WO2025041187A1 - 処理装置 - Google Patents

処理装置 Download PDF

Info

Publication number
WO2025041187A1
WO2025041187A1 PCT/JP2023/029805 JP2023029805W WO2025041187A1 WO 2025041187 A1 WO2025041187 A1 WO 2025041187A1 JP 2023029805 W JP2023029805 W JP 2023029805W WO 2025041187 A1 WO2025041187 A1 WO 2025041187A1
Authority
WO
WIPO (PCT)
Prior art keywords
image data
unit
product
processing
search
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/JP2023/029805
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
永記 石寺
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NEC Corp
Original Assignee
NEC Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NEC Corp filed Critical NEC Corp
Priority to PCT/JP2023/029805 priority Critical patent/WO2025041187A1/ja
Priority to JP2025541150A priority patent/JPWO2025041187A1/ja
Publication of WO2025041187A1 publication Critical patent/WO2025041187A1/ja
Anticipated expiration legal-status Critical
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/53—Querying
    • G06F16/532—Query formulation, e.g. graphical querying

Definitions

  • This disclosure relates to a processing device, a processing method, and a recording medium.
  • Product recognition processing may be performed using image data for the purpose of product confirmation, etc.
  • Patent Document 1 is an example of a document that describes such processing.
  • Patent Document 1 describes a product recognition device that performs recognition processing based on image data (images).
  • the product recognition device detects the appearance feature amounts of the product contained in the image data captured by an imaging unit from the image data.
  • the product recognition device compares the appearance feature amount data with feature amount data in a recognition dictionary file to extract product candidates contained in the image data.
  • the product recognition device recognizes character strings contained in the image data captured by the imaging unit from the image data.
  • the product recognition device determines the product to be recognized from the extracted product candidates based on the recognized character strings.
  • one of the objectives of this disclosure is to provide a processing device, processing method, and recording medium that can solve the above-mentioned problems.
  • the processing device of the present disclosure comprises: An image data acquisition unit that acquires image data of a target product; A product name acquisition unit that acquires a product name of the product; a search unit that acquires image data from a Web site by performing a search using the product name acquired by the product name acquisition unit as a search key; a matching unit that performs a matching process to search the image data acquired by the search unit for image data that can be determined to be the same as the image data acquired by the image data acquisition unit; A processing unit that performs processing according to a result of the matching process by the matching unit;
  • the configuration has the following:
  • the processing method in the present disclosure includes: An information processing device, Acquire image data of the target product, acquire the product name of the product, Acquire image data from a Web site by performing a search using the acquired product name as a search key; A matching process is performed to search for image data that can be determined to be identical to the image data of the target product among the image data obtained by the search,
  • the system is configured to perform processing according to the results of the matching process.
  • the recording medium in the present disclosure is In the information processing device, Acquire image data of the target product, acquire the product name of the product, Acquire image data from a Web site by performing a search using the acquired product name as a search key; A matching process is performed to search for image data that can be determined to be identical to the image data of the target product among the image data obtained by the search, A computer-readable recording medium having recorded thereon a program for implementing processing that performs processing according to the results of the matching process.
  • the above-mentioned configurations can reduce the risk of not being able to properly recognize the recognition target.
  • FIG. 2 is a diagram for explaining an overview of a process performed by a recognition device according to the present disclosure.
  • 1 is a block diagram showing a configuration example of a recognition device according to the present disclosure.
  • 11 is a diagram for explaining an example of processing by a database matching unit;
  • FIG. 11 is a diagram for explaining an example of a product name acquisition process.
  • FIG. 11 is a diagram for explaining an example of acquired image matching processing.
  • FIG. 11 is a diagram for explaining a processing example of a processing unit.
  • FIG. 11 is a diagram for explaining a processing example of a processing unit.
  • FIG. 11 is a diagram for explaining a processing example of a processing unit.
  • FIG. 11 is a diagram for explaining a processing example of a processing unit.
  • FIG. 11 is a diagram for explaining a processing example of a processing unit.
  • FIG. 11 is a diagram for explaining a processing example of a processing unit.
  • FIG. 11 is a diagram for explaining a processing example of
  • FIG. 11 is a diagram for explaining a processing example of a processing unit.
  • 13 is a flowchart showing an example of the operation of the recognition device.
  • FIG. 2 is a diagram illustrating an example of a hardware configuration of a processing device according to the present disclosure.
  • FIG. 2 is a block diagram showing a configuration example of a processing device.
  • 10 is a flowchart showing an example of the operation of the processing device.
  • Fig. 1 is a diagram for explaining an overview of the processing performed by the recognition device 100.
  • Fig. 2 is a block diagram showing a configuration example of the recognition device 100.
  • Fig. 3 is a diagram for explaining an example of processing by the database matching unit 152.
  • Fig. 4 is a diagram for explaining an example of product name acquisition processing.
  • Fig. 5 is a diagram for explaining an example of acquired image matching processing.
  • Figs. 6 to 10 are diagrams for explaining an example of processing by the processing unit 157.
  • Fig. 11 is a flowchart showing an operation example of the recognition device 100. Note that in the present disclosure, the drawings may be associated with one or more embodiments.
  • a recognition device 100 which is a processing device that performs recognition processing using image data of a product to be recognized.
  • the recognition device 100 matches the image data of the product to be recognized with each image data stored in the product image database 142.
  • the recognition device 100 checks whether image data that can be determined to be the same as the image data of the product to be recognized is stored in the product image database 142 (process 1 in FIG. 1). Then, if it is determined that image data that can be determined to be the same as the image data of the product to be recognized is stored in the product image database 142, the recognition device 100 specifies attributes of the product to be recognized according to the matching result. In other words, if the matching is successful, the recognition device 100 can recognize whether the product to be recognized is real, fake, or a correct product according to the matching result.
  • the recognition device 100 acquires information indicating the product name of the product to be recognized by performing OCR (Optical Character Recognition) processing on the image data of the product to be recognized. Then, the recognition device 100 acquires image data corresponding to the product name by performing crawling using the acquired information, and temporarily stores the image data in the temporary database 143 (processing 2 in FIG. 1). After that, the recognition device 100 matches the image data of the product to be recognized with the image data acquired by crawling, and performs processing according to the matching result.
  • OCR Optical Character Recognition
  • the recognition device 100 can identify the attributes of the product according to the matching result.
  • the recognition device 100 may register the image data acquired by crawling that can be determined to be the same as the image data of the product to be recognized in the product image database 142.
  • the recognition device 100 may be configured to change the content of the processing according to the matching result, depending on whether the source of the image data acquired by crawling is reliable or not.
  • the recognition device 100 may also be configured to match only image data acquired by crawling that can be evaluated as coming from a trustworthy source.
  • the recognition device 100 may also crawl only sites that can be determined as trustworthy.
  • the recognition device 100 can register the image data of the product to be recognized in the unknown image database 144 (Process 3 in FIG. 1). In this way, registering unknown image data in the unknown image database 144 can encourage confirmation by an expert.
  • the recognition device 100 described in this disclosure can be used in the healthcare or medical care field, for example, when trying to recognize whether a medicine that has been purchased or is about to be purchased is genuine. For example, by performing recognition using the recognition device 100, it is possible to confirm in advance whether the medicine is genuine, thereby assisting the user in making a decision when deciding whether to buy the medicine that is the target of recognition.
  • the recognition device 100 may be used in situations and for objects other than those exemplified above.
  • the recognition device 100 can be used during inspection when delivering goods in response to an order, when recognizing goods using a POS (Point of Sale) system using image recognition, or when recognizing any other item.
  • the object recognized by the recognition device 100 is not limited to medicines and may be any product.
  • the image data of a product may be an image of the primary packaging that comes into direct contact with the product or medicine, or an image of an outer container or outer covering that further packages the primary packaging for retail purposes, etc.
  • the image data of a product may be an image of the primary packaging, or an image of secondary packaging such as a product package.
  • FIG. 2 shows an example of the configuration of a recognition device 100, which is an information processing device that performs recognition processing using image data.
  • the recognition device 100 has, as main components, for example, an operation input unit 110, a screen display unit 120, a communication I/F unit 130, a storage unit 140, and an arithmetic processing unit 150.
  • FIG. 2 illustrates an example in which the functions of the recognition device 100 are realized using one information processing device.
  • the functions of the recognition device 100 may be realized using multiple information processing devices, for example, on the cloud.
  • the recognition device 100 may not include some of the configurations exemplified above, such as not having the operation input unit 110 or the screen display unit 120, or may have a configuration other than those exemplified above.
  • the operation input unit 110 is made up of operation input devices such as a keyboard and a mouse.
  • the operation input unit 110 detects the operation of the operator who operates the recognition device 100 and outputs the operation to the calculation processing unit 150.
  • the screen display unit 120 is made up of a screen display device such as a liquid crystal display or an organic electroluminescence (EL) display.
  • the screen display unit 120 can display various information stored in the memory unit 140 on the screen in response to instructions from the calculation processing unit 150.
  • the communication I/F unit 130 is composed of a data communication circuit and the like.
  • the communication I/F unit 130 performs data communication with an external device connected via a communication line.
  • the storage unit 140 is a storage device such as a hard disk or memory.
  • the storage unit 140 stores processing information and programs 145 required for various processes in the arithmetic processing unit 150.
  • the programs 145 are loaded into the arithmetic processing unit 150 and executed to realize various processing units.
  • the programs 145 are loaded in advance from an external device or recording medium via a data input/output function such as the communication I/F unit 130, and are stored in the storage unit 140.
  • Main information stored in the storage unit 140 includes, for example, reliability information 141, product image database 142, temporary database 143, unknown image database 144, etc.
  • the reliability information 141 is information that indicates the reliability of the image acquisition source.
  • the reliability information 141 associates specific information for identifying the image acquisition source, such as a uniform resource locator (URL), with reliability judgment information that indicates whether or not the related site is reliable.
  • the reliability information 141 may include reliability judgment information based on the results of a judgment made, such as a prior investigation, as to whether or not the products or image data posted on the site can be trusted as genuine.
  • Each piece of information included in the reliability information 141 is acquired in advance using a method such as accepting input of information using the operation input unit 110 or accepting information from an external device via the communication I/F unit 130, and is stored in the memory unit 140.
  • the reliability information 141 may include, for example, reliability judgment information for each seller on an EC (electronic commerce) site, or may include information indicating standards for evaluating sellers on an EC site according to their evaluation.
  • the reliability judgment information is information indicating whether or not a related site is reliable, and may be, for example, an arbitrary value according to the level of reliability.
  • the reliability judgment information may simply indicate whether or not something is reliable, or may be more specific information, such as the reliability of the item being genuine according to the possibility that it is genuine, or the reliability of the item being fake according to the possibility that it is fake.
  • Product image database 142 contains image data of products.
  • product image database 142 contains information that associates information indicating product attributes, such as whether the product is genuine, with product image data.
  • Each piece of information contained in product image database 142 is acquired in advance by, for example, receiving information from an external device via communication I/F unit 130, and is stored in storage unit 140.
  • Product image database 142 can also be updated by processing unit 157, which will be described later.
  • the information indicating the attributes of a product can indicate the authenticity of the product, such as whether the related product is real or fake.
  • the information indicating the attributes of a product may include information indicating the possibility of authenticity, such as a value indicating the possibility of authenticity, in addition to or instead of the above examples, or may include any other information.
  • the information indicating the attributes of a product may include information indicating whether the information indicating authenticity has been confirmed by an expert, or information indicating the registration history, such as the fact that it was registered via crawling.
  • the image data of the product may include image data of the product captured from the front, as well as image data of the product captured from any direction.
  • the image data included in the product image database 142 may be an image of the primary packaging, or may be an image of the secondary packaging, etc.
  • the product image database 142 may include information indicating product attributes and product image data, as well as information indicating product names and other arbitrary information.
  • the product image database 142 may include, together with or instead of the image data, feature amounts extracted from the image data using an arbitrary method.
  • the temporary database 143 temporarily stores image data acquired by crawling performed by the crawling unit 154 (described later).
  • the temporary database 143 can be updated by the crawling unit 154, the processing unit 157, etc.
  • the unknown image database 144 temporarily stores image data that cannot be determined to be genuine or fake. As described above, image data stored in the unknown image database is subject to verification by experts. The unknown image database 144 can be updated by the processing unit 157, etc.
  • the calculation processing unit 150 has a calculation device such as a CPU (Central Processing Unit) and its peripheral circuits.
  • the calculation processing unit 150 reads and executes the program 145 from the storage unit 140, thereby realizing various processing units by having the above hardware and the program 145 work together.
  • the main processing units realized by the calculation processing unit 150 include, for example, an image data acquisition unit 151, a database matching unit 152, a product name acquisition unit 153, a crawling unit 154, a reliability evaluation unit 155, an acquired image matching unit 156, and a processing unit 157.
  • the arithmetic processing unit 150 may have a GPU (Graphic Processing Unit), a DSP (Digital Signal Processor), an MPU (Micro Processing Unit), an FPU (Floating point number Processing Unit), a PPU (Physics Processing Unit), a TPU (Tensor Processing Unit), a quantum processor, a microcontroller, or a combination of these.
  • GPU Graphic Processing Unit
  • DSP Digital Signal Processor
  • MPU Micro Processing Unit
  • FPU Floating point number Processing Unit
  • PPU Physicals Processing Unit
  • TPU Transsor Processing Unit
  • quantum processor a microcontroller, or a combination of these.
  • the image data acquisition unit 151 acquires image data of the product to be recognized.
  • the image data acquisition unit 151 can acquire image data of the product to be recognized from an external device such as a camera connected via the communication I/F unit 130 or the like.
  • the image data acquisition unit 151 may acquire image data using any method other than the methods exemplified above.
  • the database matching unit 152 matches the image data acquired by the image data acquisition unit 151 with each image data stored in the product image database 142. In other words, the database matching unit 152 performs a matching process to search the image data stored in the product image database 142 for image data that can be determined to be the same as the image data of the product to be recognized.
  • the method of matching performed by the database matching unit 152 is not particularly limited.
  • the database matching unit 152 extracts features from the image data acquired by the image data acquisition unit 151 using any means, such as using a model that has been machine-learned in advance to extract features according to the input of image data. Then, as shown in FIG. 3, the database matching unit 152 performs matching by checking whether the extracted features are similar to the features of each image data present in the product image database 142. At this time, the database matching unit 152 may check whether there is similarity between each image data of real images present in the product image database 142, and may check whether there is similarity between each image data of counterfeits.
  • the database matching unit 152 can calculate the distance between the features and determine whether the image data to be judged is similar depending on whether the calculated distance exceeds a predetermined value.
  • the database matching unit 152 may determine that the image data of the product to be recognized and the image data stored in the product image database 142 are the same when the calculated distance is equal to or less than a predetermined value.
  • the database matching unit 152 may perform matching using a method other than the above-mentioned examples, such as using a model that has been machine-learned in advance.
  • the database matching unit 152 may also perform the above matching after performing any pre-processing, such as performing front correction to perform keystone correction on the area of the image data acquired by the image data acquisition unit 151 that corresponds to the product.
  • the processing unit 157 described below can output information according to the matching result. For example, if the image data that can be determined to be identical to the image data of the product to be recognized is image data that has the attributes of a genuine product, the processing unit 157 can output information that indicates that the product to be recognized is genuine. Also, if the image data that can be determined to be identical to the image data of the product to be recognized is image data that has the attributes of a fake product, the processing unit 157 can output information that indicates that the product to be recognized is a fake.
  • the product name acquisition unit 153 acquires information indicating the product name of the product to be recognized.
  • the product name acquisition unit 153 may acquire information indicating the product name of the product to be recognized when the database matching unit 152 does not find image data that can be determined to be identical to the image data of the product to be recognized and it is determined that image data that can be determined to be identical is not stored in the product image database 142.
  • the product name acquisition unit 153 can acquire information indicating the product name of the product to be recognized by performing OCR processing on the image data of the product to be recognized, as shown in FIG. 4.
  • the product name acquisition unit 153 can identify and extract, as the product name, a character string that satisfies a predetermined condition, such as a character string that occupies the largest area in the image data from which the character string is extracted, from among the multiple character strings extracted by performing OCR processing. For example, in the example shown in FIG.
  • the product name acquisition unit 153 can identify and extract the character string "ABCD" as the product name.
  • the product name acquisition unit 153 may identify the product name from among the multiple character strings extracted by performing OCR processing, depending on the position of the extracted character string on the product, the presence or absence of decoration, and the like, in addition to the above-mentioned area. For example, the product name acquisition unit 153 may identify and extract product names based on whether the extracted character string is located in the center of the product, whether the character string is decorated, a combination of the above conditions, etc.
  • the product name acquisition unit 153 may acquire the product name using a method other than the OCR processing exemplified above.
  • the product name acquisition unit 153 may accept input of information indicating the product name in response to an operation by an operator on the operation input unit 110.
  • the product name acquisition unit 153 may also acquire information indicating the product name from an external device connected via the communication I/F unit 130.
  • the crawling unit 154 acquires image data corresponding to the product name by performing crawling using the product name acquired by the product name acquisition unit 153.
  • the crawling unit 154 functions as a search unit that acquires image data from one or more Web (World Wide Web) sites by performing a search using the product name as a search key.
  • the crawling unit 154 stores the acquired image data in the temporary database 143.
  • the crawling unit 154 may crawl only the highly reliable sites indicated by the reliability information 141 as sites from which image data may be obtained, or may crawl any site, not limited to the sites indicated by the reliability information 141.
  • the reliability evaluation unit 155 evaluates the reliability of the image acquisition source. For example, the reliability evaluation unit 155 can evaluate the reliability of the site from which the image is acquired by referring to the reliability information 141.
  • the reliability evaluation unit 155 may evaluate reliability for each site, or in the case of an EC site, may evaluate reliability for each seller on the EC site. For example, the reliability evaluation unit 155 may evaluate reliability by modifying the evaluation of the site indicated by the reliability information 141 according to the evaluation of the seller corresponding to the page from which the image data was obtained. The reliability evaluation unit 155 may also be configured to evaluate reliability when the crawling unit 154 does not perform crawling using the reliability information 141.
  • the acquired image matching unit 156 matches the image data of the product to be recognized acquired by the image data acquisition unit 151 with the image data in the temporary database 143. In other words, the acquired image matching unit 156 performs a matching process to search the image data acquired by the crawling unit 154 for image data that can be determined to be the same as the image data of the product to be recognized.
  • the acquired image matching unit 156 may perform matching using a method similar to that of the database matching unit 152 described above.
  • the acquired image matching unit 156 may also be configured to match only image data contained in the temporary database 143 whose source has been determined to be reliable by the reliability evaluation unit 155.
  • the acquired image matching unit 156 may not only simply check whether the images are identical, but may also determine that the images are not identical but cannot be said to be different, for example, when the distance between the feature amounts is equal to or greater than a predetermined value but less than a threshold value. In other words, the acquired image matching unit 156 may be configured to determine that there are subtle differences that cannot be determined to be identical when the distance between the image data of the product to be recognized and the image data acquired by crawling is within a predetermined range.
  • the processing unit 157 performs processing according to the results of matching by the database matching unit 152, the acquired image matching unit 156, etc. For example, the processing unit 157 can perform processing to identify attributes such as the authenticity of a product according to the matching results.
  • the processing unit 157 can output information according to the matching result. As an example, if the image data that can be determined to be the same as the image data of the product to be recognized is image data that has the attribute of a genuine product, the processing unit 157 outputs information that indicates that the product to be recognized is genuine. Also, if the image data that can be determined to be the same as the image data of the product to be recognized is image data that has the attribute of a fake product, the processing unit 157 outputs information that indicates that the product to be recognized is a fake product. For example, the processing unit 157 may display the above information on the screen display unit 120, or may transmit it to an external device via the communication I/F unit 130.
  • the processing unit 157 can identify the attributes of the product according to the matching result. For example, the processing unit 157 can identify that the product to be recognized is genuine. Furthermore, the processing unit 157 may perform processing according to the reliability of the image data acquisition source acquired by crawling. For example, the processing unit 157 may identify that the product to be recognized is genuine when the reliability evaluation unit 155 evaluates the acquisition source of the image data as reliable.
  • the processing unit 157 may identify that the product to be recognized is genuine when it is determined based on the reliability judgment information that the reliability of the genuine product at the acquisition source site is high and the image data is likely to be genuine.
  • the processing unit 157 may identify that the product to be recognized is fake when it is determined based on the reliability judgment information that the reliability of the counterfeit product at the acquisition source site is high and the image data is likely to be fake.
  • the processing unit 157 can output the identification result, or update the product image database 142 according to the identification result, as shown in FIG. 8. For example, if the product to be recognized is identified as genuine, the processing unit 157 may update the product image database 142 by considering the image data acquired by crawling to be genuine image data.
  • the processing unit 157 can register the image data identified as genuine in the product image database 142. At this time, the processing unit 157 may also register information indicating the registration history in the product image database 142. Furthermore, if the product to be recognized is identified as fake, the processing unit 157 may update the product image database 142 by considering the image data acquired by crawling to be fake image data.
  • the processing unit 157 can register the image data of the product to be recognized in the unknown image database 144 as shown in FIG. 9.
  • the processing unit 157 can also urge the expert to check the image data registered in the unknown image database 144.
  • the processing unit 157 can request the expert to check the image data by notifying a preregistered contact address or the like.
  • the processing unit 157 can perform processing according to the results of matching by the database matching unit 152, the acquired image matching unit 156, and the like.
  • the acquired image matching unit 156 may determine that there is a subtle difference.
  • the processing unit 157 may be configured to output the image data with the difference between them emphasized, as illustrated in FIG. 10. While such subtle differences may indicate a fake, they may also indicate the real thing. Therefore, when subtle differences exist, it is possible to output the image data with the difference emphasized as described above, assuming that more detailed confirmation, such as component analysis, is necessary.
  • the difference emphasis may be achieved by any means, such as using a model that has been machine-learned in advance.
  • the processing unit 157 may store the image data in either the product image database 142 or the unknown image database 144, or may not store the image data in either database.
  • the above is an example of the configuration of the recognition device 100.
  • an example of the operation of the recognition device 100 will be described with reference to FIG. 11.
  • a processing method performed by the recognition device 100 which is a processing device, will be described with reference to FIG. 11.
  • FIG. 11 is a flowchart showing an example of the operation of the recognition device 100.
  • the product name acquisition unit 153 acquires the product name (step S102).
  • the product name acquisition unit 153 can acquire information indicating the product name of the product to be recognized by performing OCR processing on the image data of the product to be recognized.
  • the crawling unit 154 acquires image data corresponding to the product name by performing crawling using the product name acquired by the product name acquisition unit 153.
  • the crawling unit 154 also stores the acquired image data in the temporary database 143 (step S103).
  • the reliability evaluation unit 155 evaluates the reliability of the image acquisition source (step S104). For example, the reliability evaluation unit 155 can evaluate the reliability of the site from which the image is acquired by referring to the reliability information 141.
  • the acquired image matching unit 156 matches the image data of the product acquired by the image data acquisition unit 151 with the image data in the temporary database 143 (step S105).
  • the processing unit 157 performs processing according to the result of matching by the acquired image matching unit 156 (step S106). For example, if the acquired image matching unit 156 determines that image data that can be determined to be identical to the image data of the product to be recognized is stored in the temporary database 143, the processing unit 157 can identify the attributes of the product, etc., according to the matching result. For example, the processing unit 157 can identify that the product to be recognized is genuine. The processing unit 157 may perform the identification according to the evaluation by the reliability evaluation unit 155. Furthermore, if the acquired image matching unit 156 determines that image data that can be determined to be identical to the image data of the product to be recognized is not stored in the temporary database 143, the processing unit 157 can store the image data in the unknown image database 144.
  • the processing unit 157 can output information according to the matching result (step S107). For example, if the image data that can be determined to be the same as the image data of the product to be recognized is image data that has the attributes of a genuine product, the processing unit 157 outputs information that indicates that the product to be recognized is genuine. Furthermore, if the image data that can be determined to be the same as the image data of the product to be recognized is image data that has the attributes of a fake product, the processing unit 157 outputs information that indicates that the product to be recognized is a fake.
  • the above is an example of the operation of the recognition device 100.
  • the recognition device 100 has a product name acquisition unit 153, a crawling unit 154, an acquired image matching unit 156, and a processing unit 157.
  • the acquired image matching unit 156 can match the image data of the product to be recognized with the image data acquired by the crawling unit 154 using the product name acquired by the product name acquisition unit 153.
  • the processing unit 157 can perform matching using the crawling results and identify attributes according to the matching results. As a result, even if the recognition target cannot be properly recognized due to reasons such as insufficient image data stored in the product image database 142, it is possible to perform recognition processing and identify the product attributes.
  • the recognition device 100 also has a reliability evaluation unit 155.
  • the processing unit 157 can perform processing according to the evaluation of the source of image data obtained by the reliability evaluation unit 155. As a result, the recognition device 100 can perform recognition processing more appropriately.
  • the processing unit 157 can also update the product image database 142 in accordance with the results of matching by the acquired image matching unit 156. For example, if the acquired image matching unit 156 identifies the product to be recognized as genuine, the processing unit 157 can update the product image database 142 by assuming that the image data acquired by crawling is genuine image data. With this configuration, the recognition device 100 can automatically update the product image database 142 using the results of crawling. This can reduce the effort required when updating the product image database 142.
  • a processing device 200 that is an information processing device that performs processing according to a result of matching will be described with reference to Fig. 12 to Fig. 14.
  • Fig. 12 is a diagram showing an example of the hardware configuration of the processing device 200.
  • Fig. 13 is a block diagram showing an example of the configuration of the processing device 200.
  • Fig. 14 is a flowchart showing an example of the operation of the processing device 200.
  • Fig. 12 shows an example of a hardware configuration of the processing device 200.
  • the processing device 200 has, as an example, the following hardware configuration.
  • ⁇ CPU Central Processing Unit
  • ROM Read Only Memory
  • RAM Random Access Memory
  • Program group 204 loaded into RAM 203
  • a storage device 205 for storing the programs 204
  • a drive device 206 that reads and writes data from and to a recording medium 210 outside the information processing device.
  • a communication interface 207 that connects to a communication network 211 outside the information processing device
  • Input/output interface 208 for inputting and outputting data
  • a bus 209 that connects each component
  • the processing device 200 can realize the functions of the image data acquisition unit 221, product name acquisition unit 222, search unit 223, matching unit 224, and processing unit 225 shown in FIG. 13 by having the CPU 201 acquire and execute the group of programs 204.
  • the group of programs 204 is stored in the storage device 205 or ROM 202 in advance, for example, and is loaded into the RAM 203 or the like by the CPU 201 for execution as necessary.
  • the group of programs 204 may be supplied to the CPU 201 via the communication network 211, or may be stored in the recording medium 210 in advance, and the drive device 206 may read out the programs and supply them to the CPU 201.
  • FIG. 12 shows an example of the hardware configuration of the processing device 200.
  • the hardware configuration of the processing device 200 is not limited to the above-mentioned case.
  • the processing device 200 may be configured with only a part of the above-mentioned configuration, such as not having the drive device 206.
  • the CPU 201 may be a GPU as exemplified in the first embodiment.
  • the image data acquisition unit 221 acquires image data of the target product.
  • the image data acquisition unit 221 may acquire image data from an imaging device such as a camera that captures an image of the product.
  • the product name acquisition unit 222 acquires the product name of the target product.
  • the product name acquisition unit 222 can acquire the product name of the target product by performing OCR processing on the image data acquired by the image data acquisition unit 221.
  • the search unit 223 retrieves image data from the website by performing a search using the product name retrieved by the product name retrieval unit 222 as a search key.
  • the matching unit 224 performs a matching process to search the image data acquired by the search unit 223 for image data that can be determined to be the same as the image data acquired by the image data acquisition unit 221.
  • the matching process may be performed using any method, such as performing the matching process according to the distance between feature amounts extracted from the image data.
  • the processing unit 225 performs processing according to the result of the matching process performed by the matching unit. For example, the processing unit 225 can perform processing to identify attributes such as the authenticity of a product according to the matching result.
  • FIG. 14 shows an example of the operation of the processing device 200.
  • the image data acquisition unit 221 acquires image data of the target product (step S201).
  • the image data acquisition unit 221 may acquire image data from an imaging device such as a camera that captures an image of the product.
  • the product name acquisition unit 222 acquires the product name of the target product (step S202).
  • the product name acquisition unit 222 can acquire the product name of the target product by performing OCR processing on the image data acquired by the image data acquisition unit 221.
  • the search unit 223 acquires image data from the website by performing a search using the product name acquired by the product name acquisition unit 222 as a search key (step S203).
  • the matching unit 224 performs a matching process to search the image data acquired by the search unit 223 for image data that can be determined to be the same as the image data acquired by the image data acquisition unit 221 (step S204).
  • the matching process may be performed using any method, such as performing the matching process according to the distance between feature amounts extracted from the image data.
  • the processing unit 225 performs processing according to the result of the matching process by the matching unit (step S205). For example, the processing unit 225 can perform processing to identify attributes such as the authenticity of the product according to the matching result.
  • the processing device 200 has a product name acquisition unit 222, a search unit 223, a matching unit 224, and a processing unit 225.
  • the matching unit 224 can perform a matching process that uses the product name acquired by the product name acquisition unit 222 to search for image data that satisfies the conditions from among the image data acquired by the search unit 223.
  • the processing unit 225 can perform processing according to the results of the matching process. This makes it possible to perform processing such as identifying attributes such as the authenticity of the product according to the matching results.
  • a program in another form of the present disclosure is a program for implementing processing in an information processing device, which acquires image data of a target product, acquires the product name of the product, acquires image data from a website by performing a search using the acquired product name as a search key, performs a matching process to search the image data acquired by the search for image data that can be determined to be identical to the image data of the target product, and performs processing according to the results of the matching process.
  • the processing method executed by an information processing device such as the processing device 200 described above is a method in which the information processing device acquires image data of a target product, acquires the product name of the product, acquires image data from a website by performing a search using the acquired product name as a search key, performs a matching process to search the image data acquired by the search for image data that can be determined to be identical to the image data of the target product, and performs processing according to the results of the matching process.
  • An image data acquisition unit that acquires image data of a target product;
  • a product name acquisition unit that acquires a product name of the product;
  • a search unit that acquires image data from a Web site by performing a search using the product name acquired by the product name acquisition unit as a search key;
  • a matching unit that performs a matching process to search the image data acquired by the search unit for image data that can be determined to be the same as the image data acquired by the image data acquisition unit;
  • a processing unit that performs processing according to a result of the matching process by the matching unit;
  • a processing device having (Appendix 2) 2.
  • the processing device of claim 1 a reliability evaluation unit that evaluates whether the image data source acquired by the search unit is reliable or not by using information stored in advance; The processing unit performs processing according to the reliability of the image data acquisition source evaluated by the reliability evaluation unit.
  • the processing unit identifies the target product as genuine when the reliability evaluation unit evaluates the source of the image data as reliable.
  • Appendix 4 4.
  • the processing device further comprising: The processing device, wherein the search unit acquires image data from a website that can be evaluated as being reliable based on pre-stored information.
  • the processing device further comprising: The processing unit registers image data, among the image data acquired by the search unit, that can be determined to be identical to the image data acquired by the image data acquisition unit, in an image database that registers image data of products.
  • the processing device further comprising: The product name acquisition unit acquires a product name of the product by performing an OCR (Optical Character Recognition) process on the image data acquired by the image data acquisition unit.
  • OCR Optical Character Recognition
  • the processing device according to claim 1 further comprising: a database matching unit that performs a matching process to search for image data that can be determined to be the same as the image data acquired by the image data acquisition unit from among image data that is stored in advance;
  • the product name acquisition unit acquires a product name of the product when image data that can be determined to be identical to the image data acquired by the image data acquisition unit is not found among pre-stored image data. (Appendix 10) 10.
  • the processing device further comprising:
  • the matching unit is a processing device that performs matching processing using a model that has been machine-learned in advance.
  • An information processing device Acquire image data of the target product, acquire the product name of the product, Acquire image data from a Web site by performing a search using the acquired product name as a search key;
  • a matching process is performed to search for image data that can be determined to be identical to the image data of the target product among the image data obtained by the search, A processing method that performs processing according to the results of the matching process.
  • the programs described in the above embodiments and appendices may be stored in a storage device or a computer-readable recording medium.
  • the recording medium may be a portable medium such as a flexible disk, an optical disk, a magneto-optical disk, or a semiconductor memory.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
PCT/JP2023/029805 2023-08-18 2023-08-18 処理装置 Pending WO2025041187A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/JP2023/029805 WO2025041187A1 (ja) 2023-08-18 2023-08-18 処理装置
JP2025541150A JPWO2025041187A1 (https=) 2023-08-18 2023-08-18

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2023/029805 WO2025041187A1 (ja) 2023-08-18 2023-08-18 処理装置

Publications (1)

Publication Number Publication Date
WO2025041187A1 true WO2025041187A1 (ja) 2025-02-27

Family

ID=94731779

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2023/029805 Pending WO2025041187A1 (ja) 2023-08-18 2023-08-18 処理装置

Country Status (2)

Country Link
JP (1) JPWO2025041187A1 (https=)
WO (1) WO2025041187A1 (https=)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002007413A (ja) * 2000-06-20 2002-01-11 Fujitsu Ltd 画像検索装置
JP2007034847A (ja) * 2005-07-28 2007-02-08 Canon Inc 検索装置及び検索方法
JP2019211869A (ja) * 2018-05-31 2019-12-12 株式会社マーケットヴィジョン 検索対象情報絞込システム

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002007413A (ja) * 2000-06-20 2002-01-11 Fujitsu Ltd 画像検索装置
JP2007034847A (ja) * 2005-07-28 2007-02-08 Canon Inc 検索装置及び検索方法
JP2019211869A (ja) * 2018-05-31 2019-12-12 株式会社マーケットヴィジョン 検索対象情報絞込システム

Also Published As

Publication number Publication date
JPWO2025041187A1 (https=) 2025-02-27

Similar Documents

Publication Publication Date Title
US11756047B2 (en) Fingerprinting physical items to mint NFT's
CN108520196B (zh) 奢侈品辨别方法、电子装置及存储介质
CN112507936B (zh) 图像信息审核方法、装置、电子设备及可读存储介质
US20170337449A1 (en) Program, system, and method for determining similarity of objects
TWI611305B (zh) 識別特徵群體的方法及裝置和搜索方法及裝置
CN109685528A (zh) 基于深度学习检测仿冒产品的系统和方法
US11568460B2 (en) Device, method, and program for commercial product reliability evaluation based on image comparison
US8875303B2 (en) Detecting pirated applications
CN110222511B (zh) 恶意软件家族识别方法、装置及电子设备
US12537702B2 (en) System and method for fact verification using blockchain and machine learning technologies
CN104714950B (zh) 用于对数据库中的信息进行修正及补充的方法及系统
CN111783138A (zh) 敏感数据检测方法、装置、计算机设备及存储介质
CN112308915B (zh) 用于定位快递包裹的方法和装置
CN111475700A (zh) 一种数据提取方法及相关设备
CN114978624A (zh) 钓鱼网页检测方法、装置、设备及存储介质
CN116303459A (zh) 处理数据表的方法及系统
JP2022548501A (ja) 暗号通貨取引を分析するためのデータ取得方法及び装置
CN117874758A (zh) 一种诈骗应用程序识别方法、装置、设备及存储介质
CN113743176A (zh) 一种图像识别方法、设备和计算机可读存储介质
WO2025041187A1 (ja) 処理装置
US20250292205A1 (en) Machine learning method for logistics automation
KR20220129776A (ko) 전자 상거래에서의 이상거래 추적 방법 및 시스템
CN114359918A (zh) 提货单信息提取方法、装置及计算机设备
US12051259B2 (en) Method and system for processing subpoena documents
WO2024183225A1 (zh) 一种商品匹配方法、装置、计算机设备及介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23949649

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2025541150

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 2025541150

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE