JP2007034747A - Article ascertaining system, imaging device and article ascertaining method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an article ascertaining system making it hard to produce forged medium and ascertaining the authenticity of the article easily and precisely. <P>SOLUTION: When registering the article 40 such as a card, the article ascertaining system images a plurality of feature images containing the non reproducible and fine characteristic of the surface of a standard article by varying at least either the direction of illuminating light or direction of imaging in the same imaging range 50, registers the plurality of imaged feature images or the feature information included in the plurality of the imaged feature images by respective images of the plurality of feature images, images a plurality of the feature images of the surface of an article for ascertaining under the same condition as that of imaging the standard article when ascertaining whether the article for ascertaining is the registered standard article or not, and judges whether the article for ascertaining is the standard article or not based on the comparison result of the plurality of the imaged feature images and the plurality of the standard article or the comparison result of the features included in the plurality of the imaged feature images and the features included in the plurality of the features images of the standard article. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to an article confirmation apparatus for confirming the authenticity of an article, an imaging apparatus used for confirming the authenticity of an article, and an article confirmation method.

Conventionally, various techniques have been proposed to confirm the authenticity of valuables such as credit cards and important documents. For example, as shown in FIG. 7, the article 60 is illuminated by the light source 54, and the article 60 itself originally has a surface of the article 60 from a predetermined observation area (the shooting range 70 in FIG. 7B). The non-reproducible minute features, for example, the pattern of the fine unevenness on the surface (FIG. 7B is characterized by the convex portion 60a on the article surface and the shadow extending in the opposite direction to the light source 54 with respect to the convex portion 60a. Etc.) is read with the camera 52 or the like and registered in advance, and the minute features on the surface of the article 62 to be confirmed are read with the camera 52 and compared with the features registered in advance. Document confirmation apparatuses and article confirmation apparatuses for confirming the authenticity of the object 60 to be confirmed are known (see, for example, Patent Documents 1 and 2).
JP 2004-153405 A JP 2005-010881 A

  However, in the prior art, the surface of a registered article (authentic medium) 60 (see FIG. 7) is photographed in advance by an external camera, and a camera for confirming the authenticity of the article confirmation apparatus as shown in FIG. If a photograph 64 having a resolution higher than the imaging resolution of 52 is pasted on the unregistered article 62, the feature of the pasted photograph 64 matches the registered feature, and the authenticity of the article to be confirmed cannot be distinguished. There is a problem that the judgment result may be output.

  The present invention has been made to solve the above-described problems, and makes it difficult to create a forged medium, and can easily and accurately confirm the authenticity of an article, an article confirmation apparatus, an imaging apparatus, and an article confirmation. It aims to provide a method.

  In order to achieve the above object, the article confirmation apparatus of the present invention captures the same feature image including minute features that cannot be reproduced on the article surface by varying at least one of the direction of light that illuminates the article surface and the imaging direction. An imaging unit that captures a plurality of ranges, and when a plurality of feature images of a reference article surface are captured by the imaging unit, the captured plurality of feature images or the plurality of captured feature images Registration means for registering feature information indicating the included features for each of the plurality of feature images, and a plurality of feature images on the surface of the article to be confirmed taken by the imaging means under the same conditions as when the reference article was taken A comparison result of comparing each of the plurality of captured feature images with each of the plurality of feature images of the registered reference article, or the plurality of captured feature images. Based on a comparison result between each of the included features and each of the features included in the plurality of feature images of the registered reference item, whether or not the item to be confirmed is the registered reference item Determining means for determining whether or not.

  According to such a configuration, when registering a reference article and confirming an article to be confirmed, the same imaging range can be obtained by changing the direction of light that illuminates the article or by changing the imaging direction. A plurality of feature images can be picked up, and feature images that cannot be reproduced with a single feature image obtained by picking up a reference article with an external image pickup means in the same image pickup range can be obtained in multiple. it can. Further, a comparison result between each of the plurality of feature images to be confirmed and each of the plurality of feature images of the registered reference article, or each of the features included in the plurality of feature images to be confirmed It is difficult to create a counterfeit medium because it is determined whether or not the item to be confirmed is a reference item based on the comparison result with each of the features included in the plurality of feature images of the registered reference item. In addition, the authenticity of the article can be confirmed easily and with high accuracy.

  In addition, the fine feature that cannot be reproduced on the surface of the article here means a fine feature that cannot be reproduced from the outside that can be read from the outside. In the case of an article covered with a transparent protective film (transparent layer), not only the non-reproducible fine features appearing in the transparent layer itself, but also the non-reproducible fine features appearing under the transparent layer Is also included.

  The imaging unit may irradiate the surface of the article with light in the same wavelength range from different directions at different timings in each direction, and may capture a plurality of feature images in synchronization with each irradiation timing. It is also possible to simultaneously irradiate the surface of the article with light in a wavelength range from different directions, and simultaneously capture a plurality of feature images by a plurality of light receiving means corresponding to each wavelength range. In addition, the surface of the article is irradiated with light in a predetermined wavelength range, and a plurality of feature images are simultaneously captured from different directions by a plurality of light receiving means arranged at different positions, or a single light receiving means is moved. A plurality of feature images may be taken from different directions.

  The determination unit is configured such that the number of matches between each of the plurality of captured feature images of the surface of the article to be confirmed and each of the plurality of feature images of the registered reference article exceeds a majority. Or a majority of the number of matches between each of the features included in the plurality of captured feature images of the surface of the article to be confirmed and each of the features included in the plurality of feature images of the registered reference article Can be determined that the item to be confirmed is the registered reference item.

  Thereby, for example, even when the number of coincidence decreases due to noise included in the captured feature image, a change with time of the article, or the like, it is possible to make a correct determination without erroneous determination. Note that the term “match” as used herein includes not only a case where they completely match, but also a case where the degree of similarity is greater than or equal to a predetermined value or the degree of difference is less than a predetermined value.

  In addition, the imaging apparatus according to the present invention, when a plurality of feature images including non-reproducible fine features on the reference article surface are captured, the plurality of captured feature images or the plurality of captured images. Registration means for registering feature information indicating features included in the feature image for each of the plurality of feature images, and a plurality of feature images on the surface of the article to be confirmed are captured under the same conditions as when the reference article is captured. A comparison result of comparing each of the plurality of captured feature images with each of a plurality of feature images of the registered reference article, or included in the plurality of captured feature images Whether or not the item to be confirmed is the registered reference item based on a comparison result between each of the registered features and each of the features included in the plurality of feature images of the registered reference item With judgment means for judging An image pickup device for picking up a feature image used in the device, wherein at least one of the direction of light for illuminating the article surface and the image pickup direction is different, and the same feature image including minute features that cannot be reproduced on the article surface is the same. A plurality of images are captured in the imaging range.

  Such an imaging device makes it difficult to create a counterfeit medium, and the determination device can easily and accurately confirm the authenticity of the article.

  According to the article confirmation method of the present invention, a plurality of feature images including fine features that cannot be reproduced on the reference article surface are made different in at least one of the direction of light that illuminates the reference article surface and the imaging direction. A plurality of feature information indicating features included in a plurality of feature images captured in the first imaging step or a plurality of feature images captured in the first imaging step; A registration step of registering for each feature image of the image, a second imaging step of imaging a plurality of feature images of the surface of the article to be confirmed under the same conditions as when the reference article was imaged in the first imaging step, A comparison result of comparing each of the plurality of feature images captured in the two imaging steps with each of the plurality of feature images of the registered reference article, or a plurality of feature images captured in the second imaging step Included in feature image Whether or not the item to be confirmed is the registered reference item based on a comparison result between each of the features and each of the features included in the plurality of feature images of the registered reference item. A determination step of determining.

  Since the article confirmation method of the present invention also operates in the same manner as the article confirmation apparatus of the present invention, it is difficult to create a forged medium, and the authenticity of the article can be confirmed easily and with high accuracy.

  As described above, according to the present invention, there is an excellent effect that it is difficult to create a forged medium and that the authenticity of an article can be easily and accurately confirmed.

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

[Random pattern]
First, prior to the description of the embodiment of the present invention, the non-reproducible fine unevenness characteristic (hereinafter referred to as random pattern) inherent in the article itself will be described.

  For example, non-woven fabrics are made by intricately intertwining fibers, and none of the patterns by the fibers are the same. That is, a random pattern due to fibers can be observed from the nonwoven fabric. Also, paper is made of intricately intertwined plant fibers, and a random pattern can be observed from paper as well as non-woven fabric. Even if the paper is the same type and the same lot, the pattern is different for each paper.

  Random patterns can also be observed from the surface of carbon-filled black rubber, the surface of ceramics for IC packages, and the surface of coatings (so-called lame coating) of UV-curable paint dispersed with fine metal particles, due to surface microcracks and material particles. Can be observed. Moreover, the random pattern made at the time of surface finishing, such as a hairline process and a sandblast process, can also be observed from the stainless steel material surface. In addition, since the leather has a natural wrinkle and random wrinkles formed on the surface, the wrinkles are observed as a random pattern.

  Thus, random patterns can be observed from various articles. This random pattern is not intentionally created, but is randomized in the formation of the article itself, in the manufacturing process, or after production, and it is unlikely that there are multiple articles with the same pattern. . Also, it seems difficult to deliberately create the same thing. That is, even if the article is manufactured and distributed through the same process, the random pattern is microscopically different for each article. In particular, the random pattern as described above is a microscopic fine pattern, and it is not easy to forge it. In addition, a random pattern of a soft material whose shape is likely to change, such as a rubber surface, a leather surface, or a non-woven fabric, is stable when no external force is applied.

  Note that the detailed description of the random pattern is described in Patent Document 1 (Japanese Patent Laid-Open No. 2004-153405) and Patent Document 2 (Japanese Patent Laid-Open No. 2005-010881) cited above as prior art documents. Further description of the random pattern is omitted here.

  The present invention utilizes a random pattern inherent to an article as described above as information for confirming (identifying / collating) each article. For reading such a fine random pattern, several methods such as a stylus method and an electron microscope observation method are conceivable. From the viewpoint of article protection, it is desirable that the sample is unprocessed and nondestructive. The method using light is excellent in this respect. Hereinafter, an article confirmation apparatus that reads light using a random pattern and confirms the authenticity of the article will be described.

[overall structure]
FIG. 1 is a schematic configuration diagram of an article confirmation device according to an embodiment of the present invention. As shown in FIG. 1, the article confirmation device 10 includes a CPU 12, a RAM 14, a ROM 16, an external I / F (interface) processing device 18, and an internal I / F processing device 20, which are connected to each other via a system bus 32. Has been.

  The CPU 12 executes a program stored in the ROM 16 and controls the operation of the entire article confirmation apparatus 10. In the program stored in the ROM 16, an image including a random pattern on the surface of the article to be registered (hereinafter referred to as a feature image) is imaged, and a feature amount indicating the feature of the random pattern on the article surface is extracted and registered. To capture a feature image of the surface of the article to be confirmed and the object to be confirmed, extract a feature amount indicating a random pattern feature of the article surface from the captured feature image, and compare the feature amount with a pre-registered feature amount A confirmation processing program for determining authentication / non-authentication is included.

  The random pattern on the surface of the article here refers to a fine feature that cannot be reproduced of the article that is visible from the outside. For example, in the case of an article that is covered with a transparent protective film to the extent that fine features of the lower layer appear to be imageable, the non-reproducible fine features appearing on the transparent protective film itself and transparent It includes both features of non-reproducible fine features appearing under the protective film. Specifically, a card such as a credit card that is currently widely used in financial institutions, for example, has a transparent layer such as a hard coat affixed to a paint on which a lamellar fine tint pattern appears, for example. Types are widely used. Therefore, in the case of such an article, both a fine random pattern such as irregularities appearing on the protective film itself and a fine ground pattern (random pattern) below the protective film can be included.

  In the present embodiment, as an item to be registered and confirmed, a magnetic card (hereinafter referred to as a card) such as a cash card or a credit card in which a tape-like (striped) magnetic recording medium is attached to a plastic card is taken as an example. explain.

  The RAM 14 is a work memory, and includes an area that temporarily stores captured feature images, data indicating extracted feature amounts, data indicating feature amounts acquired from the external device 34, and the like.

  The external I / F processing device 18 is an interface for exchanging data with the external device 34. The article confirmation apparatus 10 transmits data indicating the feature amount of the random pattern on the article surface or causes the external I / F processing apparatus 18 to register the article to be registered in the external apparatus 34 or the external I / F processing apparatus 18. The data indicating the feature amount of the registered article is received from the external apparatus 34 for use in the confirmation process in the article confirmation apparatus 10 via the / F processing apparatus 18.

  A light source unit 22, a camera 24, a magnetic head control device 26, and a card transport device 30 are connected to the internal I / F processing device 20.

  The light source unit 22 includes four light sources: a first light source 22a, a second light source 22b, a third light source 22c, and a fourth light source 22d (see FIG. 2). As shown in FIG. 2, the light sources 22 a to 22 d are arranged so as to illuminate the card 40 by irradiating light from different directions, respectively, irradiating light in the same wavelength region, and inserted into the article confirmation apparatus 10. Illuminate the card 40. The lighting timing (light irradiation timing) of each of the light sources 22 a to 22 d is controlled by the CPU 12 via the internal I / F processing device 20. For each of the light sources 22a to 22d, for example, an LED, a halogen lamp, a fluorescent lamp, a xenon discharge tube, or the like can be used.

  The camera 24 captures a feature image from a predetermined imaging range 50 on the surface of the card 40 illuminated by the light emitted from the light source unit 22. In the present embodiment, the camera 24 and the imaging range 50 of the camera 24 are fixed. The imaging timing of the camera 24 is controlled by the CPU 12 via the internal I / F processing device 20.

  A magnetic head 28 is connected to the magnetic head controller 26. The magnetic head 28 is controlled by the magnetic head control device 26, and when the card 40 is inserted from an insertion port (not shown) and conveyed to the reading position of the magnetic head 28, information is read from the magnetic recording medium affixed to the card 40. read out.

  The card transport device 30 includes a transport roller 30a and a motor 30b. When the card 40 is inserted from an insertion port (not shown), the transport roller 30a is rotated to transport the inserted card 40 to a predetermined position, and the processing using the inserted card 40 is completed. Then, the transport roller 30a is rotated in the reverse direction so that the processed card 40 is transported and discharged from the insertion slot.

  In addition, when the external device 34 that exchanges data with the article confirmation device 10 receives data indicating the identification code and feature amount of the card 40 from the article confirmation device 10, Is stored in the database in association with each other, and when a request for feature quantity data is received from the article confirmation device 10, the data indicating the feature quantity is read from the database in response to the request, and the article confirmation apparatus 10 to send.

[Operation of article confirmation device]
Next, the operation of the article confirmation device 10 will be described. In order to determine the authenticity of the card 40 by the article confirmation device 10, it is necessary to register in advance the characteristics of the random pattern that the real card 40 has. With reference to FIG.2 and FIG.3, the registration process performed in the goods confirmation apparatus 10 is demonstrated.

  When the registration target card 40 is inserted from an insertion port (not shown), the card transport device 30 transports the card 40 to the reading position of the magnetic head 28. At this time, the registration processing program shown in FIG. 3 is started.

  In step 100, the magnetic head controller 26 controls the magnetic head 28 to read out and obtain the identification code from the magnetic recording medium of the card 40. This identification code is a unique code for identifying the card 40 and is recorded in advance on the magnetic recording medium. After obtaining the identification code, the card transport device 30 transports the card 40 to a predetermined position.

  Subsequently, in step 102, the first light source 22a is turned on as shown in FIG. 2A, and the surface of the card 40 is illuminated with light from the direction of the first light source 22a. The light from the first light source 22a travels along the light path 36a, illuminates the surface of the card 40 including the convex portion 40a as a part of the random pattern, and the convex portion on the downstream side of the light path 36a with respect to the convex portion 40a. Create a shadow of 40a. Note that the direction and shape of the shadow depend not only on the uneven shape on the surface of the card 40 but also on the direction of the light to be illuminated (including the incident angle of light on the surface of the card 40). The feature image of the imaging range 50 on the surface of the card 40 is captured by the camera 24 with the surface of the card 40 illuminated in this way. After imaging, the first light source 22a is turned off.

  In step 104, a subroutine for extracting a feature amount from the image data of the captured feature image is executed. FIG. 4 is a flowchart showing the flow of processing of the feature amount extraction subroutine. Note that a conventionally known technique can be employed for extracting the feature amount. However, in this embodiment, Patent Document 1 (Japanese Patent Laid-Open No. 2004-153405) and Patent Document previously cited as prior art documents are used. 2 (Japanese Patent Laid-Open No. 2005-010881) is applied.

  First, in step 150, the captured feature image is divided (quantized) into meshes of appropriate size (number of meshes d = vertical M × horizontal N), and each mesh is represented by a certain density value (density level q). (Sampling) and converting into image data of a mosaic image.

  In step 152, the image data after quantization sampling is set to a vector of x = (x1, x2,... Xd) t (t represents transposition), where jj mesh density is xj. (Feature vector). This feature vector is used as a feature amount.

  Each element of this feature vector gives the density of the corresponding image area. The obtained pattern is represented as one point on the feature space spanned by the feature vector. As described above, since each article has a random pattern that differs microscopically, the feature vector also represents a unique feature. That is, the feature of the random pattern of each article can be represented by this feature vector. Instead of the feature vector, a variance-covariance matrix or correlation matrix may be obtained from all the vectors, and this may be used as the feature quantity.

  Data indicating a feature amount calculated from a feature image captured by turning on the first light source 22a is referred to as data RD1.

  After the feature quantity extraction subroutine at step 104 is completed, the routine proceeds to step 106 where the second light source 22b is turned on as shown in FIG. 2B, and the surface of the card 40 is moved from the direction of the second light source 22b. Illuminate with light. The light from the second light source 22b travels along the light path 36b, illuminates the surface of the card 40 including the convex portion 40a as a part of the random pattern, and the convex portion on the downstream side of the light path 36b with respect to the convex portion 40a. Create a shadow of 40a. The feature image of the imaging range 50 on the surface of the card 40 is captured by the camera 24 with the surface of the card 40 illuminated in this way. After imaging, the second light source 22b is turned off.

  In step 108, a subroutine for extracting a feature amount from image data of a feature image captured by turning on the second light source 22b is executed in the same manner as described above. Data indicating a feature amount calculated from a feature image captured by turning on the second light source 22b is referred to as data RD2.

  Subsequently, in step 110, the third light source 22c is turned on as shown in FIG. 2C, and the surface of the card 40 is illuminated with light from the direction of the third light source 22c. The light from the third light source 22c travels along the light path 36c, illuminates the surface of the card 40 including the convex part 40a as a part of the random pattern, and the convex part 40a downstream of the light path 36c with respect to the convex part 40a. To create a shadow. The feature image of the imaging range 50 on the surface of the card 40 is captured by the camera 24 with the surface of the card 40 illuminated in this way. After imaging, the third light source 22c is turned off.

  In step 112, a subroutine for extracting a feature amount from image data of a feature image captured by turning on the third light source 22c is executed in the same manner as described above. Data indicating a feature amount calculated from a feature image captured by turning on the third light source 22c is referred to as data RD3.

  Subsequently, in step 114, the fourth light source 22d is turned on as shown in FIG. 2D, and the surface of the card 40 is illuminated with light from the direction of the fourth light source 22d. The light from the fourth light source 22d travels along the light path 36d, illuminates the surface of the card 40 including the convex part 40a as a part of the random pattern, and the convex part 40a downstream of the light path 36d with respect to the convex part 40a. To create a shadow. The feature image of the imaging range 50 on the surface of the card 40 is captured by the camera 24 with the surface of the card 40 illuminated in this way. After imaging, the fourth light source 22d is turned off.

  In step 116, the subroutine for extracting the feature amount from the image data of the feature image captured by turning on the fourth light source 22d is executed in the same manner as described above. Data indicating the feature amount calculated from the feature image captured by turning on the fourth light source 22d is referred to as data RD4.

  In step 118, as described above, the light sources 22a to 22d are turned on sequentially (at different timings) to illuminate the card 40 from different directions, and data RD1 indicating the feature amount for each feature image captured in synchronization with each lighting timing. ˜RD4 are registered in the external device 34 in association with the identification code read from the magnetic recording medium of the card 40.

  Next, an operation for confirming the authenticity of the confirmation target card 40 will be described. FIG. 5 is a flowchart showing the flow of the confirmation processing program executed in the article confirmation apparatus 10.

  When the card 40 to be confirmed is inserted from an insertion port (not shown), the card transport device 30 transports the card 40 to the reading position of the magnetic head 28. At this time, the confirmation processing program shown in FIG. 5 is started.

  In step 200, the magnetic head controller 26 controls the magnetic head 28 to read out and obtain the identification code from the magnetic recording medium of the card 40. After obtaining the identification code, the card transport device 30 transports the card 40 to a predetermined position.

  In step 202, data RD <b> 1 to RD <b> 4 indicating feature amounts registered corresponding to the acquired identification code are acquired from the external device 34.

  In step 204, as in the registration process, the first light source 22a is turned on as shown in FIG. 2A, and the surface of the card 40 is illuminated with light from the direction of the first light source 22a. In the processing, a feature image in the same imaging range 50 as the imaging range in which the registration target card 40 is imaged is captured by the camera 24.

  In the confirmation process, when the same imaging range as that in the registration process is imaged, accurate alignment is necessary. However, the alignment method is not particularly limited. The methods described in Patent Document 1 (Japanese Patent Application Laid-Open No. 2004-153405) and Patent Document 2 (Japanese Patent Application Laid-Open No. 2005-010881) mentioned above can be applied. Further description of this alignment method is omitted here.

  In step 206, a subroutine for extracting a feature amount from image data of a feature image captured by turning on the first light source 22a is executed in the same manner as described above. Data indicating the feature amount calculated here is referred to as data D1.

  In step 208, it is determined whether or not the data RD1 and the data D1 match. Here, if the degree of similarity between the data RD1 and the data D1 is equal to or greater than a threshold value, it is determined that they match. For calculating the degree of similarity, a conventionally known technique can be employed. However, in this embodiment, Patent Document 1 (Japanese Patent Laid-Open No. 2004-153405) and Patent Document previously cited as prior art documents are used. 2 (Japanese Patent Laid-Open No. 2005-010881) is applied, and the distance between the feature quantity (feature vector) indicated by the data RD1 and the feature quantity (feature vector) indicated by the data D1 is calculated and similar. Find the degree. The closer the calculated distance, the higher the similarity (they are similar). Naturally, the distance may be obtained by reducing the dimension of the feature space by KL (Karhunen-Loeve) expansion or the like.

  Here, as the distance to be calculated as the similarity, it is possible to use a distance used in statistical discriminant analysis or cluster analysis, for example, city distance, Euclidean distance, standardized Euclidean distance, Minkowski distance, Mahalanobis distance, etc. Yes, by Masakatsu Murakami: Behavioral metric series "Science of Shinji" Asakura Shoten, 1996). The former four distances are all obtained as the distance between the feature vector of the article to be confirmed and the registered feature vector of the genuine article. The Mahalanobis distance is calculated from the feature vector of the article to be confirmed, the feature vector (average vector) of the registered genuine article, and the inverse matrix of the feature matrix (variance covariance matrix or correlation matrix).

  Note that the threshold value to be compared with the similarity is preferably set with a predetermined allowable range in consideration of a quantization sampling error or the like. That is, the size of the threshold value may be selected as appropriate according to the request for strict similarity determination or sweetening. Further, the allowable range may be varied depending on the type of article to be registered (confirmed).

  If it is determined in step 208 that the data RD1 and the data D1 do not match, the process proceeds to step 232, and the card 40 to be confirmed is determined to be unauthenticated (fake).

  On the other hand, if it is determined in step 208 that the data RD1 and the data D1 match, the process proceeds to step 210.

  In step 210, as in the registration process, the second light source 22b is turned on as shown in FIG. 2B, and the surface of the card 40 is illuminated with light from the direction of the second light source 22b. A feature image of the imaging range 50 on the surface is captured by the camera 24.

  In step 212, a subroutine for extracting a feature amount from image data of a feature image captured by turning on the second light source 22b is executed in the same manner as described above. Data indicating the feature amount calculated here is referred to as data D2.

  In step 214, it is determined whether or not the data RD2 and the data D2 match. The determination method is the same as the method in step 208 described above.

  If it is determined in step 214 that the data RD2 and the data D2 do not match, the process proceeds to step 232, and the card 40 to be confirmed is determined to be unauthenticated (fake).

  On the other hand, if it is determined in step 214 that the data RD2 and the data D2 match, the process proceeds to step 216.

  In step 216, as in the registration process, the third light source 22c is turned on as shown in FIG. 2C, and the surface of the card 40 is illuminated with light from the direction of the third light source 22c. A feature image of the imaging range 50 on the surface is captured by the camera 24.

  In step 218, the subroutine for extracting the feature amount from the image data of the feature image captured by turning on the third light source 22c is executed in the same manner as described above. Data indicating the feature amount calculated here is referred to as data D3.

  In step 220, it is determined whether or not the data RD3 and the data D3 match. The determination method is the same as the method in step 208 described above.

  If it is determined in step 220 that the data RD3 and the data D3 do not match, the process proceeds to step 232, and the card 40 to be confirmed is determined to be unauthenticated (fake).

  On the other hand, if it is determined in step 220 that the data RD3 and the data D3 match, the process proceeds to step 222.

  In step 222, as in the registration process, the fourth light source 22d is turned on as shown in FIG. 2D, and the surface of the card 40 is illuminated with light from the direction of the fourth light source 22d. A feature image of the imaging range 50 on the surface is captured by the camera 24.

  In step 224, a subroutine for extracting the feature amount from the image data of the feature image captured by turning on the fourth light source 22d is executed in the same manner as described above. Information indicating the feature amount calculated here is referred to as data D4.

  In step 226, it is determined whether data RD4 and data D4 match. The determination method is the same as the method in step 208 above.

  If it is determined in step 226 that the data RD4 and the data D4 do not match, the process proceeds to step 232, where the card 40 for the confirmation process is determined to be unauthenticated (fake).

  On the other hand, if it is determined in step 226 that the data RD4 and the data D4 match, the process proceeds to step 230, where it is determined that the confirmation processing card 40 is genuine (registered card). Certify.

  When the determination result is obtained in step 230 and step 232, the determination result may be transmitted to the external device 34. When the article confirmation apparatus 10 is provided with a display device, the display device The determination result may be displayed on the screen.

  As described above, during the registration process, the light sources 22a to 22d are sequentially turned on (at different timings) to illuminate the card 40 from different directions, and include a random pattern on the surface of the card 40 in synchronization with each lighting timing. A plurality of images are captured in the same imaging range, a feature amount is calculated from each feature image, and is registered for each feature image. At the time of the confirmation process, the characteristics of the card 40 to be confirmed under the same imaging conditions as at the registration process A plurality of images are captured, a feature amount is calculated from each feature image, and the calculated feature amount is compared with a feature amount registered for each feature image during registration processing to determine authentication / non-authentication Thus, there is an effect that it is difficult to create a forged medium. That is, during the registration process and the confirmation process, a plurality of feature images are captured by changing the direction of light that illuminates the article (the card 40 in the above) in the same imaging range. Feature quantities that cannot be reproduced with one image can be obtained in multiple for one imaging range. As a result, even if a single image captured by an external camera is pasted on the counterfeit medium, an image that matches a plurality of registered feature quantities cannot be reproduced, making it difficult to create the counterfeit medium. Further, since a plurality of feature images are captured and registered and authenticated, the authenticity of the card 40 can be confirmed easily and with high accuracy.

  In the above-described embodiment, the card to be confirmed when it is determined in the confirmation process that all of the data D1 to D4 indicating the feature amount match the data RD1 to RD4 registered in the external device 34. The example in which 40 is authentic (registered card) and authenticated is described. However, the present invention is not limited to this, and a majority of the data D1 to D4 indicating the feature amount is registered in the external device 34. When it is determined that the data matches the data RD1 to RD4, the authentication target card 40 may be determined to be authentic (registered card) and authenticated.

  In FIG. 6, when it is determined that the majority of the data D1 to D4 indicating the feature values match the data RD1 to RD4, it is determined that the confirmation target card 40 is genuine (registered card). It is a flowchart which shows the flow of the confirmation process program in the case of authenticating.

  In FIG. 6, steps that perform the same processing as in FIG. 5 are assigned the same step numbers as in FIG. 5, and descriptions thereof are omitted. Further, in this program, n is used as a variable for counting the number of matches, and although not shown, first, the variable n is reset (n is set to 0) and then the following processing is executed.

  The processing from step 200 to step 206 is the same as that in FIG. In step 208, it is determined whether or not the data RD1 and the data D1 match in the same manner as described above. If it is determined that they match, n is incremented by 1 in step 209. The process proceeds to step 210.

  On the other hand, if it is determined in step 208 that the data RD1 and the data D1 do not match, the process of step 209 is skipped and the process proceeds to step 210.

  The processing from step 210 to step 212 is the same as in FIG. In step 214, it is determined whether or not the data RD2 and the data D2 match in the same manner as described above. If it is determined that they match, in step 215, n is incremented by 1, Control goes to step 216. On the other hand, if it is determined in step 214 that the data RD2 and the data D2 do not match, the process of step 215 is skipped and the process proceeds to step 216.

  The processing from step 216 to step 218 is the same as that in FIG. In step 220, it is determined whether or not the data RD3 and the data D3 match in the same manner as described above. If it is determined that they match, in step 221, n is incremented by 1, Control goes to step 222. On the other hand, if it is determined in step 220 that the data RD3 and the data D3 do not match, the process of step 221 is skipped and the process proceeds to step 222.

  The processing from step 222 to step 224 is the same as in FIG. In step 226, it is determined whether or not the data RD4 and data D4 match in the same manner as described above. If it is determined that they match, in step 227, n is incremented by 1, Control goes to step 228. On the other hand, if it is determined in step 226 that the data RD4 and the data D4 do not match, the process of step 227 is skipped and the process proceeds to step 228.

  In step 228, it is determined whether n exceeds a majority. In the present embodiment, at the time of registration and confirmation, the feature amount is calculated by capturing four feature images with different light directions, so when n exceeds 2 (n is 3 or 4). A), and when n is 2 or less, a negative determination is made. If it is determined that n exceeds a majority, the process proceeds to step 230, where it is determined that the card 40 to be confirmed is genuine (registered card) and is authenticated. On the other hand, if n is determined to be less than or equal to the majority, the process proceeds to step 232, and the confirmation target card 40 is determined to be unauthenticated (fake).

  Even in the case where the confirmation process is performed in this manner, it is difficult to create a forged card and the authenticity of an article can be confirmed easily and with high accuracy, as described above.

  In the above-described embodiment, an example has been described in which the feature amount is calculated by capturing four feature images with different light directions at the time of registration and confirmation. However, two or more feature images are captured. If it is, it will not specifically limit.

  Moreover, although the said embodiment demonstrated the example which illuminates the card | curd 40 surface from four directions and changes the direction of the light which illuminates the card | curd 40 surface, it illuminates by varying the incident angle of the light with respect to the card | curd 40 surface. Also good.

  Moreover, although the said embodiment demonstrated the example which lights the some light source 22a-22d arrange | positioned in a different position at a different timing, and illuminates the card | curd 40 surface from the direction of a different light, It is limited to this. Instead, a single light source may be movably provided, and the card 40 may be illuminated from different light directions by moving the light source. Also by this, it is possible to capture a plurality of different feature images in the same imaging range, making it difficult to create a forged medium, and confirming the authenticity of the card 40 easily and with high accuracy.

  In the above embodiment, an example in which a plurality of feature images are picked up by changing the direction of light that illuminates the card 40 has been described. However, the present invention is not limited to this, and a plurality of features are provided by changing the shooting direction. An image may be taken. For example, with respect to the surface of the card 40, the feature image captured from a high position and the feature image captured from a low position have different unevenness and shade shapes. Therefore, it is possible to capture a plurality of different feature images in the same imaging range even by changing the imaging direction. In the case of changing the imaging direction, the imaging target card 40 may be moved to change the angle and direction to sequentially capture images, or the camera 24 may be moved to sequentially capture images. Alternatively, the card 40 may be imaged by arranging a plurality of cameras 24 so that the imaging directions are different (at different positions). In addition, when imaging with a plurality of cameras 24, a plurality of feature images can be simultaneously captured.

  In addition, a plurality of feature images may be picked up with different wavelength ranges of light. For example, if a plurality of light sources that irradiate light in different wavelength ranges are provided at different positions and a plurality of cameras having image sensors corresponding to the respective wavelength ranges are provided corresponding to the respective wavelength ranges, A plurality of feature images can be taken simultaneously by lighting a plurality of light sources simultaneously and illuminating the surface of the card 40 from different directions.

  If a plurality of different feature images can be obtained for the same imaging range, a combination of the above methods may be used to change both the direction of light and the imaging direction to capture a plurality of feature images.

  Also, in the above embodiment, when comparing the registered feature quantity (feature vector) and the feature quantity to be confirmed (feature vector), the similarity is judged based on the distance and the two match. However, it may be determined from the angle formed by the registered feature vector and the feature vector to be confirmed.

  In the above-described embodiment, the example in which the feature amount is extracted and registered during the registration process has been described. However, the captured feature image is registered as it is without extracting the feature amount during the registration process, and the feature image is registered during the confirmation process. The registered feature image may be read to extract the feature amount, and compared with the feature amount of the feature image to be confirmed.

  Furthermore, a feature image can be registered instead of the feature amount, and the similarity can be obtained by comparing the registered feature image with the feature image to be confirmed (image matching method). In addition to comparing feature images in real space for identification and collation, the feature images may be converted to the frequency domain by two-dimensional Fourier transform and compared in Fourier space. In this case, the feature image obtained from the card 40 registered in advance and the feature image obtained from the card 40 to be confirmed are synthesized in Fourier space, and the correlation intensity image is obtained by inverse Fourier transform, and the peak The similarity between two images can be evaluated from the value. For example, when the magnitude of the amplitude peak is equal to or greater than a predetermined threshold, it can be determined that the registered feature quantity and the feature quantity to be confirmed are similar (matched).

  In the above embodiment, the example in which the registration target card 40 is registered by storing the data indicating the feature amount in the external device 34 has been described. However, the feature amount and the feature image are stored in the article confirmation device 10. A storage device may be provided and stored in this storage device.

  Furthermore, the article confirmation apparatus 10 is connected to the imaging apparatus having an imaging unit that illuminates the card 40 and captures a characteristic image, and the imaging apparatus is connected to the imaging apparatus via a communication line or a cable and is captured by the imaging apparatus. You may comprise with the processing apparatus which performs a registration process and a confirmation process using an image. Specifically, the imaging device captures a plurality of feature images on the surface of the card 40 with different light directions or imaging directions, and transmits the captured feature images to the processing device. In the registration process, the processing device calculates a feature value from the feature image of the registration target card 40 received from the imaging device in the same manner as in the above embodiment, and stores data indicating the feature value in a database or the like. In the confirmation process, a feature amount is calculated from a plurality of feature images of the confirmation target card 40 received from the imaging device in the same manner as in the above embodiment, and the calculation result and a feature amount of the card 40 registered in advance are calculated. The authenticity of the card 40 to be confirmed is determined by comparing data for each of a plurality of feature images indicating Further, the process up to extraction of the feature amount may be performed on the imaging apparatus side. Even with such a configuration, the same operational effects as the above-described embodiment can be obtained.

  Further, in the above-described embodiment, as an article for confirming authenticity, a card such as a credit card or a cash card has been described as an example. However, the present invention is not limited to this, and the article itself is not made intentionally. Any article that has a fine random pattern that is randomly created in the manufacturing process or after manufacturing, and that is not easily changed in shape without external force applied, is related to the present invention. The authenticity can be confirmed using the article confirmation apparatus, the imaging apparatus, and the article confirmation method.

1 is a schematic configuration diagram of an article confirmation device according to an embodiment of the present invention. (A)-(D) are explanatory drawings explaining a mode that the card | curd of registration object or confirmation object is illuminated by each of the four light sources arrange | positioned in a different position. It is a flowchart which shows the flow of a process of a registration process program. It is a flowchart which shows the flow of a process of a feature-value extraction subroutine. It is a flowchart which shows the flow of a confirmation process program. It is a flowchart which shows the modification of a confirmation process program. It is explanatory drawing explaining the conventional document confirmation apparatus and the goods confirmation apparatus, (A) is a side view of goods, (B) is a top view of goods. It is explanatory drawing explaining the problem in the conventional document confirmation apparatus and the goods confirmation apparatus, (A) is a side view of the forged goods, (B) is a top view of the forged goods.

Explanation of symbols

10 article confirmation device 12 CPU
14 RAM
16 ROM
18 External I / F processing device 20 Internal I / F processing device 22 Light source units 22a to 22d Light source 24 Camera 34 External device 40 Card 50 Imaging range

Claims (7)

Imaging means for imaging a plurality of feature images including fine features that cannot be reproduced on the article surface by varying at least one of the direction of light that illuminates the article surface and the imaging direction;
When a plurality of feature images of the reference article surface are picked up by the image pickup means, the plurality of feature images picked up or feature information indicating features included in the picked up feature images Registration means for registering each feature image;
When a plurality of feature images on the surface of the article to be confirmed are picked up by the image pickup unit under the same conditions as when the reference article is picked up, each of the picked up feature images and the registered reference A comparison result obtained by comparing each of the plurality of feature images of the article or each of the features included in the plurality of captured feature images and included in the plurality of feature images of the registered reference article Determining means for determining whether or not the item to be confirmed is the registered reference item based on a comparison result with each of the features;
An article confirmation apparatus including:   The article confirmation apparatus according to claim 1, wherein the imaging unit irradiates the surface of the article with light in the same wavelength range from different directions at different timings in each direction, and captures a plurality of characteristic images in synchronization with the irradiation timings.   2. The article confirmation apparatus according to claim 1, wherein the imaging means simultaneously irradiates the article surface with light in different wavelength ranges from different directions, and simultaneously takes a plurality of feature images by a plurality of light receiving means corresponding to the respective wavelength ranges. .   The imaging means irradiates the surface of the article with light of a predetermined wavelength region, and simultaneously picks up a plurality of feature images from different directions by a plurality of light receiving means arranged at different positions, or a single light receiving means. The article confirmation apparatus according to claim 1, wherein a plurality of feature images are taken from different directions by being moved.   The determination means, when the number of matches between each of the plurality of captured feature images of the confirmation target article surface and each of the plurality of feature images of the registered reference article exceeds a majority, Alternatively, the number of matches between each of the features included in the plurality of captured feature images of the surface of the article to be confirmed and each of the features included in the plurality of feature images of the registered reference article is a majority. The article confirmation device according to any one of claims 1 to 4, wherein when the number exceeds, the article to be confirmed is determined to be the registered reference article. When a plurality of feature images including non-reproducible fine features on the surface of the reference article are captured, the plurality of captured feature images or features indicating the features included in the captured feature images Registration means for registering information for each of the plurality of feature images, and when a plurality of feature images on the surface of the article to be confirmed are captured under the same conditions as when the reference article is captured, the plurality of captured images A comparison result of comparing each of the feature images and each of the plurality of feature images of the registered reference article, or each of the features included in the plurality of captured feature images and the registered Determination provided with determination means for determining whether or not the article to be confirmed is the registered reference article based on a comparison result with each of the features included in the plurality of feature images of the reference article Feature images used in the device An imaging apparatus for imaging,
An imaging apparatus that captures a plurality of feature images including fine features that cannot be reproduced on an article surface by changing at least one of a direction of light that illuminates the article surface and an imaging direction. A first imaging step of imaging a plurality of feature images including fine features that cannot be reproduced on the reference article surface by changing at least one of the direction of light that illuminates the reference article surface and the imaging direction; ,
A registration step of registering, for each of the plurality of feature images, feature information indicating features included in the plurality of feature images captured in the first imaging step or the plurality of feature images captured in the first imaging step. When,
A second imaging step of imaging a plurality of characteristic images of the surface of the article to be confirmed under the same conditions as when the reference article was imaged in the first imaging step;
A comparison result of comparing each of the plurality of feature images captured in the second imaging step with each of the plurality of feature images of the registered reference article, or a plurality of images captured in the second imaging step Based on the comparison result between each of the features included in the feature images and each of the features included in the plurality of feature images of the registered reference article, the article to be confirmed is A determination step of determining whether the item is an article;
An article confirmation method including:

Images