and a color information difference of each feature point are referred to and stored in association with each feature point stored in the storage unit. Based on the difference in color information and the difference in color information of the plurality of feature points of the authentication image determined by the feature point determination unit, the plurality of feature points stored in the storage unit, A matching unit that performs matching with the plurality of feature points of the authentication image;
An authentication device comprising:   The template matching execution unit generates a plurality of template images by rotating the master image by a predetermined rotation angle unit within a predetermined rotation angle range, and the plurality of template images and the read image are generated. To determine the angle range in which the read image is rotated, and by rotating the master image in a predetermined rotation angle unit in the determined angle range, The template image is generated, and the angle range in which the read image is rotated is determined by comparing the generated plurality of template images with the read image. The rotation direction deviation from the position of the master image is detected. Authentication device according to. In the authentication image, luminance information for each predetermined region is acquired, and for each feature point, the luminance information of each feature point is compared with the luminance information of one or more predetermined regions located around each feature point. A luminance vector determining unit that determines a luminance vector that is information indicating a result;
In addition to the plurality of feature points of the registered image and the difference of the color information of each feature point, the storage unit stores a brightness vector of each feature point in association with each other.
The matching unit determines the feature point of the authentication image when the brightness vector of the feature point stored in the storage unit and the brightness vector of the feature point of the authentication image do not satisfy a predetermined condition. The authentication apparatus according to claim 1, wherein matching is performed by excluding the plurality of determined feature points.   The authentication device according to claim 1, wherein the storage unit sorts and stores the feature points based on a difference in the color information of the feature points.   The feature point determination unit, for each of the plurality of regions included in the image, according to the direction of printing of the authentication target, only a part of the plurality of regions located around the region The authentication apparatus according to claim 1, wherein a difference between the color information is determined.   The authentication apparatus according to claim 1, further comprising an edge removal unit that removes the authentication target edge included in the authentication image acquired by the template matching execution unit. A read image acquisition unit that acquires a read image that is an image including an authentication target for registration;
A template matching execution unit that acquires a registered image in which the read image is erected by detecting a shift in the rotation direction of the read image from the position of the master image by template matching with reference to the master image;
In the registered image, color information is acquired for each predetermined area that is a predetermined size area composed of one or a plurality of pixels, and each predetermined area is included in each of the predetermined areas included in the registered image. A difference of the color information with one or a plurality of predetermined areas located in the vicinity of the image, and based on the determination result, the feature of the authentication target is selected from the plurality of the predetermined areas included in the registered image. A feature point determination unit for determining a region to be a plurality of feature points to be shown;
For each of the plurality of feature points of the registered image, a storage unit that associates and stores each feature point and the difference of the color information of each feature point;
A registration device for authentication comprising:   The registration device according to claim 7, further comprising an edge removal unit that removes the authentication target edge included in the registration image acquired by the template matching execution unit. An authentication method executed by a computer device,
Obtaining a read image that is an image including an authentication target;
Obtaining an authentication image in which the read image is erected by detecting a shift in the rotation direction of the read image from the position of the master image by template matching with reference to the master image;
In the authentication image, color information is acquired for each predetermined area that is an area of a predetermined size composed of one or a plurality of pixels, and each predetermined area is included in each of the predetermined areas included in the authentication image. A difference of the color information with one or a plurality of predetermined areas located in the periphery of the image, and based on the determination result, the feature of the authentication target is selected from the plurality of the predetermined areas included in the authentication image. Determining a region to be a plurality of feature points to be shown;
A plurality of feature points of an image registered in advance and a color information difference of each feature point are referred to and stored in association with each feature point stored in the storage unit. The plurality of feature points stored in the storage unit and the plurality of authentication images based on the difference in color information and the difference in color information of the plurality of feature points of the determined authentication image Matching with feature points of
An authentication method that includes: A registration method executed by a computer device,
Obtaining a read image that is an image including an authentication target for registration;
Obtaining a registered image in which the read image is erected by detecting a shift in the rotation direction of the read image from the position of the master image by template matching on the basis of the master image;
In the registered image, color information is acquired for each predetermined area that is a predetermined size area composed of one or a plurality of pixels, and each predetermined area is included in each of the predetermined areas included in the registered image. A difference of the color information with one or a plurality of predetermined areas located in the vicinity of the image, and based on the determination result, the feature of the authentication target is selected from the plurality of the predetermined areas included in the registered image. Determining a region to be a plurality of feature points to be shown;
Storing each feature point and the difference of the color information of each feature point in association with each other for the plurality of feature points of the registered image;
Registration method including.   A computer program for causing a computer to execute the method according to claim 9 or 10.   A computer-readable recording medium storing a computer program for causing a computer to execute the method according to claim 9 or 10.

Images