Authenticity determination system and authenticity determination device

Abstract

To provide structure which can improve determination accuracy related to authenticity determination of a two-dimensional code, by extracting a feature point from a part of a captured image of the two-dimensional code.SOLUTION: Information about a plurality of feature points extracted from a second extraction object range E2 of a captured image of a two-dimensional code 10 is associated with inherent information for authenticity determination recorded on the two-dimensional code 10 as second authenticity feature point information and registered with a server 40. Then, when an image portion equivalent to the second extraction object range E2 in the captured image of the two-dimensional code captured by a capturing unit 23 is cut out as a part code image, the plurality of feature points are extracted from the part code image. Then, second authenticity feature point information associated with the information for authenticity determination read out from the two-dimensional code in which the part code image has been cut out is acquired from the server 40, and authenticity determination is performed about the two-dimensional code captured by the capturing unit 23, on the basis of an extraction result of feature point extraction processing and an acquisition result from the server 40.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an authenticity determination system and an authenticity determination device for determining the authenticity of a two-dimensional code. [Background technology]

[0002] Conventionally, a method has been disclosed in which an image of an individual to be authenticated is captured, scratches, dents, etc. that the individual has in the captured image are extracted as feature points, and the extracted feature points are compared with individual authentication data to authenticate the imaged individual, i.e., to determine whether the imaged individual is a genuine item or not.

[0003] As a technology for authenticity determination using such feature points extracted from a captured image, for example, an individual identification system disclosed in the following Patent Document 1 is known. In this individual identification system, when each feature point of a subject extracted from a captured image by a feature point extraction process is displayed superimposed on the subject in the image, the user adjusts the shooting conditions so that feature points are extracted with a focus on areas where the color of the surface pattern is unlikely to change even after the manufacturing process. This allows accurate identification even if the surface pattern changes between the time of image registration and the time of identification. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-174439 Summary of the Invention [Problem to be solved by the invention]

[0005] Incidentally, there is a method for authenticity determination using a two-dimensional code such as a QR code (registered trademark), which uses authentic feature information on feature points (hereinafter also referred to as authentic feature points) extracted from a captured image of a two-dimensional code (hereinafter also referred to as an authentic code) attached to an authentic product. Specifically, for example, there is a method for obtaining authentic feature information in advance at a stage before distribution and registering it in a server or the like, and performing authenticity determination based on a comparison result between the feature points extracted from a captured image of the two-dimensional code attached to the product to be authenticated and the authentic feature points obtained from the server or the like.

[0006] In such an authenticity determination method, when the number of matching feature points extracted from a captured image of a two-dimensional code and genuine feature points obtained from a server or the like exceeds a predetermined threshold, it can be determined that the captured two-dimensional code is a genuine code and that the article to which the two-dimensional code is affixed is a genuine product. This is because, in a copied two-dimensional code, the printing condition changes due to printing unevenness and the like, so that the number of matching feature points extracted from the captured image and the genuine feature points described above becomes smaller than in the case of a genuine code.

[0007] However, there are cases where a two-dimensional code attached to a genuine product can be counterfeited with high accuracy by scanning the two-dimensional code attached to the genuine product with a high-performance scanner and printing it with a high-performance laser printer, etc. In such cases, since the change in the printing state becomes small, if the number of matching feature points extracted from the captured image of the counterfeit two-dimensional code and the genuine feature points described above exceeds a predetermined threshold, there is a problem that the product is erroneously determined to be genuine.

[0008] The present invention has been made to solve the above-mentioned problems, and its object is to provide a configuration that can improve the accuracy of determining the authenticity of a two-dimensional code by extracting feature points from a portion of a captured image of the two-dimensional code. [Means for solving the problem]

[0009] In order to achieve the above object, the present invention provides A two-dimensional code (10) on which unique information for authenticity determination is recorded, the information indicating that the code is for authenticity determination; an authenticity determination device (20) that determines the authenticity of the two-dimensional code by using an image of the two-dimensional code and information from a registration unit (40); An authenticity determination system (1) comprising: In the registration unit, information regarding a plurality of feature points extracted from a predetermined portion (E2) of the captured image of the two-dimensional code is associated with the authenticity determination information recorded in the two-dimensional code as genuine feature point information and registered; The authenticity determination device includes: An imaging unit (23); an image cutting unit (21) that cuts out an image portion corresponding to the predetermined portion from the captured image of the two-dimensional code captured by the imaging unit as a partial code image; a feature point extraction unit (21) that extracts a plurality of feature points from the partial code image cut out by the image cutout unit; an acquisition unit (21, 27) that acquires from the registration unit the authenticity feature information associated with the authenticity determination information read from the two-dimensional code from which the partial code image is cut out; an authenticity determination unit (21) that determines the authenticity of the two-dimensional code captured by the imaging unit based on the extraction result of the feature point extraction unit and the acquisition result of the acquisition unit; The present invention is characterized by comprising:

[0010] The present invention also provides a method for producing a semiconductor device comprising the steps of: An authenticity determination device (20) for determining the authenticity of a two-dimensional code (10) using an image of the two-dimensional code (10) on which unique authenticity determination information indicating that the code is for authenticity determination and information from a registration unit (40), comprising: In the registration unit, information regarding a plurality of feature points extracted from a predetermined portion (E2) of the captured image of the two-dimensional code is associated with the authenticity determination information recorded in the two-dimensional code as genuine feature point information and registered; An imaging unit (23); an image cutting unit (21) that cuts out an image portion corresponding to the predetermined portion from the captured image of the two-dimensional code captured by the imaging unit as a partial code image; a feature point extraction unit (21) that extracts a plurality of feature points from the partial code image cut out by the image cutout unit; an acquisition unit (21, 27) that acquires from the registration unit the authenticity feature information associated with the authenticity determination information read from the two-dimensional code from which the partial code image is cut out; an authenticity determination unit (21) that determines the authenticity of the two-dimensional code captured by the imaging unit based on the extraction result of the feature point extraction unit and the acquisition result of the acquisition unit; The present invention is characterized by comprising: The symbols in parentheses above indicate the corresponding relationship with the specific means described in the embodiments described later. Effect of the Invention

[0011] In the present invention, information on a plurality of feature points extracted from a predetermined portion of a captured image of a two-dimensional code (authentic code) is associated with unique authenticity determination information recorded in the two-dimensional code as authentic feature point information and registered in a registration unit. Then, when an image portion corresponding to the predetermined portion in the captured image of the two-dimensional code captured by the imaging unit is cut out as a partial code image by an image cutout unit, a plurality of feature points are extracted from this partial code image by a feature point extraction unit. Then, the acquisition unit acquires from the registration unit authentic feature point information associated with the authenticity determination information read from the two-dimensional code from which the partial code image has been cut out, and the authenticity determination unit performs authenticity determination on the two-dimensional code captured by the imaging unit based on the extraction result of the feature point extraction unit and the acquisition result of the acquisition unit.

[0012] When extracting feature points from a captured image of a two-dimensional code, the edge parts of each cell that constitutes the two-dimensional code are areas where the shape is easy to capture, and so the edge parts are easily extracted as feature points. Therefore, when extracting feature points from the entire two-dimensional code, the number of feature points extracted from the edge parts is greater than other parts. As a result, in a copied two-dimensional code, edge parts that are not affected by printing unevenness are easily extracted as feature points, and the feature points extracted in this way are more likely to match the genuine feature points. Therefore, the more edge parts are extracted as feature points, the higher the possibility of erroneously determining that the copied two-dimensional code is a genuine code.

[0013] Therefore, by extracting feature points from the partial code image rather than from the entire two-dimensional code, the number of edge portions present within the extraction target range is reduced, making it possible to extract more portions of printing unevenness caused by duplication as feature points, thereby improving the accuracy of determining the authenticity of two-dimensional codes.

[0014] The image cutting out unit cuts out a partial code image for each captured image of the same two-dimensional code captured multiple times by the imaging unit, and the authenticity determination unit may determine that the two-dimensional code captured by the imaging unit is authentic when the number of matching feature points with the authentic feature point information acquired by the acquisition unit for at least one of the extraction results obtained for each of the multiple partial code images by the feature point extraction unit becomes equal to or exceeds a predetermined threshold value.

[0015] When authenticity is determined using a captured image of a genuine code, if the number of matching feature points falls below the predetermined threshold due to the effects of camera shake during image capture, the code is erroneously determined to be not genuine. For this reason, feature points are extracted from a portion of the code image for each captured image captured multiple times, and if the number of matching feature points with the genuine feature point information for at least one of the extracted results is equal to or greater than the predetermined threshold, the captured two-dimensional code is determined to be genuine. As a result, even if the number of matching feature points falls below the predetermined threshold in some (e.g., 3 out of 10) captured images due to camera shake, the number of matching feature points in the remaining (e.g., 7 out of 10) captured images that are not affected by camera shake is equal to or greater than the predetermined threshold, so that the accuracy of authenticity determination that the code is determined to be genuine can be improved.

[0016] The two-dimensional code may be a QR code with finder patterns arranged at three corners, and the predetermined portion may be set based on the finder patterns. The finder patterns are easy to extract and have relatively few edge portions, so not only can a portion of the code image be accurately cut out, but other portions different from the edge portions can be extracted as more feature points, further improving the accuracy of authenticity determination. [Brief description of the drawings]

[0017] [Figure 1] 1 is an explanatory diagram illustrating a schematic configuration of an authenticity determination system according to a first embodiment. [Diagram 2] FIG. 2(A) is an explanatory diagram illustrating the position of a first extraction target range relative to an image of a two-dimensional code, and FIG. 2(B) is an explanatory diagram illustrating the position of a second extraction target range relative to an image of a two-dimensional code. [Diagram 3] 3A is an explanatory diagram illustrating an image of feature points extracted from the upper left range E2a of the second extraction target range E2, where FIG. 3(A) shows the captured image before the feature points are extracted, and FIG. 3(B) shows the state in which the extracted feature points are superimposed on FIG. 3(A). [Figure 4]13 is an explanatory diagram illustrating a comparison result between a score value for an entire image and a score value for a partial code image. FIG. [Diagram 5] FIG. 5(A) is an explanatory diagram showing another example of the second extraction target range, where FIG. 5(A) shows a state in which the second extraction target range is set to a range other than the finder patterns, FIG. 5(B) shows a state in which the second extraction target range is set to an L-shaped range connecting each finder pattern, FIG. 5(C) shows a state in which the second extraction target range is set to a range connecting the two finder patterns on the left, and FIG. 5(D) shows a state in which the second extraction target range is set to a range connecting the two finder patterns on the top. [Figure 6] 2 is a block diagram illustrating an electrical configuration of the mobile terminal of FIG. 1. [Figure 7] 4 is a flowchart illustrating the flow of an authenticity determination process performed by a mobile terminal in the first embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] [First embodiment] Hereinafter, a first embodiment of an authenticity determining system and an authenticity determining device according to the present invention will be described with reference to the drawings. The authenticity determination system 1 according to this embodiment is a system that performs authenticity determination (individual authentication) of an imaged two-dimensional code (authentic code) by utilizing authenticity feature information related to feature points (authentic feature points) extracted from a captured image of a two-dimensional code (authentic code) attached to an authentic product. The authenticity determination system 1 performs authenticity determination of a two-dimensional code attached to an item, thereby making it possible to perform authenticity determination as to whether or not the item to which the two-dimensional code is attached is an authentic item. An example of an item to which a two-dimensional code is attached for authenticity determination is a packaging box in which a brand-name item is packaged.

[0019] 1, the authenticity determination system 1 is configured as a system in which a two-dimensional code 10 for authenticity determination is attached to an item G to be subjected to authenticity determination, and the two-dimensional code 10 is imaged and read by a mobile terminal 20 functioning as an authenticity determination device, thereby determining the authenticity of the two-dimensional code 10 and the item G. The authenticity determination system 1 includes a feature point extraction device 30 that performs a feature point extraction process to extract a prescribed number of feature points as authentic feature points from the image of the two-dimensional code 10, and a server 40 in which authentic feature point information related to the feature points (authentic feature points) extracted by the feature point extraction device 30 is registered.

[0020] The two-dimensional code 10 according to this embodiment is a QR code formed by arranging a plurality of square light color cells and dark color cells two-dimensionally in a code area 11. Three finder patterns 12a to 12c are arranged as position detection patterns at the three corners of the square code area 11. The two-dimensional code 10 is generated such that unique authenticity determination information indicating that it is for authenticity determination is recorded therein.

[0021] In this embodiment, two types of extraction target ranges are prepared as extraction target ranges for extracting feature points from the captured image of the two-dimensional code 10 by the feature point extraction process: a first extraction target range E1 which is the code region 11 (i.e., the entire two-dimensional code 10) as shown in Fig. 2(A), and a second extraction target range E2 which is a predetermined part of the captured image of the two-dimensional code 10 as shown in Fig. 2(B). In particular, the second extraction target range E2 in this embodiment is separated into three ranges as shown in Fig. 2(B): an upper left range E2a consisting of finder pattern 12a and three cells below and three cells to the right of finder pattern 12a, a lower left range E2b consisting of finder pattern 12b and three cells above and three cells to the right of finder pattern 12b, and an upper right range E2c consisting of finder pattern 12c and three cells below and three cells to the left of finder pattern 12c. For the sake of simplicity, cells in a range different from the second extraction target range E2 are not shown in FIG. 2(B).

[0022] When a two-dimensional code 10, which is an authentic code, is attached to an article G, the feature point extraction device 30 performs the above-mentioned feature point extraction process by imaging the two-dimensional code 10, thereby performing a process for extracting feature points in each of the first extraction target range E1 and the second extraction target range E2 of the captured image of the same two-dimensional code 10. This feature point extraction process obtains authentic feature point information (hereinafter also referred to as first authentic feature point information) regarding the feature points extracted from the first extraction target range E1, and authentic feature point information (hereinafter also referred to as second authentic feature point information) regarding the feature points extracted from the second extraction target range E2 (E2a to E2c). For example, in the upper left range E2a of the second extraction target range E2, feature points are extracted as illustrated in FIG. 3(B) for the captured image of FIG. 3(A). The feature point extraction device 30 may perform the feature point extraction process before the two-dimensional code 10 is attached to the article G, for example, immediately after the two-dimensional code 10 is printed on a label to be attached.

[0023] The feature point extraction device 30 transmits the first genuine feature point information and the second genuine feature point information acquired as described above to the server 40 via the Internet N or the like together with the authenticity determination information recorded in the two-dimensional code 10. Note that the maximum number of feature points extracted from a captured image by the feature point extraction device 30 (e.g., 2000) is determined, and in this embodiment, the maximum value is adopted as the prescribed number for extracting feature points.

[0024] The server 40 registers the first genuine feature information and the second genuine feature information received from the feature point extraction device 30 in the database in such a manner that the information is associated with the authenticity determination information. The server 40 may correspond to an example of a "registration unit."

[0025] Here, the reason for acquiring not only the first genuine feature information but also the second genuine feature information will be explained below. In this embodiment, the authenticity is determined based on a comparison result between feature points extracted from a captured image of a two-dimensional code attached to an article to be authenticated and genuine feature points acquired from the server 40. Specifically, when the number of matches (hereinafter also referred to as a score value) between the feature points extracted from a captured image of the two-dimensional code and the genuine feature points acquired from the server 40 is equal to or greater than a predetermined threshold (hereinafter also referred to as a threshold value Nth) serving as an authenticity determination criterion, it is determined that the captured two-dimensional code is a genuine code and that the article to which the two-dimensional code is attached is a genuine product.

[0026] When extracting feature points from a captured image of a two-dimensional code as described above, the edge parts of each cell constituting the two-dimensional code are easy to capture the shape of, and therefore the edge parts are easily extracted as feature points. Therefore, when extracting feature points from the entire image of the entire two-dimensional code (code area), the number of feature points extracted from the edge parts is greater than that of other parts. As a result, in a two-dimensional code that has been copied and printed (hereinafter also referred to as a copied code), the edge parts that are not affected by printing unevenness are easily extracted as feature points, and the feature points extracted in this way are likely to match the genuine feature points. Therefore, the more edge parts are extracted as feature points, the greater the possibility that the copied code will be erroneously determined to be the genuine code.

[0027] For this reason, in this embodiment, an image portion corresponding to the second extraction target range E2 is cut out as a partial code image from the captured image of the two-dimensional code to be subjected to authenticity determination, and the feature points extracted from this partial code image are compared with each feature point of the second authentic feature point information registered in advance.

[0028] Since the partial code image is within a range of three cells from each of the finder patterns 12a to 12c, the number of edge portions present within the extraction range is reduced compared to when feature points are extracted from the entire image of the two-dimensional code. By extracting feature points from the partial code image in this way, it is possible to extract more feature points from parts with printing irregularities caused by duplication, thereby improving the accuracy of determining the authenticity of the two-dimensional code.

[0029] FIG. 4 is an explanatory diagram for explaining the result of comparing the score value N1 in the whole image with the score value N2 in the partial code image. The score value N1 in the whole image indicates the number of matching feature points extracted from the whole image of the two-dimensional code and the feature points of the first genuine feature point information. The score value N2 in the partial code image indicates the number of matching feature points extracted from the partial code image of the two-dimensional code and the feature points of the second genuine feature point information. In FIG. 4, the number of extracted feature points from the captured image (prescribed number) is 2000, and No. 1 indicates the result of capturing an authentic code, and Nos. 2 to 12 indicate the results of capturing a duplicated code that has been duplicated by a different duplication method. Specific duplication methods for duplicated codes are shown in the notes of FIG. 4.

[0030] Since the number of extracted feature points is 2000, if the threshold value Nth serving as the standard for determining authenticity is set to 400, as can be seen from Figure 4, authenticity determination based on the score value N1 of the entire image will erroneously determine that codes No. 3 and No. 4 are genuine. In particular, since there is not much difference between the score value N1 of No. 1, which is an image of the genuine code, and the score value N1 of No. 3, which is an image of the duplicated code, if the threshold value Nth is set to a value sufficiently high for the score value N1 of each duplicated code, genuine codes may be erroneously determined to be duplicated codes.

[0031] On the other hand, when determining authenticity based on the score value N2 for some code images, the difference between the score value N2 of No. 1 and the score values ​​N2 of No. 3 and No. 4 is sufficiently large that No. 3 and No. 4 are not erroneously determined to be genuine codes.

[0032] In this way, by performing authenticity determination based on the score value N2 of the partial code image, the accuracy of authenticity determination can be improved compared to the case where authenticity determination is performed based on the score value N1 of the entire image. For this reason, in this embodiment, the second genuine feature information used for comparison with each feature point extracted from the partial code image is acquired in advance as described above and registered in the server 40. Note that in this embodiment, the first genuine feature information used for comparison with each feature point extracted from the entire image is also registered in the server 40 at the same time as the second genuine feature information.

[0033] Next, the reason why the second extraction target range E2 is composed of an upper left range E2a based on finder pattern 12a, a lower left range E2b based on finder pattern 12b, and an upper right range E2c based on finder pattern 12c will be explained below with reference to Figures 5(A) to (D).

[0034] For a captured image of a duplicated code in which the score value N1 of the first extraction target range E1 is "1357" and the score value N2 of the second extraction target range E2 is "264", the score value N2 of the other second extraction target range E2 (E2d to E2g) shown in Figs. 5(A) to (D) was calculated. In Fig. 5(A), the second extraction target range E2 is set to the range E2d other than the finder patterns 12a to 12c, and the score value N2 was calculated as "951". In Fig. 5(B), the second extraction target range E2 is set to the L-shaped range E2e connecting the finder patterns 12a to 12c, and the score value N2 was calculated as "808". In Fig. 5(C), the second extraction target range E2 is set to the range E2f connecting the left finder pattern 12a and the finder pattern 12b, and the score value N2 was calculated as "536". In FIG. 5(D), second extraction target range E2 is set to range E2g connecting upper finder pattern 12a and finder pattern 12c, and score value N2 is calculated as "550".

[0035] As can be seen from these results, the score value N2 is smallest when the second extraction target range E2 is composed of the range E2a to E2c. The smaller the score value N2 calculated from the captured image of the duplicated code, the less likely it is that the duplicated code will be erroneously determined to be a genuine code. Therefore, in this embodiment, the second extraction target range E2 is composed of the range E2a to E2c shown in FIG. 2(B).

[0036] Next, the configuration of the mobile terminal 20 that functions as an authenticity determining device will be described with reference to FIG. The mobile terminal 20 is a portable information processing terminal carried by a user who desires to carry out an authenticity determination process using the image capturing result of capturing an image of the two-dimensional code 10. This mobile terminal 20 is configured by installing a predetermined application program for authenticity determination (hereinafter, simply referred to as an authenticity app) distributed and provided by an operating company or the like that operates the authenticity determination system 1 on a smartphone or tablet terminal or the like that has a camera function. The outer hull of this mobile terminal 20 is formed by a housing formed in a substantially thin plate shape, and a display screen capable of displaying information related to the authenticity determination result is disposed in the center of the surface of the housing.

[0037] 6, the mobile terminal 20 includes a control unit 21 that processes image data captured based on pixel signals from an imaging unit 23 configured as a camera equipped with a light receiving sensor (e.g., a C-MOS area sensor, a CCD area sensor, etc.). The control unit 21 is configured mainly with a microcomputer, has a CPU, a system bus, an input / output interface, etc., and functions as an information processing device together with the storage unit 22. The storage unit 22 is configured with known semiconductor memories such as ROM, RAM, and non-volatile memory, and the authenticity application, etc. are stored in the storage unit 22 so that they can be executed by the control unit 21.

[0038] The mobile terminal 20 also includes a touch panel 24, an operation unit 25, a notification unit 26, a communication unit 27, and the like. The touch panel 24 is configured as a known touch panel type display device, and includes a display unit configured as a known display device such as a liquid crystal display, and a transparent operation panel that is superimposed on the display screen of the display unit and functions as a detection unit capable of detecting the range of a pressing operation (contact) on the display screen. The display content of the display unit of the touch panel 24 is controlled by the control unit 21. The operation unit 25 includes a plurality of keys provided on the side of the housing, and is configured to output a signal corresponding to a pressing operation or key operation on the operation panel to the control unit 21. The notification unit 26 includes a light-emitting unit such as an LED, a speaker, a buzzer, and the like, and is configured to perform a predetermined notification corresponding to the result of the authenticity determination process, etc., by controlling the light-emitting state of the light-emitting unit, the voice guidance of the speaker, the sounding state of the buzzer, and the like under the control of the control unit 21.

[0039] The communication unit 27 is configured as an interface for performing data communication with an external device such as a server 40, and functions to perform communication processing in cooperation with the control unit 21. A power supply unit (not shown) is also provided within the housing, and power is supplied to the control unit 21 and various electric components by this power supply unit and a battery.

[0040] Next, in the authenticity determination system 1 configured as described above, the authenticity determination process performed by the mobile terminal 20 when capturing an image of the two-dimensional code attached to the item G to be subjected to authenticity determination and performing authenticity determination on the item G will be described in detail with reference to the flowchart shown in FIG.

[0041] When the authenticity determination process is started on the mobile terminal 20 that has launched the authenticity app, an imaging process is performed using the imaging unit 23 (S101 in FIG. 7), and a decoding process is performed on the captured image to decode the information code (S102).

[0042] If the authenticity determination information is successfully decoded from the captured two-dimensional code (Yes in S103), a partial code image generation process is performed as shown in step S104. In this process, an image portion corresponding to the second extraction target range E2 of the two-dimensional code from the successfully decoded captured image is generated so as to be cut out as the partial code image described above. Note that the control unit 21 that performs the partial code image generation process may correspond to an example of an "image cutout unit."

[0043] Then, in the image storage process shown in step S105, the partial code image cut out as described above and the entire image of the successfully decoded two-dimensional code are associated with the authenticity determination information decoded from the two-dimensional code and stored in memory unit 22.

[0044] Next, a first individual authentication process shown in step S106 is performed. In this process, first, a request based on the authenticity determination information stored in the storage unit 22 is made to the server 40, and first genuine feature information associated with the authenticity determination information is received and acquired from the server 40 via the communication unit 27. Then, a score value N1 is calculated for the feature points extracted from the entire image stored in the storage unit 22 by the feature point extraction process and the genuine feature points of the first genuine feature information acquired from the server 40.

[0045] In the determination process of step S107, individual authentication determination is performed based on the result of comparing the score value N1 calculated from the entire image with a threshold value Nth. If the score value N1 calculated as described above is less than the threshold value Nth, the determination result in the determination process of step S107 is No, a duplication notification process shown in step S110 is performed, and the authenticity determination process ends.

[0046] In the above-mentioned copy notification process, information indicating that the captured two-dimensional code is highly likely to be a copy code (a counterfeit two-dimensional code) is notified using the display on the display screen, the light-emitting state of the light-emitting section, audio guidance from the speaker, the sounding state of the buzzer, etc. A user who receives this notification can easily understand that the captured two-dimensional code is a copy code and that the article G to which the two-dimensional code is affixed is highly likely to be a counterfeit.

[0047] On the other hand, if the score value N1 calculated as described above is equal to or greater than the threshold value Nth (Yes in S107), the second individual authentication process shown in step S108 is performed. In this process, first, a request based on the authenticity determination information stored in the storage unit 22 is made to the server 40, and second genuine feature information associated with the authenticity determination information is received and acquired from the server 40 via the communication unit 27. Then, a score value N2 is calculated for the feature points extracted by the feature point extraction process from the partial code image stored in the storage unit 22 and the genuine feature points of the second genuine feature information acquired from the server 40. The control unit 21 and the communication unit 27 that perform the process of acquiring the second genuine feature information associated with the authenticity determination information from the server 40 may correspond to an example of an "acquisition unit". The control unit 21 that performs the feature point extraction process of extracting a plurality of feature points from the partial code image may correspond to an example of a "feature point extraction unit".

[0048] In the determination process of step S109, individual authentication determination is performed based on a comparison result between the score value N2 calculated from a portion of the code image and a threshold value Nth. If the score value N2 calculated as described above is equal to or greater than the threshold value Nth, the determination process of step S109 is determined as Yes, an authenticity notification process shown in step S111 is performed, and this authenticity determination process ends. If the score value N2 using the second authentic feature information is less than the threshold value Nth (No in S109), the processes of steps S110 and after are performed. The control unit 21 performing the determination process of steps S109 and S107 may correspond to an example of an "authenticity determination unit."

[0049] In the above authenticity notification process, information indicating that the captured two-dimensional code is highly likely to be an authentic code (genuine two-dimensional code) is notified using the display on the display screen, the light-emitting state of the light-emitting part, the voice guidance of the speaker, the sounding state of the buzzer, etc. A user who receives this notification can easily understand that the captured two-dimensional code is an authentic code and that the article G to which the two-dimensional code is affixed is highly likely to be an authentic item.

[0050] As described above, in the authenticity determination system 1 and the mobile terminal 20 according to the present embodiment, information on a plurality of feature points extracted from the second extraction target range E2, which is a predetermined part of the captured image of the two-dimensional code 10, is associated with unique authenticity determination information recorded in the two-dimensional code 10 as second authentic feature point information and registered in the server 40. Then, when an image portion corresponding to the second extraction target range E2 in the captured image of the two-dimensional code captured by the imaging unit 23 is cut out as a partial code image (S104), if the first individual authentication process fails (Yes in S107), a plurality of feature points are extracted from the partial code image (S108). Then, the second authentic feature point information associated with the authenticity determination information read from the two-dimensional code from which the partial code image is cut out is acquired from the server 40, and the authenticity of the two-dimensional code captured by the imaging unit 23 is determined based on the extraction result of the feature point extraction process and the acquisition result from the server 40.

[0051] In this way, by extracting feature points from the partial code image rather than from the entire two-dimensional code 10, the number of edge portions present within the extraction range is reduced, making it possible to extract more portions of printing irregularities caused by duplication as feature points, thereby improving the accuracy of determining the authenticity of the two-dimensional code 10.

[0052] Particularly in this embodiment, the two-dimensional code 10 is a QR code with finder patterns 12a to 12c arranged at three corners, and the second extraction target range E2 is set based on the finder patterns 12a to 12c. The finder patterns 12a to 12c are easy to extract and have relatively few edge parts, so not only can a portion of the code image be accurately cut out, but also other parts different from the edge parts can be extracted more as feature points, further improving the accuracy of authenticity determination.

[0053] As a modification of this embodiment, the two-dimensional code attached to the article G to be subjected to the authenticity determination may be imaged multiple times, and a partial code image may be cut out for each image captured, and the second individual authentication process (S108) may be performed. In this case, if the score value N2 of even one of the partial code images is equal to or greater than the threshold value Nth, the determination process in step S109 is determined as Yes, and the authenticity notification process shown in step S111 above may be performed.

[0054] That is, the same two-dimensional code is captured multiple times by the imaging unit 23, and a partial code image is cut out for each captured image. For at least one of the extraction results obtained in the feature point extraction process for each of the multiple partial code images, if the number of matching feature points (score value N2) with the second genuine feature point information obtained from the server 40 becomes equal to or exceeds a threshold value Nth, the two-dimensional code captured by the imaging unit 23 is determined to be genuine.

[0055] When authenticity is determined based on a captured image of a genuine code, if the number of matching feature points (score value N2) falls below threshold value Nth due to the effects of camera shake during imaging, etc., it will be erroneously determined that the code is not genuine. As a result, even if the score value N2 falls below threshold value Nth in some (e.g., 3 out of 10) captured images due to camera shake, etc., the score value N2 will be equal to or greater than the threshold value in the remaining captured images that are not affected by camera shake, etc. (e.g., 7 out of 10) so that the accuracy of authenticity determination that the code is determined to be genuine can be improved.

[0056] The present invention is not limited to the above-described embodiment, and may be embodied as follows, for example. (1) In the above authenticity determination process, steps S106 and S107 may be omitted, and individual authentication determination (S108) may be performed based on score value N2 calculated from a portion of the code image without calculating score value N1.

[0057] (2) The second extraction target range E2 is not limited to being composed of three ranges (upper left range E2a, lower left range E2b, upper right range E2c) based on the finder patterns 12a to 12c, and may be set, for example, as a range of two cells based on the finder patterns 12a to 12c, or as a range of four cells based on the finder patterns 12a to 12c. Depending on the value of the threshold Nth to be set, the second extraction target range E2 may be set, for example, as shown in Fig. 5(A) to (D), or may be set to be a part of the code region based on a specific pattern (for example, a timing pattern) of a different finder pattern.

[0058] (3) The two-dimensional code 10 is not limited to being configured as a QR code, and may be configured as other code types such as a data matrix code, maxicode, etc. Even in such a configuration, the above-mentioned effects can be achieved by setting a part of the code region as the second extraction target range E2 so as to use as a reference a specific pattern of the two-dimensional code formed by arranging rectangular cells.

[0059] (4) The authenticity determination information, the first authenticity feature information, and the second authenticity feature information of the readable two-dimensional code 10 may be obtained from the server 40 in advance before the start of the authenticity determination process and stored in the storage unit 22. In such a configuration, the authenticity determination process can be performed by using the information stored in the storage unit 22 without communicating with the server 40 each time.

[0060] (5) The authenticity determination device according to the present invention is not limited to being configured as a portable terminal 20 carried by a user, and may be configured as a stationary information processing terminal having the same functions as the portable terminal 20.

[0061] 1 Authenticity determination system 10 2D Code 11 Code Region 12a~12c Finder Patterns 20 Mobile terminal (authentication device) 21 Control unit (image extraction unit, acquisition unit, feature point extraction unit, authenticity determination unit) 23 Imaging unit 27 Communication Department (Acquisition Department) 30 Feature point extraction device 40 Server (Registry Department) E1 First extraction scope E2 Second Extraction Scope G Goods N1,N2 score value Nth Threshold

Claims

1. A two-dimensional code on which unique information for authenticity determination is recorded, the information indicating that the item is for authenticity determination; an authenticity determination device that determines the authenticity of the two-dimensional code by using an image of the two-dimensional code and information from a registration unit; An authenticity determination system comprising: the registration unit registers information about a plurality of feature points extracted from a predetermined portion of the captured image of the two-dimensional code as genuine feature point information in association with the authenticity determination information recorded in the two-dimensional code; The authenticity determination device includes: An imaging unit; an image cropping unit that crops out, as a partial code image, an image portion corresponding to the predetermined portion from the captured image of the two-dimensional code captured by the imaging unit; a feature point extraction unit that extracts a plurality of feature points from the partial code image cut out by the image cutout unit; an acquisition unit that acquires from the registration unit the authenticity feature information associated with the authenticity determination information read from the two-dimensional code from which the partial code image is cut out; an authenticity determination unit that performs authenticity determination on the two-dimensional code captured by the imaging unit based on the extraction result of the feature point extraction unit and the acquisition result of the acquisition unit; An authenticity determination system comprising:

2. The image cropping unit crops out the partial code image for each captured image obtained by capturing the same two-dimensional code multiple times by the imaging unit, The authenticity determination system according to claim 1, characterized in that the authenticity determination unit determines that the two-dimensional code imaged by the imaging unit is authentic when a number of matching feature points with the authentic feature point information acquired by the acquisition unit for at least one of the extraction results of the feature point extraction unit obtained for each of the multiple partial code images becomes equal to or greater than a predetermined threshold.

3. The two-dimensional code is a QR code having finder patterns arranged at three corners, 2. The authenticity determination system according to claim 1, wherein the predetermined portion is set based on the finder pattern.

4. An authenticity determination device that performs authenticity determination of a two-dimensional code by using an image of the two-dimensional code, on which unique authenticity determination information indicating that the two-dimensional code is for authenticity determination, and information from a registration unit, the registration unit registers information about a plurality of feature points extracted from a predetermined portion of the captured image of the two-dimensional code as genuine feature point information in association with the authenticity determination information recorded in the two-dimensional code; An imaging unit; an image cropping unit that crops out, as a partial code image, an image portion corresponding to the predetermined portion from the captured image of the two-dimensional code captured by the imaging unit; a feature point extraction unit that extracts a plurality of feature points from the partial code image cut out by the image cutout unit; an acquisition unit that acquires from the registration unit the authenticity feature information associated with the authenticity determination information read from the two-dimensional code from which the partial code image is cut out; an authenticity determination unit that performs authenticity determination on the two-dimensional code captured by the imaging unit based on the extraction result of the feature point extraction unit and the acquisition result of the acquisition unit; An authenticity determining device comprising:

Images