JP2019040449A - Disk discrimination device and disk discrimination method - Google Patents

Abstract

To provide a disk discrimination device and a disk discrimination method capable of automatically setting a moire region or the like of a disk and preventing deterioration of the discrimination accuracy of the disk due to the moire.SOLUTION: The disk discrimination device includes: a reference image generating part for integrating a plurality of input images corresponding to each of a plurality of disks to be discriminated as an authentic disk and generating a reference image; a moire image selecting part for selecting a plurality of moire images having moire regions from the plurality of input images on the basis of a comparison result between each of the plurality of input images and the reference image; a mask image generating part for generating a mask image in which the moire region is excluded from an effective pixel on the basis of a comparison result between the integrated moire images obtained by integrating the plurality of moire images and the reference image; and a discrimination part for discriminating the authenticity of a disk to be discriminated by comparing an input discriminated image and the reference image by applying the mask image.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a disc discriminating apparatus and disc discriminating method, and more particularly, to a disc discriminating apparatus and disc discriminating method for discriminating the authenticity of a disc to be discriminated by imaging a pattern on the disc surface. Note that the disc in this specification is a concept that includes medals and tokens used in gaming machines, and coins as currency.

  A technology for imaging the front or back surface of a medal or coin (generally referred to as “front surface” in this specification) and determining the authenticity based on the pattern of the surface using a captured image has been proposed in the past. For example, there are those disclosed in Patent Document 1 and Patent Document 2.

  In general, a disk such as a medal or a coin has a pattern formed on the surface thereof, and when an image is acquired by capturing the pattern with an imaging device, the pixel arrangement of the imaging device interferes with the pattern to cause moire. May occur. When a disk is imaged, the state of moiré changes according to the rotation angle of the disk. In other words, the pattern in the image acquired according to the rotation angle of the disk changes under the influence of moire. Therefore, when the difference or coincidence is derived by comparing the captured image of the disc to be discriminated with an image serving as a reference for comparison (hereinafter referred to as a reference image), the dissimilarity or coincidence changes due to the influence of moire, There is a problem that a desired discrimination result cannot be obtained.

  In the first prior art disclosed in Patent Document 1, in consideration of the fact that moire appears and the reflectance changes significantly depending on the angle between the pixel arrangement of the image sensor and the pattern, the reference is excluded except for a specific portion depending on the rotation angle. Checking with images.

  On the other hand, in the second prior art disclosed in Patent Document 2, the recognition accuracy is improved by applying a mask to a part where the character is changed due to the issuance year of the coin and the pattern itself partially changes like the year part. Decreasing factors are decreasing.

JP 2004-157975 A (Claim 1, Claim 8, Paragraph Nos. 0018, 0019, FIG. 15) JP-A-9-27056 (paragraph numbers 0013 and 0019, FIG. 3)

  In the first prior art, there is no specific disclosure about a method for setting a specific area to be excluded. Similarly, in the second prior art, there is no specific disclosure about a method for setting a portion to be masked. Generally, there are a wide variety of disc patterns such as medals and coins, and it is necessary to set an area where moire occurs (hereinafter referred to as a moire area) according to the type of the disk. Although it is possible to manually set the moire area while visually confirming the state of occurrence of moire, in that case, there is a problem that much time and labor are required. Moreover, when set visually, there exists a possibility that variation may arise in setting accuracy. When the setting accuracy of the moire area varies, there is a problem that the accuracy of discriminating the authenticity of discs such as medals and coins is significantly reduced.

  The present invention has been made in view of the above-described problems, and an object of the present invention is to automatically set the moiré area of the disc, and to reduce the disc discrimination accuracy caused by the moiré. An object of the present invention is to provide a disc discrimination device and a disc discrimination method that can be prevented. Other objects of the present invention which are not specified here will be apparent from the following description and the accompanying drawings.

  In order to achieve this object, the disc discriminating apparatus and disc discriminating method according to the present invention are configured as follows.

  (1) The disc discriminating apparatus according to the present invention discriminates the authenticity of the disc to be discriminated by comparing the discriminated image corresponding to the disc to be discriminated with the reference image by excluding the moire area from the effective pixels. A reference image generation unit that generates a reference image by accumulating a plurality of input images corresponding to each of a plurality of discs to be determined as authentic discs, each of the plurality of input images, and the reference image A moire image selection unit that selects, from the plurality of input images, a plurality of moire images having the moire region based on the comparison result, an integrated moire image obtained by integrating the plurality of moire images, and the reference image A mask image generating unit that generates a mask image for excluding the moire region from effective pixels based on the comparison result, the input image to be discriminated, and the base A disc discrimination apparatus and a discrimination unit for discriminating the authenticity of the determination target disk by comparing the image by applying the mask image.

  The disc discriminating apparatus of the present invention includes a reference image generation unit that generates a reference image, a moire image selection unit that selects a moire image from an input image, and a mask image that generates a mask image that excludes a moire region from effective pixels. A generating unit; and a determining unit configured to determine the authenticity of the determination target disk. The reference image generating unit generates a reference image by integrating a plurality of input images corresponding to each of a plurality of discs to be determined as authentic discs. The moire image selection unit selects a plurality of moire images having a moire area from the plurality of input images based on a comparison result between each of the plurality of input images and the reference image. The mask image generation unit generates a mask image that excludes the moire area from the effective pixels based on a comparison result between the accumulated moire image obtained by integrating a plurality of moire images and the reference image. The discriminating unit discriminates the authenticity of the disc to be discriminated by comparing the discriminated image corresponding to the disc to be discriminated with the reference image by applying a mask image. In the first disc discrimination device, a mask image is generated based on a comparison result between an accumulated moire image obtained by integrating a plurality of moire images selected from a plurality of input images and a reference image. Therefore, it is possible to automatically set the moire area of the disc. Further, by applying a mask image to each of the discriminated image and the reference image corresponding to the disc to be discriminated and excluding the moire area from the effective pixels, it is possible to prevent the disc discrimination accuracy from being lowered due to moire. It becomes possible.

  (2) In a preferred example of the disc discriminating apparatus of the present invention, an evaluation value deriving unit for deriving an evaluation value of matching with respect to the reference image for each of the plurality of input images, and a plurality of values derived by the evaluation value deriving unit A determination threshold value setting unit that sets a determination threshold value of the moire image from the frequency distribution of the evaluation values, and the moire image selection unit uses the determination threshold value as a reference for each of the evaluation values of the plurality of input images. The moire image is selected by determining. In this case, there is an advantage that a plurality of moire images having a moire area can be automatically selected from a plurality of input images.

  (3) In another preferred example of the disk discriminating apparatus of the present invention, the determination threshold setting unit sets the determination threshold based on the frequency distribution having a higher evaluation value than the average value of the frequency distribution. . In this case, there is an advantage that a determination threshold value can be set according to the state of occurrence of moire.

  (4) In still another preferred example of the disc discriminating apparatus according to the present invention, the mask image generation unit sets a threshold value at which the degree of separation in the frequency distribution of difference pixel values between the integrated moire image and the reference image is maximized. As an example, an image obtained by binarizing a difference image between the integrated moire image and the reference image is used as the mask image.

  (5) The disc discrimination method of the present invention discriminates the authenticity of the disc to be discriminated by comparing the discriminated image corresponding to the disc to be discriminated with the reference image by excluding the moire area from the effective pixels. A reference image generation step of generating a reference image by integrating a plurality of input images corresponding to each of a plurality of discs to be identified as authentic discs, each of the plurality of input images, and the reference image A moire image selection process for selecting a plurality of moire images having the moire area from the plurality of input images based on a comparison result with the integrated moire image obtained by integrating the plurality of moire images and the reference image. A mask image generation step of generating a mask image for excluding the moire region from effective pixels based on the comparison result; and the input image to be discriminated A determination step of determining the authenticity of the determination target disk by a serial reference image contrast by applying the mask image, a disk discriminating method comprising.

  In the disc discrimination method of the present invention, a reference image generation process for generating a reference image, a moire image selection process for selecting a moire image from an input image, and a mask image for generating a mask image for excluding a moire area from effective pixels A generation process and a determination process for determining the authenticity of the determination target disk. In the reference image generation process, a reference image is generated by integrating a plurality of input images corresponding to each of a plurality of discs to be determined as authentic discs. In the moire image selection process, a plurality of moire images having a moire area are selected from the plurality of input images based on a comparison result between each of the plurality of input images and the reference image. In the mask image generation process, a mask image that excludes the moire area from the effective pixels is generated based on the comparison result between the accumulated moire image obtained by integrating a plurality of moire images and the reference image. In the discrimination process, the authenticity of the disc to be discriminated is discriminated by comparing the discriminated image corresponding to the disc to be discriminated with the reference image by applying a mask image. In the first disc discrimination method, a mask image is generated based on a comparison result between an accumulated moire image obtained by integrating a plurality of moire images selected from a plurality of input images and a reference image. Therefore, it is possible to automatically set the moire area of the disc. Further, by applying a mask image to each of the discriminated image and the reference image corresponding to the disc to be discriminated and excluding the moire area from the effective pixels, it is possible to prevent the disc discrimination accuracy from being lowered due to moire. It becomes possible.

  (6) In a preferred example of the disc discrimination method of the present invention, an evaluation value deriving step for deriving an evaluation value for matching with the reference image for each of the plurality of input images, and a plurality of values derived in the evaluation value deriving step A determination threshold value setting step for setting a determination threshold value of the moire image from the frequency distribution of the evaluation values, and in the moire image selection step, the evaluation value of each of the plurality of input images is set based on the determination threshold value. The moire image is selected by determining. In this case, there is an advantage that a plurality of moire images having a moire area can be automatically selected from a plurality of input images.

  (7) In another preferred example of the disc discrimination method of the present invention, in the determination threshold setting step, the determination threshold is set based on the frequency distribution having a higher evaluation value than the average value of the frequency distribution. . In this case, there is an advantage that a determination threshold value can be set according to the state of occurrence of moire.

  (8) In still another preferred example of the disc discrimination method of the present invention, in the mask image generation step, a value at which the degree of separation in the frequency distribution of the difference pixel value between the integrated moire image and the reference image is a threshold value. As an example, an image obtained by binarizing a difference image between the integrated moire image and the reference image is used as the mask image.

  In the disc discriminating apparatus and disc discriminating method of the present invention, (a) it is possible to automatically set the moiré area of the disc, and (b) preventing the disc discrimination accuracy from being lowered due to the moiré. The effect that it becomes possible is acquired.

1 is a schematic block diagram illustrating a disk discrimination device according to an embodiment of the present invention. It is principal part sectional drawing which shows the image acquisition part which comprises the disc discrimination | determination apparatus of FIG. It is a schematic block diagram which shows the image process part and image memory | storage part which comprise the disk discrimination | determination apparatus of FIG. 3 is a flowchart for explaining the operation of the disk discriminating apparatus in FIG. 1. 5 is a flowchart showing details of reference image generation processing in FIG. 4. It is a flowchart which shows the detail of the captured image acquisition process of FIG. It is a flowchart which shows the detail of the pre-processing of FIG. It is a flowchart which shows the detail of the image rotation process of FIG. It is a flowchart which shows the detail of the contrast determination process of FIG. 5 is a flowchart showing details of moire image determination processing in FIG. 4. FIG. 10 is a flowchart showing details of the moire image determination process in FIG. 4 and is a continuation of FIG. 10. It is a flowchart which shows the detail of the mask image generation process of FIG. It is a flowchart which shows the detail of the authenticity determination process of FIG. It is a flowchart which shows the detail of the contrast determination process of FIG. It is a flowchart which shows the detail of the modification of the mask image generation process of FIG. It is a flowchart which shows the detail of the modification of the authenticity determination process of FIG.

  Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.

(Constitution)
1 to 3 show a disk discriminating apparatus 1 according to an embodiment of the present invention. The disc discriminating apparatus 1 has a function of acquiring a captured image of the front surface or the back surface (hereinafter, generically referred to as “front surface”) of the disc D and discriminating the authenticity of the disc D based on the acquired captured image. As shown in FIG. 1, the disc discrimination device 1 includes an image acquisition unit 2, an imaging timing sensor 3, a control unit 4, an image processing unit 5, an image storage unit 6, an input / output interface (I / F) 7, and a status indicator. 8 and a discrimination reference storage unit 9.

  First, the image acquisition unit 2 will be described with reference to FIGS. 1 and 2. As shown in FIG. 2, the image acquisition unit 2 has a function of acquiring a captured image of the surface of the disk D transported through the disk transport path 31 and outputting the captured image data ID of the disk D to the control unit 4. The image acquisition unit 2 includes a light projecting device 11, a two-dimensional imaging device 12, and a half mirror 26. The image acquisition unit 2 is arranged corresponding to the imaging window 33 opened in the base plate 32 that supports one surface of the disk D in the disk transport path 31.

  The imaging window 33 defines an imaging area 35 of the disk D that is transported through the disk transport path 31. The imaging window 33 has a pair of long sides substantially parallel to the transport direction DL of the disk D transported through the disk transport path 31 and a pair of short sides substantially perpendicular to the transport direction DL. A translucent plate 34 having translucency is disposed in the imaging window 33, and the surface of the translucent plate 34 on the side of the disk conveyance path 31 is substantially the same as the surface of the base plate 32, in other words, the bottom surface of the disk conveyance path 31. It is composed of one. The length of the pair of long sides of the imaging window 33 is set larger than the diameter of the disk D. This is because information regarding the diameter of the disk D in the longitudinal direction of the imaging window 33 is acquired. The short sides of the image pickup window 33 are arranged so that a straight line connecting the midpoints of the short sides of the image pickup window 33 and the locus of the center of the disk D conveyed on the disk transfer path 31 substantially coincide. This is because the information on the surface of the disk D can be obtained with certainty.

  The light projecting device 11 has a function of projecting light onto the surface of the disk D moving on the disk transport path 31. The light projecting device 11 is, for example, a surface light projecting device 21. This is because the use of the surface light projecting device 21 enables imaging without the influence of shadows even if the rotational phase of the disk D is different. The surface light projecting device 21 includes a light emitting element 22, a light guide plate 23, a reflection sheet 24, and a diffusion sheet 25. In this embodiment, the light emitting element 22 is an LED (Light Emitting Diode). The light emitting element (that is, LED) 22 is a light source for projecting light onto the disk D. White LED is used for the light emitting element 22, and the light emitting element 22 projects white visible light. However, a three-color LED can also be used as the light emitting element 22. As shown in FIG. 2, the light emitting element 22 is disposed so as to face the side end surface of the light guide plate 23. Therefore, the light emitting element 22 can be disposed in a plane parallel to the disk transport path 31, and the installation space is small. Note that the position of the light emitting element 22 shown in FIG. 2 is shown for convenience.

  In this embodiment, the light guide plate 23 is a rectangular thin plate made of resin from the viewpoint of low cost, and the surface thereof is arranged in parallel to the disk transport path 31. The resin exhibits a milky white color due to the transparent or diffusing material. When the diffusion material is mixed, the diffusion sheet 25 becomes unnecessary. The light guide plate 23 can also be configured by a glass substrate. In the present embodiment, the light guide plate 23 is opposed to the imaging region 35. The reflection sheet 24 has a function of preventing light from diffusing from the light guide plate 23 to the opposite side of the disk conveyance path 31 and reflecting the light toward the disk conveyance path 31. The reflection sheet 24 is in close contact with the surface of the light guide plate 23 located on the opposite side of the disk conveyance path 31. Note that a silver film may be deposited on the light guide plate 23 instead of the reflection sheet 24. The diffusion sheet 25 has a function of uniformly diffusing light projected from the surface of the light guide plate 23 on the disk transport path 31 side. Therefore, the projection light from the light emitting element 22 guided by the light guide plate 23 or reflected by the reflection sheet 24 is made a uniform amount of light over the entire surface by the diffusion sheet 25 and projected toward the disk transport path 31. To be lighted. As a result, the light is uniformly projected onto the disk D. The projection light projected from the diffusion sheet 25 is projected at a right angle to the disk transport path 31, in other words, the disk D moving on the disk transport path 31. This is because an optical shadow due to the unevenness of the flat surface of the disk D is not created. Since the light guide plate 23, the reflection sheet 24, and the diffusion sheet 25 are thin, the light projecting device 11 can be reduced in size.

  In addition, although the surface projector 21 of a present Example is comprised including LED as the light emitting element 22, the light guide plate 23, the reflective sheet 24, and the diffusion sheet 25, it is not limited to this. For example, an LED array in which a plurality of LEDs are arranged two-dimensionally, or parallel light combining a point light source such as an LED and a lens can be used. In this embodiment, an LED is used as the light emitting element 22, but the present invention is not limited to this, and a light source such as a cold cathode ray tube or a halogen lamp can also be used.

  The half mirror 26 has a function of reflecting part of incident light and transmitting part of incident light. Specifically, the light projection from the light projecting device 11 is transmitted, and the reflected light from the disk D is reflected. In other words, the half mirror 26 projects the light projected from the light projecting device 11 at a right angle to the disk D in the disk transport path 31 and the reflected light from the disk D in a direction parallel to the disk transport path 31. To reflect. The half mirror 26 is disposed at an angle of 45 degrees with respect to the surface of the disk transport path 31 on the side of the imaging region 35. In this embodiment, the half mirror 26 is formed by depositing or plating chromium as a reflective film on an organic glass formed of a light-projecting resin having a small thickness. However, the present invention is not limited to this, and optical glass such as borosilicate glass, quartz glass, zirconia, ruby and sapphire may be used as the substrate glass instead of organic glass. In addition, instead of chromium, a metal film such as tin and silver, or a dielectric material such as titanium oxide, silicon oxide, niobium pentoxide, tantalum pentoxide, and magnesium fluoride may be used as the reflective film. Further, the half mirror 26 may be a prism-type half mirror in which two right-angle prisms are bonded together, instead of the thin organic glass.

  The two-dimensional imaging device 12 includes a condenser lens 41 and an imaging element 42. The condenser lens 41 has a function of condensing the light reflected by the half mirror 26 into a predetermined small range. The condensing lens 41 is a convex lens having a predetermined refractive index because of the above function, and is disposed on the side of the half mirror 26, in other words, in the direction in which the half mirror 26 is inclined, and is equal to or smaller than the half mirror 26. It has a diameter. It is preferable to devise the shape of the light projecting device 11 and the like to reduce the size of the condenser lens 41. This is to reduce the price and size of the two-dimensional imaging device 12. The imaging element 42 has a function of capturing an image condensed by the condenser lens 41. The imaging element 42 is disposed on the opposite side of the half mirror 26 with respect to the condenser lens 41 and at a position where the surface image of the disk D is formed via the condenser lens 41. For the image pickup element 42, a CCD image sensor or a CMOS image sensor is employed for miniaturization.

  Next, the imaging timing sensor 3 will be described. The imaging timing sensor 3 has a function of detecting the timing at which the disk D conveyed on the disk conveyance path 31 passes over the imaging area 35. The imaging timing sensor 3 is arranged so that the imaging timing sensor 3 can detect the disk D or a transport unit (not shown) that transports the disk D when almost the entire surface of the disk D reaches above the half mirror 26. . Therefore, the imaging timing sensor 3 outputs a timing signal TS indicating the timing at which the disk D can be optimally imaged as a detection signal for the disk D.

  The control unit 4 controls the operation of the imaging element 42 and the light emitting element 22 based on the timing signal TS output from the imaging timing sensor 3, and stores the captured image acquired by the imaging element 42 in the image storage unit 6, The image processing unit 5 has a function of executing predetermined image processing based on the stored captured image. As shown in FIG. 3, the control unit 4 outputs the captured image data ID of the disk D output from the image acquisition unit 2 to a captured image holding unit 600 of the image storage unit 6 described later. Further, the control unit 4 outputs an image processing control signal PCS for the image processing unit 5 to the image processing unit 5. Further, the control unit 4 outputs a storage unit control signal MCS for the image storage unit 6 to the image storage unit 6. The control unit 4 is configured by, for example, a microcomputer that operates based on a predetermined program.

  As shown in FIG. 3, the image processing unit 5 includes a preprocessing unit 500, a reference image generation unit 510, a moire image processing unit 520, a mask image processing unit 540, and a determination unit 560, and is stored in the image storage unit 6. It has a function to perform various processes on the captured image. The image processing unit 5 is controlled by an image processing control signal PCS output from the control unit 4. Details of the image processing unit 5 will be described later.

  Next, the image storage unit 6 will be described. As shown in FIG. 3, the image storage unit 6 includes a captured image holding unit 600, a processed image holding unit 602, an input image holding unit 604, a reference image holding unit 606, a moire image holding unit 608, and a mask image holding unit 610. . The captured image holding unit 600 holds the captured image of the disc D to be discriminated based on the captured image data ID output from the control unit 4 and also the captured image data ID of each disc D to be discriminated. Is output to the preprocessing unit 500 of the image processing unit 5. The processed image holding unit 602 temporarily holds a captured image (hereinafter, referred to as a preprocessed image) processed by the preprocessing unit 500 of the image processing unit 5 and the stored preprocessed image as preprocessed image data PD. As a reference image generation unit 510 and a determination unit 560 of the image processing unit 5. The input image holding unit 604 temporarily holds an image processed by the reference image generation unit 510 (hereinafter referred to as an input image), and uses the held input image as input image data BD as a reference image of the image processing unit 5. It has a function of outputting to the generation unit 510 and the moire image processing unit 520.

  The reference image holding unit 606 holds the reference image generated by the reference image generation unit 510 of the image processing unit 5, and uses the held reference image as reference image data RD, the moire image processing unit 520 of the image processing unit 5, A function of outputting to the mask image processing unit 540 and the determination unit 560 is provided. The moire image holding unit 608 temporarily holds the input image selected as having a moire area in the moire image processing unit 520 of the image processing unit 5 as a moire image, and the held moire image as moire image data MD. A function of outputting to the moiré image processing unit 520 is provided. Further, the moire image holding unit 608 temporarily holds an accumulated moire image obtained by integrating a plurality of moire images in the moire image processing unit 520 of the image processing unit 5 and also stores the accumulated accumulated moire image. The image data IMD is output to the mask image processing unit 540 of the image processing unit 5. The mask image holding unit 610 holds the mask image generated by the mask image processing unit 540 of the image processing unit 5 and outputs the held mask image to the determination unit 560 of the image processing unit 5 as mask image data BMD. It has a function. The captured image holding unit 600, the processed image holding unit 602, the input image holding unit 604, and the moire image holding unit 608 are configured by, for example, a RAM (Random Access Memory) from the viewpoint of data reading / writing speed. The reference image holding unit 606 and the mask image holding unit 610 are configured by a nonvolatile memory such as an EEPROM (Electrically Erasable Programmable Read-Only Memory), for example, from the viewpoint of data holding durability. The operations of the captured image holding unit 600, the processed image holding unit 602, the input image holding unit 604, the reference image holding unit 606, the moire image holding unit 608 and the mask image holding unit 610 are stored in the storage unit control signal output from the control unit 4. Controlled by MCS.

  The input / output interface (I / F) 7 has a function of electrically connecting to a main device (not shown) in which the disc discrimination device 1 is incorporated. By connecting the main unit to the disc discriminating apparatus 1 via the input / output interface (I / F) 7, a desired signal can be input / output to / from the main unit.

  The status indicator 8 has a function of displaying the operation status of the disc discrimination device 1. The status indicator 8 is composed of, for example, a plurality of LEDs (not shown) having different emission colors, and the light emission of these LEDs is controlled by the control unit 4 so that various statuses (for example, the disc discrimination device 1) (for example, Normal operation, error occurrence, etc.) are notified. As the status indicator 8, a display device such as a liquid crystal panel can be used.

  The discrimination reference storage unit 9 has a function of storing a threshold value for discriminating a fake disk in the disc discrimination device 1. The discrimination reference storage unit 9 outputs the discrimination reference data SLS to the control unit 4. The control unit 4 determines the authenticity of the disc D to be discriminated based on the threshold value based on the sent discrimination reference data SLS.

  Next, the image processing unit 5 will be described in detail with reference to FIG. The image processing unit 5 has a function of generating a reference image for discriminating the disc D to be discriminated based on its surface pattern, a function of discriminating the presence or absence of a moire area of the input image of the disc D, and the disc D It has a function of generating a mask image that masks the moire area of the preprocessed image and the reference image, and a function of determining the pattern on the surface of the disc D to be determined based on the reference image. The image processing unit 5 includes a preprocessing unit 500, a reference image generation unit 510, a moire image processing unit 520, a mask image processing unit 540, and a determination unit 560.

  First, the preprocessing unit 500 will be described. The preprocessing unit 500 performs a reference image generation process in the reference image generation unit 510, a moire image selection process in the moire image processing unit 520, and a moire image selection process on the captured image of the disk D held in the captured image holding unit 600 of the image storage unit 6. The determination unit 560 has a function of performing a predetermined process for efficiently executing each of the determination processes. The captured image of the disk D held in the captured image holding unit 600 is input to the preprocessing unit 500 as the captured image data ID and processed by the preprocessing unit 500. Then, the pre-processed captured image (preprocessed image) of the disk D is output to the processed image holding unit 602 of the image storage unit 6 and is held by the processed image holding unit 602 of the image storage unit 6. As illustrated in FIG. 3, the preprocessing unit 500 includes an edge extraction unit 502, a center extraction unit 504, and an image cutout unit 506.

  The edge extraction unit 502 has a function of extracting an edge from the captured image held in the captured image holding unit 600. Edge extraction is a process of extracting, as an edge (feature), a portion where the luminance or color of a pixel in an image has changed greatly. Edge extraction can be performed by using a filter based on a first order derivative (Sobel filter and Prewitt filter) and a filter based on a second order derivative (Laplacian filter).

  The center extraction unit 504 has a function of extracting the center position of the disk D in the captured image based on the captured image held in the captured image holding unit 600. In other words, the coordinate value indicating the center of the disk D in the captured image is calculated. A known method is used for extraction of the center position. For example, one and the other of the peripheral portions of the disk D are detected for each line extending in the vertical axis (Y-axis) direction in the captured image, and both detected peripheral edges are detected. The midpoint between the two peripheral portions in the line where the interval between the portions is maximum is set as the center position of the disk D. However, other methods can be used to extract the center position.

  The image cutout unit 506 has a function of cutting out the image from which the center position is extracted by the center extraction unit 504 into a preset size with the center position as a reference. In this embodiment, the image cutout unit 506 cuts out the image whose center position is extracted by the center extraction unit 504 into a square shape so that the center position of the disk D and the intersection of the diagonal lines coincide. In addition, the shape which cuts out an image can also be cut out into a rectangular shape, and can also be cut out into a circular shape according to the outer periphery of the disc D.

  Next, the reference image generation unit 510 will be described. The reference image generation unit 510 has a function of performing a predetermined process for generating a reference image serving as a reference for determining the authenticity of the disc D. The reference image generation unit 510 applies the preprocessed image based on the processed image data PD sent from the processed image holding unit 602 of the image storage unit 6 and the input image data BD sent from the input image holding unit 604 of the image storage unit 6. A predetermined process is performed on each of the input image based on the reference image and the reference image based on the reference image data RD sent from the reference image holding unit 606 of the image storage unit 6. Then, the preprocessed image processed by the reference image generation unit 510 is output as input image data BD to the input image holding unit 604 of the image storage unit 6 and is held as an input image by the input image holding unit 604. Further, the preprocessed image processed by the reference image generation unit 510 is output to the reference image holding unit 606 as reference image data RD, and is held by the reference image holding unit 606 as a reference image. Further, the reference image processed by the reference image generation unit 510 is output to the reference image holding unit 606 as reference image data RD, and is held by the reference image holding unit 606 as a reference image. As illustrated in FIG. 3, the reference image generation unit 510 includes a comparison determination unit 512, an image rotation unit 514, and an image integration unit 516.

  The comparison determination unit 512 compares the pixel values of each pixel of the desired two images (pixels having the same coordinate value), and the degree of difference between the two images (hereinafter referred to as difference) or the degree of coincidence (hereinafter referred to as coincidence). A function to determine whether or not the two images match based on the degree). For example, when determining based on the degree of difference, if the total value of the number of pixels that do not match the pixel value exceeds a predetermined threshold stored in the discrimination reference storage unit 9, it is determined that the two images do not match. On the other hand, when determining based on the degree of coincidence, if the total value of the number of pixels with matching pixel values exceeds a predetermined threshold stored in the discrimination reference storage unit 9, it is determined that the two images match. In this embodiment, the determination is based on the degree of difference. Furthermore, the comparison determination unit 512 has a function of correcting a rotation angle shift between two images and a shift in a horizontal direction (a direction parallel to the image) (hereinafter collectively referred to as a relative position shift). The relative positional deviation can be corrected by a rotational deviation and positional deviation correction method disclosed in, for example, Japanese Patent Application Laid-Open No. 2006-134073. The comparison determination unit 512 detects the relative positional deviation between the reference image held in the reference image holding unit 606 of the image storage unit 6 and the preprocessed image of the disk number i held in the processed image holding unit 602 of the image storage unit 6. Make corrections. The comparison determination unit 512 compares the reference image with the preprocessed image of the disk number i that has been corrected for the relative displacement, and calculates the difference DF. The comparison determination unit 512 determines whether or not the preprocessed image with the disk number i matches the reference image based on the calculated dissimilarity DF.

  The image rotation unit 514 has a function of rotating a desired image around the center position of the disk D. The image rotation unit 514 rotates the reference image held in the reference image holding unit 606 of the image storage unit 6 with a predetermined rotation angle difference θd around the center position of the disk D. In other words, the image rotation unit 514 refers to the reference angle corresponding to the rotation angle “θ + θd” obtained by rotating the rotation angle difference θd with respect to the reference image corresponding to the rotation angle θ (hereinafter referred to as the reference image of the rotation angle θ). Generate an image. In this way, by preparing a plurality of reference images rotated for each rotation angle difference θd, a comparison determination process in step S21 of the reference image generation process in FIG. 5 described later and a true image in FIG. In the comparison determination process in step S145 of the false determination process, it is not necessary to compare the reference image with the rotation of the preprocessed image, and the comparison determination process between the preprocessed image and the reference image can be executed efficiently.

  The image integration unit 516 has a function of performing image integration processing on desired two images. The image integration process is a process for sharpening the edges of an image and smoothing to remove noise. The image integration process can be performed by simple integration in which a plurality of image weights to be integrated are constant and pixel values of each pixel are simply accumulated. The image accumulating unit 516 performs the rotation of “0 degrees” on the reference image held in the reference image holding unit 606 of the image storage unit 6 and the input image held on the input image holding unit 604 of the image storage unit 6. Perform image integration processing. The image subjected to the image integration process is output to the reference image holding unit 606 as the reference image data RD, and held in the reference image holding unit 606 as a reference image with a rotation angle “0 degree”.

  Next, the moire image processing unit 520 will be described. The moire image processing unit 520 has a function of determining whether or not there is a moire area with respect to a desired image and selecting an image with a moire area as a moire image. Further, the moire image processing unit 520 performs an image integration process on the selected plurality of moire images. The moiré image processing unit 520 determines whether each of the input images of the disk number i held in the input image holding unit 604 of the image storage unit 6 has a moiré area. The moire image processing unit 520 outputs the input image determined to have a moire area to the moire image holding unit 608 of the image storage unit 6 as moire image data MD. An image determined to have a moiré area is stored and held as a moiré image having a moiré number j by the moiré image holding unit 608. Further, the moire image processing unit 520 performs image integration processing on all moire images held in the moire image holding unit 608. The moiré image processing unit 520 outputs the image subjected to the image integration processing to the moire image holding unit 608 as integrated moire image data IMD. The image subjected to the image integration process is held by the moire image holding unit 608 as an integrated moire image. As shown in FIG. 3, the moire image processing unit 520 includes an evaluation value deriving unit 522, a determination threshold setting unit 524, a moire image selecting unit 526, and a moire image integrating unit 528.

  The evaluation value deriving unit 522 has a function of comparing pixel values for each pixel of the desired two images (pixels having the same coordinate value) and deriving an evaluation value from the degree of difference or coincidence between the two images. The evaluation value deriving unit 522 compares the pixel values of the reference image held in the reference image holding unit 606 of the image storage unit 6 and each pixel of the input image of each disk number i held in the input image holding unit 604. The degree of difference or the degree of coincidence is calculated, and the evaluation value EV of the input image of each disk number i is derived based on the calculated degree of difference or coincidence. Note that the method of calculating the degree of difference or the degree of coincidence in the evaluation value deriving unit 522 is the same as the method of calculating the degree of difference or the degree of coincidence in the comparison determination unit 512. The derived evaluation value EV is stored in a storage area (not shown) of the image storage unit 6.

  The determination threshold value setting unit 524 has a function of setting a determination threshold value for determining whether or not the input image of each disk number i has a moire area. The determination threshold setting unit 524 sets a determination threshold based on the frequency distribution table of the evaluation values EV derived by the evaluation value deriving unit 522. The set determination threshold value is stored in a storage area (not shown) of the image storage unit 6.

  The moire image selection unit 526 has a function of determining whether or not a desired image has a moire area and selecting an image having a moire area. Based on the evaluation value EV derived by the evaluation value deriving unit 522 and the determination threshold set by the determination threshold setting unit 524, the moire image selection unit 526 determines whether the input image of each disk number i has a moire area. Determine whether or not. For example, when the evaluation value EV is smaller than the determination threshold, the moire image selection unit 526 determines that the input image with the disk number i has a moire area. The input image of the disk number i determined to have a moire area is output to the moire image holding unit 608 of the image storage unit 6 as the moire image data MD, and held by the moire image holding unit 608 as the moire image of the moire number j. The

  The moiré image integration unit 528 has a function of performing image integration processing on a desired plurality of images. The moire image integration unit 528 performs image integration processing on all moire images held in the moire image holding unit 608 of the image storage unit 6. The image integration process of the moire image is the same as the image integration process in the image integration unit 516 of the reference image generation unit 510. The moire image that has undergone image integration processing is output to the moire image holding unit 608 as integrated moire image data IMD, and is held by the moire image holding unit 608 as an integrated moire image.

  Next, the mask image processing unit 540 will be described. The mask image processing unit 540 has a function of generating a mask image for excluding a moire area from effective pixels when comparing two desired images (pixels having the same coordinate value). The mask image processing unit 540 generates a mask image based on the reference image held in the reference image holding unit 606 of the image storage unit 6 and the accumulated moire image held in the moire image holding unit 608. The image generated by the mask image processing unit 540 is output as mask image data BMD to the mask image holding unit 610 of the image storage unit 6 and is held by the mask image holding unit 610 as a mask image. As illustrated in FIG. 3, the mask image processing unit 540 includes a mask threshold setting unit 542 and a mask image generation unit 544.

  The mask threshold value setting unit 542 calculates pixel value difference information for each pixel (pixels having the same coordinate value) of the desired two images, and sets effective pixels and ineffective pixels based on the calculated difference information. Has a function of setting a mask threshold. For example, the background difference method can be used to calculate the difference information, and an absolute value (hereinafter referred to as a difference pixel value) of a difference between pixel values of pixels (pixels having the same coordinate value) of the two images is a difference. Calculated as information. The mask threshold is set based on a frequency distribution table for the calculated difference pixel value of each pixel. For setting the mask threshold value, for example, a general binary image processing threshold value setting method such as a discriminant analysis method or a mode method can be used. The mask threshold setting unit 542 calculates a difference pixel value of each pixel which is difference information between the reference image held in the reference image holding unit 606 and the accumulated moire image held in the moire image holding unit 608. The mask threshold setting unit 542 sets the mask threshold based on the calculated frequency distribution table of the difference pixel value of each pixel. The set mask threshold is stored in a storage area (not shown) of the image storage unit 6.

  The mask image generation unit 544 has a function of generating a mask image. The mask image generation unit 544 applies the mask threshold set by the mask threshold setting unit 542 to an image based on the difference information between the reference image and the accumulated moire image (hereinafter referred to as a difference image), and obtains the difference image. Perform binarization. In other words, the mask image generation unit 544 applies a mask to the difference image based on the difference pixel value of each pixel (pixel having the same coordinate value) between the reference image and the integrated moire image calculated by the mask threshold setting unit 542. The mask threshold set by the threshold setting unit 542 is applied, and the difference image is binarized. The binarized difference image is held in the mask image holding unit 610 of the image storage unit 6 as a mask image.

  Next, the determination unit 560 will be described. The discriminating unit 560 uses the preprocessed image of the disc D to be discriminated held in the processed image holding unit 602 of the image storage unit 6 as a discriminated image and holds it in the discriminated image and the reference image holding unit 606 of the image storage unit 6. After the mask image held in the mask image holding unit 610 of the image storage unit 6 is applied to each of the plurality of reference images, the discriminated image and each reference image are compared, and the disc to be discriminated from the comparison result It has a function of determining whether D is true or false. The discrimination result is output from the image processing unit 5 to the control unit 4 as a discrimination signal IS. The determination unit 560 includes a mask image application unit 562 and a dissimilarity deriving unit 564.

  The mask image application unit 562 has a function of applying the mask image held in the mask image holding unit 610 of the image storage unit 6 to a desired image. The mask image application unit 562 applies an image storage unit to each of the discriminated image held in the processed image holding unit 602 of the image storage unit 6 and the plurality of reference images held in the reference image holding unit 606 of the image storage unit 6. The mask image held in the mask image holding unit 610 is applied. As a result, the moire area of each of the discriminated image and the plurality of reference images is excluded from the effective pixels for discriminating the authenticity of the disc D.

  The dissimilarity deriving unit 564 compares pixel values for each pixel (pixels having the same coordinate value) of the desired two images, and determines whether the two images match based on the dissimilarity or coincidence of the two images. It has the function to judge. For example, when the determination is made based on the degree of difference, when the total value of the number of pixels that do not match the pixel value exceeds a predetermined threshold stored in the image storage unit 6, it is determined that the two images do not match. On the other hand, when the determination is based on the degree of coincidence, if the total value of the number of pixels with matching pixel values exceeds a predetermined threshold stored in the image storage unit 6, it is determined that the two images match. In this embodiment, the determination is based on the degree of difference.

  The edge extraction unit 502, the center extraction unit 504, the comparison determination unit 512, the image rotation unit 514, the image integration unit 516, the evaluation value derivation unit 522, the determination threshold setting unit 524, and the moire image selection unit that constitute the image processing unit 5. 526, moire image integration unit 528, mask threshold setting unit 542, mask image generation unit 544, mask image application unit 562, and dissimilarity derivation unit 564 may be either hardware or software as long as they have their respective functions. It may be configured. It is possible to make a part of the hardware and the rest software.

(Operation)
Next, the operation of the disk discriminating apparatus 1 will be described with reference to FIGS. Note that the captured image acquired by the operation of the disc discriminating apparatus 1 is one of the front surface and the back surface of the disc D. Therefore, when the patterns on the front and back surfaces of the disc D are different, it is necessary to generate the reference images for the front and back surfaces, and to compare with the reference images for the front and back surfaces. In the present embodiment, description will be made assuming that the patterns on the front and back surfaces of the disk D are the same.

  First, as shown in FIG. 4, initialization is performed in step S1. In initialization, the frame rate of the image sensor 42, the sensitivity of the imaging timing sensor 3, and the like are set.

  In the next step S2, it is determined whether one of the registration mode for registering the reference image and the determination mode for determining the authenticity of the disk D has been selected. If it is determined in step S2 that the registration mode has been selected, the process proceeds to step S3. On the other hand, if it is determined in step S2 that the determination mode is selected, the process proceeds to step S8.

  In step S <b> 3, it is determined whether or not it has been selected whether or not to generate a reference image. When it is determined that the generation of the reference image is selected, the process proceeds to step S4, the reference image generation process for generating the reference image is executed, and the process proceeds to step S5. On the other hand, if it is determined that the generation of the reference image has not been selected, the process proceeds to step S5. Details of the reference image generation process in step S4 will be described later.

  In step S5, it is determined whether or not to generate a mask image has been selected. When it is determined that the generation of the mask image has been selected, in step S6, a moire image determination process is performed in which a moire image having a moire area is selected from the input image held in the input image holding unit 604 of the image storage unit 6. In the next step S7, a mask image generation process for generating a mask image for excluding the moire areas of the reference image and the input image of the disc D from the effective pixels for discriminating the authenticity of the disc D is executed. . After the mask image generation process in step S7 is completed, the process returns to step S2. On the other hand, if it is determined that the generation of the mask image has not been selected, the process returns to step S2. Details of the moire image determination process in step S6 and the mask image generation process in step S7 will be described later.

  In step S8, authenticity determination processing for determining the authenticity of the disk D is executed. After the authenticity determination process in step S8 is completed, the process returns to step S2. Details of the authenticity determination process in step S8 will be described later.

  Next, the reference image generation process in step S4 of FIG. 4 will be described with reference to FIG. In step S11, “1” is set to the disk number i (i = 1). In other words, the disk number i of the disk D is initialized. In the next step S12, “0” is set to the rotation angle θ (θ = 0). In other words, the rotation angle θ is initialized.

  In the next step S13, a captured image acquisition process for acquiring a captured image of any one of the front surface and the back surface of the disk D is executed. The image acquisition unit 2 images the disk D that has reached the imaging position, in other words, the disk D that faces the imaging window 33 and acquires the captured image of the disk D. The image acquisition unit 2 outputs the acquired captured image to the control unit 4 as a captured image data ID. The control unit 4 transfers the supplied captured image data ID to the image storage unit 6. The image storage unit 6 stores and holds the captured image based on the transmitted captured image data ID in the captured image holding unit 600. Details of the captured image acquisition process in step S13 will be described later.

  In step S14, the preprocessing unit 500 performs preprocessing on the captured image of the disk D. The control unit 4 outputs a storage unit control signal MCS to the image storage unit 6, and the image storage unit 6 outputs the captured image data ID based on the captured image held in the captured image holding unit 600 based on the storage unit control signal MCS. The data is output to the processing unit 500. The preprocessing unit 500 performs preprocessing on the captured image based on the transmitted captured image data ID. The preprocessing unit 500 outputs the preprocessed image to the processed image holding unit 602 of the image storage unit 6 as processed image data PD. Details of the preprocessing in step S14 will be described later.

  In step S15, it is determined whether the disk number i exceeds 1 (i> 1) or not (i ≦ 1). When the disk number i is 1 or less (i ≦ 1), in other words, when the disk number i is “1” (i = 1), in other words, in the reference image generation process in step S4 of FIG. When the disc D from which the image acquisition unit 2 has acquired the captured image is the first disc, the process proceeds to step S16. On the other hand, if the disk number i exceeds 1 (i> 1), in other words, if the disk D from which the image acquisition unit 2 has acquired the captured image is the second or subsequent disk, the process proceeds to step S21.

  In the next step S16, the input image holding unit 604 of the image storage unit 6 holds the input image of the disk D with the disk number “1”. The preprocessing unit 500 outputs the preprocessed image (preprocessed image) of the disk D with the disk number “1” to the input image holding unit 604 as input image data BD. The input image holding unit 604 stores and holds the input image based on the sent input image data BD in association with the disk number i. In step S16, the input image holding unit 604 stores and holds the input image based on the sent input image data BD in association with the disk number “1”. In other words, the input image holding unit 604 stores and holds the input image based on the sent input image data BD as the input image of the disk number “1”.

  In the next step S <b> 17, the reference image holding unit 606 of the image storage unit 6 holds the reference image of the disk D. The preprocessing unit 500 outputs the preprocessed image (preprocessed image) of the disk D with the disk number “1” to the reference image holding unit 606 as the reference image data RD. The reference image holding unit 606 stores and holds a reference image of the disk D based on the sent reference image data RD. Note that the input image data BD output by the preprocessing unit 500 in step S16 and the reference image data RD output by the preprocessing unit 500 in step S17 are based on the preprocessed image of the disk D having the same disk number “1”. It is data. In other words, at the time of step S17, the input image holding unit 604 and the reference image holding unit 606 hold the same image. In other words, at the time of step S17, the input image with the disk number “1” held in the input image holding unit 604 and the reference image held in the reference image holding unit 606 are the same image.

  In the next step S18, the image rotation unit 514 of the reference image generation unit 510 creates a plurality of reference images by rotating the reference image for each predetermined rotation angle difference θd. The reference image holding unit 606 outputs the reference image data RD to the reference image generation unit 510. The image rotation unit 514 of the reference image generation unit 510 performs a rotation process for rotating the image on the reference image based on the sent reference image data RD. The image rotation unit 514 rotates the reference image for each predetermined rotation angle difference θd with the center position of the disk D as the rotation center, and creates a plurality of reference images. The reference image generation unit 510 outputs the plurality of reference images rotated by the image rotation unit 514 to the reference image holding unit 606 as reference image data RD. The reference image holding unit 606 stores and holds each of the plurality of reference images based on the sent reference image data RD in association with the rotation angle θ. The rotation angle difference θd can be arbitrarily set. For example, when the rotation angle difference θd is “1 degree”, the rotation angle difference θd is rotated by “1 degree”, that is, the rotation angle θ is different by “1 degree”. 360 reference images are created. When the rotation angle difference θd is “3.6 degrees”, 100 reference images with different rotation angles θ by “3.6 degrees” are created. Further, when the rotation angle difference θd is “5 degrees”, 72 reference images having different rotation angles θ by “5 degrees” are created. Details of the image rotation processing in step S18 will be described later.

  In the next step S19, “i + 1” is set to the disk number i. In other words, a value obtained by adding “1” to the current disk number i is set as a new disk number i. In other words, the disk number i is updated.

  In the next step S20, it is determined whether or not the disk number i exceeds a preset value imax (i> imax). In other words, it is determined whether or not the disk number i has reached the total number imax of the disks D set in advance for generating the reference image. If the disk number i is less than or equal to the value imax (i ≦ imax), the process returns to step S12 and the reference image generation process is continued. On the other hand, if the disk number i exceeds the value imax (i> imax), the process proceeds to step S25.

  If the disk number i exceeds “1” in step S15 (i> 1), the process proceeds to step S21. In the next step S21, the comparison determination unit 512 of the reference image generation unit 510 determines whether or not the preprocessed image with the disk number i matches the reference image. The reference image holding unit 606 outputs the reference image data RD to the reference image generation unit 510. The processed image holding unit 602 outputs the preprocessed image data PD to the reference image generating unit 510. The comparison determination unit 512 of the reference image generation unit 510 compares the reference image based on the sent reference image data RD with the preprocessed image of the disk number i based on the sent preprocessed image data PD, and The difference degree of the preprocessed image is calculated, and it is determined whether or not the preprocessed image matches the reference image based on the calculated difference degree. In other words, the comparison determination unit 512 determines whether or not the disk D with the disk number i matches the disks D with the disk numbers “1” to “i−1”. If it is determined that the preprocessed image with the disk number i matches the reference image, the process proceeds to step S22. On the other hand, if it is determined that the preprocessed image on the disk D does not match the reference image, that is, does not match, the process returns to step S12, and the process on the next disk D is executed. The details of the comparison determination process in step S21 will be described later.

  In the next step S22, the input image holding unit 604 holds the input image of the disk number i. The reference image generation unit 510 outputs the preprocessed image with the disk number i to the input image holding unit 604 as the input image data BD. The input image holding unit 604 stores and holds the input image based on the sent input image data BD in association with the disk number i.

  In the next step S23, the image integration unit 516 of the reference image generation unit 510 integrates the input image with the disk number i on the reference image. The reference image holding unit 606 outputs the reference image data RD to the reference image generation unit 510. The input image holding unit 604 outputs the input image data BD to the reference image generation unit 510. The image accumulating unit 516 of the reference image generating unit 510 receives the input image of the disk number i based on the input image data BD sent to the reference image with the rotation angle “0 degrees” based on the supplied reference image data RD. Accumulate.

  In the next step S24, the reference image holding unit 606 holds the reference image. The reference image generation unit 510 outputs the reference image after image integration to the reference image holding unit 606 as reference image data RD. The reference image holding unit 606 stores and holds a reference image based on the sent reference image data RD as a reference image with a rotation angle “0 degrees”. After the reference image holding unit 606 stores and holds the reference image after the image integration, the process proceeds to step S19.

  When the disk number i is equal to or greater than imax in step S19 (i ≧ imax), the process proceeds to step S25, and the image rotation unit 514 rotates the reference image with the rotation angle “0 degree” for each predetermined rotation angle difference θd. Create multiple reference images. The reference image holding unit 606 outputs the reference image data RD to the reference image generation unit 510. The image rotation unit 514 of the reference image generation unit 510 performs a rotation process for rotating the image on the reference image with the rotation angle “0 degrees” based on the transmitted reference image data RD. The image rotation unit 514 rotates a reference image with a rotation angle “0 degree” for each predetermined rotation angle difference θd with the center position of the disk D as the rotation center, and creates a plurality of reference images. The reference image generation unit 510 outputs the plurality of reference images rotated by the image rotation unit 514 to the reference image holding unit 606 as reference image data RD. The reference image holding unit 606 stores and holds each of a plurality of reference images based on the sent reference image data RD in association with the rotation angle θ. Note that the image rotation process in step S25 is exactly the same as the image rotation process in step S18. When the image rotation process in step S25 is completed, the reference image generation process ends. In this way, the reference image generation process in step S4 in FIG. 4 is completed, and a plurality of input images associated with each disk number i, that is, each of the disk numbers “1” to “imax”, are input image holding unit 604. And a plurality of reference images associated with the respective rotation angles θ are held in the reference image holding unit 606. The input image holding unit 604 stores and holds the input image associated with each disk number i, and the reference image holding unit 606 stores and holds the reference image associated with each rotation angle θ. Return to step S5 of step 4.

  In the present embodiment, in the reference image generation process in step S3 of FIG. 4, in the image integration process in step S23, the input image is input to the reference image of the rotation angle θ held in the reference image holding unit 606 of the image storage unit 6. However, it is also possible to sequentially integrate each of the input images having the disk numbers “2” to “imax” with respect to the input image having the disk number “1”, for example. Further, in the comparison determination process of step S21, the determination of matching of the preprocessed images with the disk numbers “3” to “imax” is performed on the reference image obtained by integrating the input images with the disk numbers “1” to “i-1”. However, it is also possible to hold the preprocessed image with the disk number “1” as a temporary reference image and perform a match determination of the preprocessed image with the disk number i based on the temporary reference image.

  The captured image acquisition process in step S13 in FIG. 5 will be described with reference to FIG. In step S31, it is determined whether or not the imaging timing sensor 3 is turned on. In other words, it is determined whether or not the disk D moving on the disk transport path 31 has reached the imaging position. When the disk D reaches the imaging position, the imaging timing sensor 3 is turned on. That is, the imaging timing sensor 3 is turned on corresponding to the movement of the disk D in the disk transport path 31. If the imaging timing sensor 3 is on, the process proceeds to step S32. If the disk D does not reach the imaging position, the imaging timing sensor 3 is kept off and step S31 is repeatedly executed. In other words, the image acquisition unit 2 is in a standby state until the disk D reaches the imaging position.

  In the next step S32, the control unit 4 outputs a lighting control signal LCS to the light emitting element 22, and the light emitting element 22 is lighted for a short time (that is, flash issuance) based on the lighting control signal LCS. Accordingly, diffused light is emitted from the light projecting device 11 toward the imaging window 33, and the disk D facing the imaging window 33 is projected.

  In the next step S33, the control unit 4 outputs the imaging control signal ICS to the imaging element 42, and the imaging element 42 images the disc D to be determined based on the imaging control signal ICS. In other words, a captured image of the disc D to be determined is acquired by the two-dimensional imaging device 12. The imaging element 42 outputs the acquired captured image data ID to the control unit 4. The control unit 4 transfers the supplied captured image data ID to the image storage unit 6. The image storage unit 6 stores and holds the captured image based on the transmitted captured image data ID in the captured image holding unit 600. After the captured image acquisition process in step S13 in FIG. 5 is completed in this way, the process returns to step S14 in FIG.

  The preprocessing in step S14 in FIG. 5 will be described with reference to FIG. In step S <b> 41, the edge extraction unit 502 performs edge extraction processing on the captured image held in the captured image holding unit 600. The edge-extracted image is held in the processed image holding unit 602 of the image storage unit 6.

  In the next step S42, the center extraction unit 504 extracts the center position of the disk D in the image after edge extraction held in the processed image holding unit 602. The extracted coordinate value of the center position is stored in a storage area (not shown) of the image storage unit 6.

  In the next step S43, the image cutout unit 506 cuts out the edge-extracted image held in the processed image holding unit 602 into a rectangular shape. The image cutout unit 506 cuts out the image after edge extraction of the image into a rectangular shape based on the center position of the disk D extracted by the center extraction unit 504. More specifically, the image cutout unit 506 cuts out the image after edge extraction into a rectangular shape so that the intersection of two rectangular diagonal lines matches the center position of the disk D. The image cut into a rectangular shape is held in the processed image holding unit 602. In this way, the preprocessing in step S14 in FIG. 5 is completed, and the captured image subjected to the preprocessing is held in the processed image holding unit 602 as a processed image. After the processed image holding unit 602 stores and holds the processed image, the process returns to step S15 in FIG.

  The image rotation processing in step S18 and step S25 in FIG. 5 will be described with reference to FIG. First, in step S51, “θ + θd” is set as the rotation angle θ. In other words, a value obtained by adding the rotation angle difference θd to the current rotation angle θ is set as a new rotation angle θ. In other words, the rotation angle θ is updated.

  In the next step S52, it is determined whether or not the rotation angle θ is 360 degrees or more (θ ≧ 360 degrees). When the rotation angle θ is not 360 degrees or more (θ <360 degrees), the process proceeds to step S53.

  In the next step S53, the image rotation unit 514 of the reference image generation unit 510 rotates the reference image corresponding to the rotation angle 0 ° (θ = 0) held in the reference image holding unit 606 by the rotation angle θ. The reference image rotated by the rotation angle θ (hereinafter referred to as a reference image having the rotation angle θ) is held in the reference image holding unit 606. After the reference image holding unit 606 stores and holds the reference image of the rotation angle θ, the process returns to step S51 and the image rotation process is continued.

  On the other hand, when the rotation angle θ is 360 degrees or more in step S52 (θ ≧ 360 degrees), it is determined that the creation of the reference image rotated for each rotation angle difference θd is completed, and the rotation in step S18 of FIG. The image creation process is completed. In this way, the rotation reference image generation process in step S18 of FIG. 5 is completed, and each of the reference images rotated by the rotation angle difference θd is held in the reference image holding unit 606 as a reference image of the rotation angle θ. After the reference image holding unit 606 stores and holds the reference image of each rotation angle θ, the process returns to step S19 in FIG. In addition, the rotation reference image generation process in step S25 of FIG. 5 is completed, and each reference image rotated by the rotation angle difference θd is held in the reference image holding unit 606 as a reference image of the rotation angle θ. After the reference image holding unit 606 stores and holds the reference image of each rotation angle θ, the reference image generation process of FIG. 5 is completed.

  The reference image comparison determination process in step S21 of FIG. 5 will be described with reference to FIG. First, in step S61, the reference image generation unit 510 corrects the relative position shift (rotation angle shift and horizontal shift) of the preprocessed image of the disk D with the disk number i with respect to the reference image. The correction of the relative positional deviation can be performed by, for example, a correction method for a rotational angle deviation and a horizontal direction deviation disclosed in JP-A-2006-134073. The processed image holding unit 602 of the image storage unit 6 outputs the preprocessed image data PD to the reference image generation unit 510 of the image processing unit 5. The reference image holding unit 606 of the image storage unit 6 outputs the reference image data RD to the reference image generation unit 510 of the image processing unit 5. The reference image generation unit 510 compares the preprocessed image of the disk number i based on the sent preprocessed image data PD with the reference image based on the sent reference image data RD, and compares the preprocessed image data before the disk number i with respect to the reference image. Correct the relative displacement of the processed image. The comparison determination unit 512 of the reference image generation unit 510 compares the preprocessed image with the disk number i with the reference image with each rotation angle θ, and compares the preprocessed image with the disk number i with respect to the reference image with the rotation angle “0 degrees”. The deviation angle is derived. The image rotation unit 514 of the reference image generation unit 510 rotates the deviation angle θ derived from the preprocessed image of the disk number i. The comparison determination unit 512 corrects the horizontal displacement of the preprocessed image obtained by correcting the rotation angle displacement with respect to the reference image having the rotation angle “0 degree”. The preprocessed image of the disk number i whose relative positional deviation has been corrected in this way is stored and held in the processed image holding unit 602.

  In the next step S62, the comparison determination unit 512 calculates the difference DF of the preprocessed image of the disk number i in which the relative positional deviation with respect to the reference image is corrected. The processed image holding unit 602 outputs the preprocessed image data PD to the reference image generating unit 510. The reference image holding unit 606 outputs the reference image data RD to the reference image generation unit 510. The reference image generation unit 510 compares the preprocessed image with the disk number i based on the sent preprocessed image data PD and the reference image with the rotation angle “0 degrees” based on the sent reference image data RD. The difference DF of the preprocessed image with the disk number i with respect to the reference image is calculated. The calculated difference degree DF is stored in a storage area (not shown) of the image storage unit 6.

  In the next step S63, it is determined whether or not the dissimilarity DF is equal to or less than a predetermined threshold value. If the dissimilarity DF is less than or equal to the threshold value (DF ≦ threshold value), the process proceeds to step S64, where the preprocessed image with the disk number i matches the reference image. And the process returns to step S22 in FIG. On the other hand, if the degree of difference DF exceeds the threshold (DF> threshold), the process proceeds to step S65, where the reference image and the preprocessed image with the disk number i do not match, in other words, the preprocessed image on the disk D is the reference image. It is determined that the image is not an image to be accumulated in step S13 and the process returns to step S13 in FIG.

  Next, the moire determination process in step S6 of FIG. 4 will be described with reference to FIGS. First, in step S81, “1” is set to the disk number i. In other words, the disk number i is initialized.

  In the next step S82, the moire image processing unit 520 reads the reference image held in the reference image holding unit 606. In the next step S83, the moire image processing unit 520 reads the input image of the disk number i held in the input image holding unit 604.

  In the next step S82, the evaluation value deriving unit 522 of the moire image processing unit 520 compares the input image of the disk number i with the reference image to derive the evaluation value EV. As the evaluation value EV, for example, the degree of difference or coincidence of the input image with respect to the reference image can be used. In addition, for example, the number of pixels (number of pixels) of the input image different from the reference image can be simply used as the evaluation value EV. The derived evaluation value EV is stored in a storage area (not shown) of the image storage unit 6.

  In the next step S85, “i + 1” is set to the disk number i. In other words, a value obtained by adding “1” to the current disk number i is set as a new disk number i. In other words, the disk number i is updated.

  In the next step S86, it is determined whether or not the disk number i exceeds a preset value imax (i> imax). When the disk number i is equal to or less than imax (i ≦ imax), the process returns to step S83. On the other hand, if the disk number i exceeds imax (i> imax), the process proceeds to step S87.

  In the next step S87, the determination threshold setting unit 524 of the moire image processing unit 520 sets a determination threshold DI for determining whether the input image has a moire area, in other words, whether the input image is a moire image. To do. The determination threshold DI is set from a frequency distribution based on the evaluation value EV. More specifically, the determination threshold DI is set based on the frequency distribution on the side where the evaluation value is higher than the average value of the frequency distribution based on the evaluation value EV. After the determination threshold setting unit 524 sets the determination threshold DI, the process proceeds to step S88 in FIG. The set determination threshold value DI is stored in a storage area (not shown) of the image storage unit 6.

  In the next step S88, “1” is set to the disc number i, and the moire image number j (hereinafter referred to as moire number j) is set to “1”. In other words, the disk number i and the moire number j are initialized.

  In the next step S89, the moire image selection unit 526 reads the determination threshold value DI stored in a storage area (not shown) of the image storage unit 6. In the next step S90, the moire image selection unit 526 reads the evaluation value EV of the disk number i stored in a storage area (not shown) of the image storage unit 6.

  In the next step S91, it is determined whether or not the evaluation value EV of the disk number i is equal to or less than the determination threshold value DI. The moiré image selection unit 526 compares the evaluation value EV of the disk number i with the determination threshold value DI and determines whether or not the input image of the disk number i has a moire area from the magnitude relationship, in other words, the disk number i. It is determined whether the input image is a moire image. When the evaluation value EV of the disk number i is equal to or less than the determination threshold value DI, the process proceeds to step S92, where it is determined that the input image of the disk number i has a moire area, in other words, the input image of the disk number i is a moire image. The process proceeds to step S93. On the other hand, if the evaluation value EV of the disk number i exceeds the determination threshold value DI, the process proceeds to step S98, where the input image of the disk number i does not have a moire area, in other words, the input image of the disk number i is not a moire image. And the process proceeds to step S96.

  In step S93, the moire image holding unit 608 of the image storage unit 6 stores and holds the moire image having the moire number j. The moire image processing unit 520 outputs the input image of the disk number i determined by the moire image selection unit 526 to have a moire area to the moire image holding unit 608 as moire image data MD. The moire image holding unit 608 stores and holds the moire image based on the sent moire image data MD as the moire image having the moire number j.

  In the next step S94, the moire number j is set to “j + 1”. In other words, a value obtained by adding “1” to the current moire number j is set as a new moire number j. In other words, the moire number j is updated.

  In the next step S95, the maximum moire number jmax is set to “j”. In other words, the maximum moire number jmax is updated.

  In the next step S96, the disk number i is set to “i + 1”. In other words, a value obtained by adding “1” to the current disk number i is set as a new disk number i. In other words, the disk number i is updated.

  In the next step S97, it is determined whether or not the disk number i exceeds a preset value imax (i> imax). In other words, in the reference image generation process of FIG. 5, it is determined whether or not the total number imax of the disks D stored and held in the input image holding unit 604 is exceeded. When the disk number i is equal to or less than imax (i ≦ imax), the process returns to step S90. On the other hand, when the disk number i exceeds imax (i> imax), it is determined whether or not there is a moire area for all the input images of the disk number i held in the input image holding unit 604, in other words, a moire image. The moire image determination ends. In this way, the moire image determination process in step S6 of FIG. 4 is completed, and each input image of the disk number i determined as a moire image is held in the moire image holding unit 608 as a moire image of moire number j. . After the moire image holding unit 608 stores and holds the moire image, the process returns to step S7 in FIG.

  The mask image generation process in step S7 of FIG. 4 will be described with reference to FIGS. First, in step S121, “1” is set to the moire number j. In other words, the moire number j is initialized.

  In the next step S122, the moire image holding unit 608 stores and holds the accumulated moire image. The moire image holding unit 608 of the image storage unit 6 outputs the moire image data MD based on the moire image having the moire number j to the moire image processing unit 520. The moire image processing unit 520 outputs the moire image having the moire number j based on the sent moire image data MD to the moire image holding unit 608 as integrated moire image data IMD. The moire image holding unit 608 stores and holds the accumulated moire image based on the sent accumulated moire image data IMD. In other words, the moire image having the moire number j is held in the moire image holding unit 608 as an integrated moire image. In other words, in step S122, the moire image having the moire number “1” is held in the moire image holding unit 608 as an integrated moire image.

  In the next step S123, “j + 1” is set to the moire number j. In other words, a value obtained by adding “1” to the current moire number j is set as a new moire number j. In other words, the moire number j is updated.

  In the next step S124, the moire image integrating unit 528 performs image integration processing on the integrated moire image and the moire image having the moire number j. The moire image holding unit 608 of the image storage unit 6 outputs the moire image data MD based on the integrated moire image data IMD and the moire image of the moire number j to the moire image processing unit 520. The moiré image integration unit 528 performs image integration processing on the integrated moire image based on the transmitted integrated moire image data IMD and the moire image of the moire number j based on the transmitted moire image data MD. In other words, the moire image having the moire number j is added to the integrated moire image. The moire image processing unit 520 outputs the integrated moire image subjected to the image integration process to the moire image holding unit 608 as integrated moire image data IMD. The moire image holding unit 608 stores and holds the accumulated moire image based on the sent accumulated moire image data IMD.

  In the next step S125, “j + 1” is set to the moire number j. In other words, a value obtained by adding “1” to the current moire number j is set as a new moire number j. In other words, the moire number j is updated.

  In the next step S126, it is determined whether or not the moire number j exceeds the total number jmax of the moire images of the disc D held in the moire image holding unit 608 (j> jmax). When the moire number j is equal to or less than jmax, the process returns to step S125, and the process of integrating the moire image with the moire number j on the integrated moire image is continued. On the other hand, when the moire number j exceeds jmax, the process proceeds to step S130 in FIG.

  In the next step S127, the mask threshold value setting unit 542 calculates the absolute value (difference pixel value) of the pixel value difference of each pixel between the reference image and the integrated moire image as difference information. The reference image holding unit 606 outputs the reference image data RD to the mask image processing unit 520. The moire image holding unit 608 outputs the accumulated moire image data IMD to the mask image processing unit 520. The mask threshold value setting unit 542 of the mask image processing unit 520 has an absolute value (difference pixel) of a difference between pixel values of each pixel between the reference image based on the transmitted reference image data RD and the integrated moire image data based on the integrated moire image data IMD. Value). The calculated difference information (difference pixel value of each pixel) is stored in a storage area (not shown) of the image storage unit 6.

  In the next step S128, the mask threshold value setting unit 542 sets the mask threshold value MI. The mask threshold setting unit 542 sets the mask threshold MI based on the difference information between the reference image and the accumulated moire image. In other words, the mask threshold value setting unit 542 sets the mask threshold value MI from the frequency distribution table for the difference pixel value of each pixel between the reference image and the integrated moire image. The set mask threshold MI is stored in a storage area (not shown) of the image storage unit 6.

  In the next step S129, the mask image generation unit 544 binarizes the difference image based on the difference information between the reference image and the integrated moire image. In other words, the mask image generation unit 544 binarizes the difference image based on the difference pixel value of each pixel between the reference image and the integrated moire image. The mask image processing unit 540 outputs the binarized difference image to the mask image holding unit 610 as mask image data BMD. The mask image holding unit 610 stores and holds a mask image based on the sent mask image data BMD. In this way, after the mask image generation process in step S7 in FIG. 4 is completed and the mask image holding unit 610 stores and holds the mask image, the registration mode of the disc discrimination device 1 in FIG. 4 ends.

  The authenticity determination process in step S8 of FIG. 4 will be described with reference to FIG. First, in step S141, “0 degree” is set as the rotation angle θ. In other words, the rotation angle θ is initialized.

  In the next step S142, a captured image acquisition process for acquiring a captured image of either one of the front surface and the back surface of the disc D to be determined is executed. The image acquisition unit 2 images the disc D to be discriminated that has reached the imaging position, and acquires a captured image of the disc D. The image acquisition unit 2 outputs the captured image data ID based on the acquired captured image of the disc D to be discriminated to the control unit 4. The control unit 4 transfers the supplied captured image data ID to the image storage unit 6. The image storage unit 6 stores and holds the captured image of the disc D to be discriminated based on the transmitted captured image data ID in the captured image holding unit 600. This captured image acquisition process is exactly the same as the captured image acquisition process in step S13 of FIG. 5, and is executed in the flowchart of the captured image acquisition process shown in FIG.

  In the next step S143, the preprocessing unit 500 performs preprocessing on the captured image of the disc D to be determined. The control unit 4 outputs a storage unit control signal MCS to the image storage unit 6, and the image storage unit 6 is based on the captured image of the disc D to be discriminated held in the captured image holding unit 600 based on the storage unit control signal MCS. The captured image data ID is output to the preprocessing unit 500. The pre-processing unit 500 performs pre-processing on the captured image of the disc D to be determined based on the transmitted captured image data ID. The preprocessing unit 500 outputs the preprocessed captured image of the disc D to be discriminated to the processed image holding unit 602 of the image storage unit 6 as preprocessed image data PD. The processed image holding unit 602 stores and holds a preprocessed image of the disc D to be discriminated based on the sent preprocessed image data PD as a discriminated image. This pre-process is exactly the same as the pre-process in step S14 of FIG. 5, and is executed in the pre-process flowchart shown in FIG.

  In the next step S144, the dissimilarity deriving unit 564 of the determination unit 560 determines the authenticity of the disc D to be determined. The degree-of-difference deriving unit 564 calculates the degree of difference DF of the discriminated image with respect to the reference image by comparing the reference image and the discriminated image. The difference degree deriving unit 564 determines the authenticity of the disc D to be determined based on the calculated difference degree DF. Details of the comparison determination process in step S145 will be described later. After the comparison determination process in step S145 is completed, the authenticity determination process in step S8 of FIG. 4 ends.

  The comparison determination process in step S145 of the authenticity determination process in FIG. 14 will be described with reference to FIG. First, in step S161, the dissimilarity deriving unit 564 of the determination unit 560 corrects the relative positional deviation of the determination target image with respect to the reference image. The correction of the relative positional deviation can be performed by the correction method of the rotational angle deviation and the horizontal deviation disclosed in, for example, Japanese Patent Application Laid-Open No. 2006-134073, similarly to the deviation correction processing in step S61 of FIG. The degree-of-difference deriving unit 564 compares the reference image with the image to be determined, and corrects the relative positional deviation of the image to be determined with respect to the reference image. The degree-of-difference deriving unit 564 compares the discriminated image with the reference image at each rotation angle θ, and derives the deviation angle of the discriminated image with respect to the reference image at the rotation angle “0 degree”. The degree-of-difference deriving unit 564 rotates the shift angle θ from which the image to be determined is derived. The degree-of-difference deriving unit 564 corrects the horizontal shift of the image to be discriminated in which the shift of the rotation angle is corrected with respect to the reference image having the rotation angle “0 degree”. In this way, the dissimilarity deriving unit 564 prepares an image to be discriminated in which the relative positional deviation with respect to the reference image with the rotation angle “0 degrees” is corrected.

  In the next step S162, the mask image application unit 562 of the determination unit 560 performs mask processing on each of the reference image and the determination target image. In other words, the mask image application unit 562 applies the mask image to each of the reference image and the determination target image. In other words, the mask image application unit 562 performs a mask process on each of the reference image and the determination target image with the rotation angle “0 degrees”. Mask image holding unit 610 outputs mask image data BMD to discrimination unit 560. The mask image application unit 562 applies a mask image based on the sent mask image data BMD to each of the reference image having the rotation angle “0 degrees” and the determination target image.

  In the next step S163, the degree-of-difference deriving unit 564 performs the degree-of-difference DF of the masked image to be discriminated with respect to the masked reference image with the rotation angle “0 degrees” (hereinafter referred to as the masked reference image). Is calculated. The reference image generation unit 510 compares the mask-processed reference image with the mask-processed discriminated image, and calculates a difference DF of the mask-processed discriminating image with respect to the mask-processed reference image. The calculated difference degree DF is stored in a storage area (not shown) of the image storage unit 6.

  In the next step S164, it is determined whether or not the dissimilarity DF is equal to or less than a predetermined threshold value. When the dissimilarity DF is less than or equal to the threshold (DF ≦ threshold), the process proceeds to step S165, where it is determined (match determination) that the discriminated image subjected to mask processing matches the reference image subjected to mask processing. In other words, it is determined that the disk D is a genuine disk. On the other hand, if the dissimilarity DF exceeds the threshold value (DF> threshold value), the process proceeds to step S166, where it is determined that the discriminated image subjected to mask processing does not match the reference image subjected to mask processing (non-coincidence determination). In other words, it is determined that the disk D is a fake disk. In this way, the authenticity determination process for the disc D to be determined in step S8 in FIG. 4 is completed, and the determination result is output from the image processing unit 5 to the control unit 4 as the determination signal IS. After the image processing unit 5 outputs the discrimination signal IS to the control unit 4, the discrimination mode of the disc discrimination device 1 in FIG.

(Modification)
The present invention is not limited to the above-described embodiments, and various modifications can be made. In this embodiment, each time the reference image and the preprocessed image (discriminated image) on the disk D are compared, the mask image is combined with the reference image and the discriminated image. For example, step S7 in FIG. In the mask image generation process, after the mask image is generated by the binarization process in step S132 of FIG. 12, the mask process may be performed on the reference image with the rotation angle “0 degrees”. In this case, as shown in FIG. 15, after generating a mask image in step S209, a mask process is performed in which the mask image is applied to the reference image with the rotation angle “0 degrees” held in the reference image holding unit 606 in step S210. Run. Then, in step S162 of the comparison determination process in FIG. 14, only the non-discrimination image is masked. Note that the processes in steps S201 to S209 in FIG. 15 are exactly the same as the processes in steps 121 to 129 in FIG. In this way, in the mask image generation process in step S7 of FIG. 4, the reference image subjected to the mask process is prepared, so that the reference determination process in step S145 of the authenticity determination process in FIG. It is not necessary to perform mask processing on the image, and the true / false determination process in step S8 in FIG. 4 can be efficiently executed.

  Further, in the authenticity determination process in step S8 in FIG. 4, a mask process for applying a mask image to the reference image with the rotation angle “0 degrees” is performed before the captured image acquisition process in step S142 in FIG. It is also possible. In that case, as shown in FIG. 16, before the captured image acquisition processing in step S243, mask processing is performed on the reference image in step S242. Then, in step S162 of the comparison determination process in FIG. 14, only the masked image is masked. Note that the processes in steps S241, S243, and S244 in FIG. 16 are exactly the same as the processes in steps S141, S142, and S143 in FIG. In this way, the comparison determination in step S245 in FIG. 16 is efficiently performed by preparing the reference image that has been subjected to the mask process in advance before the captured image acquisition process in step S243 of the authenticity determination process in FIG. can do.

DESCRIPTION OF SYMBOLS 1 Disc discriminating device 2 Image acquisition part 3 Imaging timing sensor 4 Control part 5 Image processing part 6 Image storage part 7 Input / output I / F
8 Status Indicator 9 Discrimination Criteria Storage Unit 11 Light Projector 12 Two-Dimensional Imaging Device 21 Surface Light Emitter 22 Light Emitting Element 23 Light Guide Plate 24 Reflective Sheet 25 Diffusion Sheet 26 Half Mirror 31 Disk Transport Path 32 Base Plate 33 Imaging Window 34 Through Optical plate 35 Imaging region 41 Condensing lens 42 Imaging element 500 Preprocessing unit 502 Edge extraction unit 504 Center extraction unit 506 Image extraction unit 510 Reference image generation unit 512 Comparison determination unit 514 Image rotation unit 516 Image integration unit 520 Moire image processing Unit 522 evaluation value derivation unit 524 determination threshold setting unit 526 moire image selection unit 528 moire image integration unit 540 mask image processing unit 542 mask threshold setting unit 544 mask image generation unit 560 determination unit 562 mask image application unit 564 difference degree derivation unit 600 Captured image holding unit 602 Processed image holding unit 604 Input image holding unit 06 Reference image holding unit 608 Moire image holding unit 610 Mask image holding unit D Disk ID Captured image data BD Input image data RD Reference image data PD Processed image data MD Moire image data IMD Integrated moire image data BMD Mask image data DL Transport direction ICS Imaging control signal IS Discrimination signal LCS Lighting control signal TS Timing signal MCS Storage unit control signal PCS Image processing control signal SS State notification instruction signal SLS Discrimination reference data DF Difference EV Evaluation value DI Determination threshold MI Mask threshold

Claims (8)

A disc discriminating apparatus that discriminates the authenticity of the disc to be discriminated by comparing a discriminated image corresponding to the disc to be discriminated with a reference image by excluding a moire area from effective pixels,
A reference image generation unit that generates a reference image by accumulating a plurality of input images corresponding to each of a plurality of discs to be determined as a genuine disc;
A moire image selection unit that selects a plurality of moire images having the moire region from the plurality of input images based on a comparison result between each of the plurality of input images and the reference image;
A mask image generating unit that generates a mask image that excludes the moire region from effective pixels based on a comparison result between the accumulated moire image obtained by integrating the plurality of moire images and the reference image;
A discriminator for discriminating the authenticity of the disc to be discriminated by comparing the input discriminated image and the reference image by applying the mask image;
A disk discrimination device comprising: An evaluation value deriving unit for deriving an evaluation value of matching with respect to the reference image for each of the plurality of input images;
A determination threshold setting unit that sets a determination threshold of the moire image from a plurality of frequency distributions of the evaluation values derived by the evaluation value deriving unit;
Further comprising
The disc determination device according to claim 1, wherein the moire image selection unit selects the moire image by determining each of the evaluation values of the plurality of input images based on the determination threshold.   The disk determination device according to claim 2, wherein the determination threshold setting unit sets the determination threshold based on the frequency distribution having a higher evaluation value than the average value of the frequency distribution.   The mask image generation unit binarizes a difference image between the accumulated moiré image and the reference image, with a value at which the degree of separation in the frequency distribution of the difference pixel value between the accumulated moiré image and the reference image is maximized. The disc discriminating apparatus according to claim 1, wherein the converted image is used as the mask image. A disc discriminating method for discriminating the authenticity of the disc to be discriminated by comparing a discriminated image corresponding to the disc to be discriminated with a reference image by excluding a moire area from effective pixels,
A reference image generation step of generating a reference image by accumulating a plurality of input images corresponding to each of a plurality of discs to be identified as authentic discs;
A moire image selection step of selecting a plurality of moire images having the moire region from the plurality of input images based on a comparison result between each of the plurality of input images and the reference image;
A mask image generation step of generating a mask image for excluding the moire region from effective pixels based on a comparison result between the accumulated moire image obtained by integrating the plurality of moire images and the reference image;
A discrimination process for discriminating the authenticity of the disc to be discriminated by comparing the inputted discriminated image and the reference image by applying the mask image;
Disc discriminating method comprising: An evaluation value deriving step of deriving an evaluation value of matching with the reference image for each of the plurality of input images;
A determination threshold setting step of setting a determination threshold of the moire image from a plurality of frequency distributions of the evaluation values derived in the evaluation value derivation step;
Further comprising
The disc determination method according to claim 5, wherein, in the moire image selection process, the moire image is selected by determining each of the evaluation values of the plurality of input images based on the determination threshold.   The disc determination method according to claim 6, wherein in the determination threshold setting step, the determination threshold is set based on the frequency distribution having a higher evaluation value than the average value of the frequency distribution. In the mask image generation process, the difference image between the accumulated moire image and the reference image is binarized using a value that maximizes the degree of separation in the frequency distribution of the difference pixel value between the accumulated moire image and the reference image as a threshold value. The disc discrimination method according to claim 5, wherein the converted image is used as the mask image.

Images