Method for generating training data, trained model, information processing apparatus, and information processing method

Abstract

To decode a graphical code rapidly, easily, and accurately.SOLUTION: In a method for generating training data, a first code image, which is a graphical code, is generated, a first numerical image, which is a discount image, is generated, a second code image is generated by applying first image processing to the first code image, a second numerical image is generated by applying the first image processing to the first numerical image, and a first image is generated by superimposing the second code image and the second numerical image onto a background image.SELECTED DRAWING: Figure 11

Description

[Technical Field]

[0001] The present invention relates to a training data generation method, a trained model, an information processing device, and an information processing method. [Background technology]

[0002] It is known that a barcode encoding information identifying a product is attached to the packaging of a product, etc. The encoded information can be decoded by scanning the barcode with a dedicated device for reading barcodes, such as a barcode scanner or touch scanner (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-153224 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventionally, decoding a graphic code such as a barcode required reading the code with a dedicated scanner or capturing an image of the code with a camera. Furthermore, if a discount sticker or the like was attached to the product packaging, in addition to reading the barcode, the user had to recognize the contents of the discount sticker and apply the discount information to the amount determined by reading the barcode to complete the transaction. This resulted in a time-consuming transaction.

[0005] In view of the above, an object of the present disclosure is to quickly, easily, and highly accurately recognize and read discount images. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems, a training data generation method according to a first aspect includes: generating a first code image that is a code of the graphic shape; generating a second code image by performing a first image processing on the first code image; The second code image is superimposed on a background image to generate a first image.

[0007] In addition, the trained model from the second perspective is The computer is caused to function so as to output, for an input image, an area of ​​a partial image of a graphical symbol in the image, which has been trained using a second image generated by a training data generation method that generates a first code image which is a graphical symbol, generates a second code image by performing a first image processing on the first code image, generates a first image by superimposing the second code image on a background image, and generates a second image by performing a second image processing on the first image, wherein the second image processing is a change in at least one of the color and contrast of the entire first image.

[0008] In addition, the trained model from the third perspective is The computer is caused to function so as to output, for an input image, an area of ​​a partial image of a graphical symbol in the image, which has been trained using the first image generated by a training data generation method that generates a first code image, which is a graphical symbol, performs first image processing on the first code image, generates a second code image, and generates a first image by superimposing the second code image on a background image.

[0009] Further, an information processing device according to a fourth aspect comprises: an acquisition unit that acquires the captured image; a control unit that inputs the captured image into a detection model to extract a partial image of a graphical code and decodes the code based on the extracted partial image, The detection model is a trained model that functions to cause a computer to output, for an input image, an area of ​​a partial image of a graphical symbol within the input image, having been trained using a second image generated by a training data generation method that generates a first code image, which is a graphical symbol, generates a second code image by applying a first image processing to the first code image, generates a first image by superimposing the second code image on a background image, and generates a second image by applying a second image processing to the first image, wherein the second image processing is a change in at least one of the color and contrast of the entire first image.

[0010] Furthermore, an information processing method according to a fifth aspect comprises: Acquire the captured image, The captured image is input to a detection model to extract a partial image of a graphic symbol; Decoding the code based on the extracted partial image; The detection model is a trained model that functions to cause a computer to output, for an input image, an area of ​​a partial image of a graphical symbol within the input image, having been trained using a second image generated by a training data generation method that generates a first code image, which is a graphical symbol, generates a second code image by applying a first image processing to the first code image, generates a first image by superimposing the second code image on a background image, and generates a second image by applying a second image processing to the first image, wherein the second image processing is a change in at least one of the color and contrast of the entire first image.

[0011] Furthermore, a training data generation method according to a sixth aspect includes the steps of: generating a first code image used to identify an attribute of the item; generating a second code image by performing a first image processing on the first code image; A method for generating a learning image by superimposing the second code image on a background image including an image of the item and a package containing the item, The first image processing is processing for reproducing a state in which at least one of the item and the packaging containing the item can be seen through the first code image. [Effects of the Invention]

[0012] According to the present disclosure, graphical codes are decoded quickly, easily, and with high accuracy. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a configuration diagram illustrating a schematic configuration of an information processing system including an information processing device according to an embodiment. [Figure 2] FIG. 2 is a block diagram showing a schematic configuration of the terminal device of FIG. [Figure 3] FIG. 3 is a block diagram showing a schematic configuration of the first information processing device of FIG. 2. [Figure 4] FIG. 4 is a first diagram for explaining the process for decoding a code in the first information processing device of FIG. 3. [Figure 5] FIG. 4 is a second diagram for explaining the process for decoding the code in the first information processing device of FIG. 3. [Figure 6] FIG. 3 is a block diagram showing a schematic configuration of the second information processing device of FIG. 2. [Figure 7] FIG. 10 is a block diagram showing a schematic configuration of a third information processing device that executes a training data generating method according to an embodiment. [Figure 8] 10 is an image showing an example of a third code image. [Figure 9] 10 is an image showing another example of the third code image. [Figure 10] 4 is a flowchart illustrating a decoding process executed by the control unit of FIG. 3. [Figure 11] 8 is a flowchart illustrating a learning data generation process executed by the control unit of FIG. 7. DETAILED DESCRIPTION OF THE INVENTION

[0014] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In the following drawings, the same components are denoted by the same reference numerals.

[0015] 1, an information processing system 10 including a first information processing device (information processing device) according to an embodiment of the present disclosure is configured to include at least one terminal device 11, a network 12, and a second information processing device 13. In this embodiment, the information processing system 10 includes a plurality of terminal devices 11. The terminal device 11 and the second information processing device 13 may communicate with each other via the network 12.

[0016] The information processing system 10 is applicable to any system that identifies a detection target based on an image of the detection target included in an image. The information processing system 10 is applicable, for example, to a checkout system that identifies a product that is a detection target based on an image. The information processing system 10 will be described below using an example in which it is applied to a checkout system.

[0017] The information processing system 10, applied to a checkout system, is used for checking out merchandise. A graphic symbol and a discount image are attached to the surface or packaging of each merchandise. The graphic symbol is a graphic symbol that encodes specific information about the merchandise based on an arbitrary encoding algorithm. Examples of the graphic symbol include one-dimensional codes such as barcodes and two-dimensional codes such as QR Code (registered trademark). The specific information about the merchandise may include an identification number assigned to each merchandise, a product name, or other information that identifies the merchandise. The discount image is an image that displays discount information for the merchandise used to calculate the invoice price for the merchandise. Examples of the discount image include, but are not limited to, the amount discounted from the regular merchandise price, the discount rate, the price of the merchandise after a certain amount is discounted from the merchandise price, etc. If the discount information indicates the merchandise price after the discount, the discount image may be placed overlapping the graphic symbol that encodes the specific information. The discount information does not need to be a uniform discount rate or amount; it may be, for example, information about discounts depending on a specific day of the week, a specific date, or a specific time period, or information indicating a discount based on a certain probability. The discount information may be, for example, information indicating that a sales price is discounted only to members of the store selling the product or to holders of a specified coupon. The discount image may be information indicating that points will be awarded to a point card distributed by the store selling the product. The discount image may be represented by a graphic code such as a barcode that encodes information on an access destination for obtaining the discount information. In this case, the terminal device 11 may provide the user with the above-mentioned discount by accessing a specified server at the access destination.

[0018] The terminal device 11 may capture an image of a product. The terminal device 11 may detect and decode a graphical code in the image generated by capturing the image. The terminal device 11 may recognize product identification information by decoding the code. The terminal device 11 may transmit the product identification information to the second information processing device 13. The second information processing device 13 may obtain the product sales price based on the product identification information and provide it to the terminal device 11. The terminal device 11 may present the purchaser with a billing amount based on the sales prices of all products for which settlement is sought, and request payment of the purchase amount.

[0019] The terminal device 11 may detect a discount image in an image generated by capturing an image of the product. The terminal device 11 may recognize discount information from the detected discount image. The second information processing device 13 may present the purchaser with the billing amount calculated based on the product identification information and the discounted billing amount calculated based on the discount information, and request payment of the purchase amount.

[0020] As shown in FIG. 2, the terminal device 11 may include an imaging unit 14, an output device 15, a mounting base 16, a support column 17, and a first information processing device 18.

[0021] The imaging unit 14 is fixed, for example, so as to be able to image at least a portion of the range of the mounting table 16. The imaging unit 14 is fixed, for example, to a support column 17 extending from the side of the mounting table 16. The imaging unit 14 is fixed, for example, so as to be able to image the entire top surface us of the mounting table 16 and so that its optical axis is perpendicular to the top surface us. The imaging unit 14 may capture video. In other words, the imaging unit 14 may generate captured images continuously at a predetermined frame rate. The captured images may be analog signals or digital data.

[0022] The imaging unit 14 may be configured to include a visible light or infrared camera. The camera is configured to include an imaging optical system and an imaging element. The imaging optical system includes optical components such as one or more lenses and an aperture. The lens may be of any type regardless of focal length, and may be, for example, a general lens, a wide-angle lens including a fisheye lens, or a zoom lens with a variable focal length. The imaging optical system forms an image of a subject on the light receiving surface of the imaging element. The imaging element may be, for example, a CCD (Charge Coupled Device) image sensor or a CMOS (Complementary Metal-Oxide Semiconductor image sensor, FIR (far infrared) The image sensor captures the image of the subject formed on the light receiving surface. Generate an image.

[0023] The output device 15 may be any conventionally known display that displays images. The display may function as a touchscreen, as described below. The output device 15 may be a speaker that notifies information. The output device 15 may output, for example, product identification information for a product whose graphical code has been decoded by the first information processing device 18, the product sales price acquired based on the identification information, discount information for the product recognized from the discount image, and the discounted sales price to which the discount information has been applied. The output device 15 may provide various notifications when a malfunction occurs in the information processing system 10 or the like. The output device 15 may output an instruction to change the orientation of a product if the decoding of the graphical code fails. The output device 15 may output information indicating whether the decoding by the first information processing device 18 was successful and an instruction to change the orientation of the product. Furthermore, the output device 15 may output an instruction to change the orientation of a product if the recognition of discount information indicated by the discount image fails. The output device 15 may output information indicating whether the first information processing device 18 recognized the graphical code and / or the discount image and an instruction to change the orientation of the product. In addition, if the discount image indicates the discounted selling price of the product, the first information processing device 18 may cause the output device 15 to display the discounted selling price of the product even if specific information cannot be deciphered from the graphical symbol.

[0024] 3, the first information processing device 18 includes a communication unit 19 (acquisition unit) and a control unit 20. The first information processing device 18 may further include a storage unit 21 and an input unit 22. In this embodiment, the first information processing device 18 is configured as a device separate from the imaging unit 14 and the output device 15, but may be configured integrally with at least one of the imaging unit 14, the mounting base 16, the support column 17, and the output device 15, for example.

[0025] The communication unit 19 includes, for example, a communication module that communicates with the imaging unit 14 via a communication line that may be wired or wireless. The communication unit 19 acquires an image from the imaging unit 14. The communication unit 19 may include a communication module that communicates with the output device 15 via a communication line. The communication unit 19 may transmit an image to be displayed as an image signal to the output device 15. The communication unit 19 may receive a position signal corresponding to a position where a contact is detected on the display surface from the output device 15 that is a display. The communication unit 19 may include a communication module that communicates with the second information processing device 13 via the network 12. The communication unit 19 may receive parameters for constructing a detection model, which will be described later, from the second information processing device 13. Parameters may be an analog signal or digital data. The communication unit 19 may transmit the decoded product identification information and the recognized discount information to the second information processing device 13, as described below. The product identification information and discount information may be analog signals or digital data. The communication unit 19 may receive amount information corresponding to the billing amount from the second information processing device 13. The amount information may be analog signals or digital data. The first information processing device 18 may cause the communication unit 19 to transmit an image of the graphical code and a discount image to the second information processing device 13. In this case, the second information processing device 13 may decode the graphical code to obtain the identification information and recognize the discount information indicated by the discount image. The second information processing device 13 may transmit the discounted selling price, which is the product selling price obtained based on the identification information and applies the discount information, to the first information processing device 18.

[0026] The input unit 22 is capable of detecting an operation input from a user. The input unit 22 includes at least one input interface capable of detecting an input from a user. The input interface is, for example, a physical key, a capacitance key, a pointing device, a touch screen integrated with a display, a microphone, etc. In this embodiment, the input / output interface is a touch screen using the output device 15.

[0027] The storage unit 21 includes any one of a semiconductor memory, a magnetic memory, and an optical memory. The semiconductor memory is, for example, a RAM (Random Access Memory) or a ROM (Read Only Memory). The RAM is, for example, an SRAM (Static Random Access Memory) or a DRAM (Dynamic Random Access Memory). The ROM is, for example, an EEPROM (Electrically Erasable Programmable Read Only Memory). The storage unit 21 may function as a main storage device, an auxiliary storage device, or a cache memory. The storage unit 21 stores data used in the operation of the first information processing device 18 and data obtained by the operation of the first information processing device 18. For example, the storage unit 21 stores system programs, application programs, embedded software, etc. For example, the storage unit 21 stores parameters for constructing a detection model obtained from the second information processing device 13.

[0028] The control unit 20 is configured to include at least one processor, at least one dedicated circuit, or a combination of these. The processor is a general-purpose processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), or a dedicated processor specialized for a specific process. The dedicated circuit may be, for example, an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). The control unit 20 executes processes related to the operation of the first information processing device 18 while controlling each unit of the first information processing device 18.

[0029] 4, the control unit 20 may store the captured image ci acquired via the communication unit 19 in the storage unit 21. The control unit 20 may generate a low-resolution image lri by reducing the resolution of the entire captured image ci already stored in the storage unit 21. The control unit 20 may reduce the resolution of the captured image ci using known image processing such as an LPF (Low Pass Filter). The low-resolution image lri may be an analog signal or digital data.

[0030] The control unit 20 inputs the captured image ci into the detection model, thereby detecting both a first region pia, which is a region of a partial image of a graphic symbol in the captured image ci, and a second region pib, which is a region of a partial image of a discounted image. Alternatively, the control unit 20 inputs a low-resolution image lri instead of the captured image ci into the detection model, thereby detecting both the first region pia and the second region pib in the low-resolution image lri. The detection model is used to detect the entire image. The control unit 20 may detect both the symbol and the discount image in the graphic and estimate the area occupied by the symbol and the area occupied by the discount image. The area occupied by the symbol and the area occupied by the discount image may be analog signals or digital data. The detection model may be a trained model, which will be described later. As shown in FIG. 5, the control unit 20 extracts, for example, a partial image of the first region pia from the captured image ci stored in the storage unit 21. The control unit 20 may extract multiple first regions pia. The control unit 20 may also extract, for example, a partial image of the second region pib from the captured image ci stored in the storage unit 21. The control unit 20 may extract multiple second regions pib. The partial images may be analog signals or digital data. The control unit 20 decodes the symbol based on the partial image in the extracted first region pia. The control unit 20 recognizes the discount image based on the partial image in the extracted second region pib. The discount image may be expressed in various shapes and designs. The discount image may be surrounded by a predetermined pattern so that the area can be clearly recognized. For example, the discount information may be surrounded by a predetermined pattern to form the discount image. The predetermined pattern may be represented by a specific color that is not used on the product packaging. The predetermined pattern may be a shape that is not used on the product packaging.

[0031] When the reliability of detection of the first region pia and / or the second region pib using the detection model is equal to or lower than a reliability threshold, the control unit 20 may cause the output device 15 to request the imaging unit 14 to change the orientation of the graphical code and the discount image so that they are easier to read. More specifically, the control unit 20 may cause the output device 15 to request the imaging unit 14 to change the orientation or angle of the product to which the graphical code and the discount image are attached so that the graphical code and the discount image are captured more clearly by the imaging unit 14. Alternatively, when the control unit 20 cannot decode the graphical code based on the extracted partial image in the first region pia, the control unit 20 may cause the output device 15 to request the imaging unit 14 to orient the graphical code. Furthermore, when the control unit 20 cannot recognize the discount image based on the partial image in the second region pib, the control unit 20 may cause the output device 15 to request the imaging unit 14 to orient the discount image. In addition, for example, in a configuration in which the control unit 20 has a large processing capacity and has sufficient capacity to detect the first area pia and the second area pib, the control unit 20 may decode the code of the captured image ci based on the input of the detection model and recognize the image without using the low-resolution image lri, as described above.

[0032] As shown in FIG. 6, the second information processing device 13 may include a communication unit 23, a storage unit 24, and a control unit 25.

[0033] The communication unit 23 may include at least one communication module connectable to the network 12. The communication module is, for example, a communication module compatible with communication standards such as a wired LAN (Local Area Network), a wireless LAN, or Wi-Fi. The communication unit 23 may be connected to the network 12 via a wired LAN or the like by the communication module.

[0034] The communication unit 23 may include a communication module capable of communicating with various external devices via a communication line. The communication module is a communication module that complies with the standards of the communication line. The communication line may be configured to include at least one of a wired and a wireless communication line.

[0035] The storage unit 24 includes any of semiconductor memory, magnetic memory, and optical memory. The semiconductor memory is, for example, RAM or ROM. The RAM is, for example, SRAM or DRAM. The ROM is, for example, EEPROM. The storage unit 24 may function as a main storage device, an auxiliary storage device, or a cache memory. The storage unit 24 stores data used in the operation of the second information processing device 13. For example, the storage unit 24 stores system programs, application programs, embedded software, etc. Furthermore, for example, the storage unit 24 stores the sales price of each product registered in the production system.

[0036] The control unit 25 is configured to include at least one processor, at least one dedicated circuit, or a combination of these. The processor is a general-purpose processor such as a CPU or GPU, or a dedicated processor specialized for a specific process. The dedicated circuit may be, for example, an FPGA, an ASIC, or the like. The control unit 25 executes processes related to the operation of the second information processing device 13 while controlling each unit of the second information processing device 13.

[0037] The control unit 25 may acquire product identification information from the terminal device 11 through decryption and read the sales price of the product corresponding to the identification information from the storage unit 24. The control unit 25 may calculate the billing amount by adding up the sales prices of multiple products. The control unit 25 may transmit monetary information corresponding to the billing amount to the terminal device 11. When the control unit 25 acquires discount information for a product in addition to the product identification information, it may calculate the discount price of the product from the sales price and discount information. The discount price is the price after a discount is applied to the sales price, calculated based on the sales price and discount information for the product stored in the storage unit 24. For example, if the product is "bread" and its sales price is "150 yen," and the discount information is "20 yen off," the discount price is "130 yen," which is the sales price of bread minus 20 yen. Note that if the discount information is the price of the product after a predetermined amount is discounted from the sales price of the product, the discount price may be the same as the discount information. For example, if the product is "bread," the selling price is "150 yen," and the discount information is "120 yen," the discount price is "120 yen." When the control unit 25 acquires the discount information for the product, it may transmit amount information corresponding to the discount price to the terminal device 11 that has assigned the product-specific information.

[0038] The detection model used in the first information processing device 18 is a trained model that is trained using a combination of an image including, as a partial image, a product with a graphic symbol and a discount image attached to the surface, and information indicating the position of the symbol and the position of the discount image as training data. A method for generating training data from training data will be described below.

[0039] The learning data may be generated by, for example, a third information processing device 26 as shown in Fig. 7. The third information processing device 26 may be a general-purpose information processing device such as a personal computer (PC) or a server device, or a dedicated information processing device. The third information processing device 26 may include an input / output interface 27, an output unit 28, an input unit 29, a storage unit 30, and a control unit 31.

[0040] The input / output interface 27 inputs and outputs data directly or indirectly via a network to, for example, a camera or other information processing device. For example, the input / output interface 27 may acquire character information for generating a first code image, which is a graphical code. The input / output interface 27 may also acquire character information for generating a first numeric image, which is a discount image. The character information may be an analog signal or digital data. The character information may be any information, may be meaningful information, or may be meaningless information consisting simply of a list of characters, etc.

[0041] The input / output interface 27 may acquire a third code image that has been generated by capturing an image of an existing graphic code. The third code image may be an analog signal or digital data. The third code image preferably includes images of a code captured not only from the front but also from various directions. The third code image preferably includes an image of a code drawn on a flexible package and captured in a curved and deformed state, as shown in FIG. 8, for example. The third code image preferably includes an image of a code that has been blurred by capturing an image shifted from the focused position, for example. The third code image preferably includes an image of a graphic code through which an underlying image can be seen through, as shown in FIG. 9, for example.

[0042] The input / output interface 27 may also acquire a third numerical image that has already been generated by capturing an existing discounted image. The third numerical image may be an analog signal or digital data. The third numerical image preferably includes discounted images captured not only from the front but also from various directions. The third numerical image preferably includes a discounted image that has been blurred by capturing the image from an out-of-focus position, for example. The third numerical image preferably includes a discounted image in which the underlying image can be seen through, as shown in FIG. 9.

[0043] The input / output interface 27 may also acquire a background image. The background image may be an analog signal or digital data. The background image is a wide-area image including an object on which a graphic symbol is drawn, such as a product or product packaging. The wide-area image may be, for example, an image of an object placed on a stand or the like, along with the seat surface of the stand.

[0044] The output unit 28 may include one or more interfaces that output information to notify the user, such as, but not limited to, a display that outputs information visually or a speaker that outputs information audibly.

[0045] The input unit 29 may include one or more interfaces for detecting user input, such as physical keys, capacitive keys, and a touch screen that is integrated with the display of the output unit 28.

[0046] The storage unit 30 includes any of semiconductor memory, magnetic memory, and optical memory. The semiconductor memory is, for example, RAM or ROM. The RAM is, for example, SRAM or DRAM. The ROM is, for example, EEPROM. The storage unit 30 may function as a main storage device, an auxiliary storage device, or a cache memory. The storage unit 30 stores data used in the operation of the third information processing device 26. For example, the storage unit 30 stores system programs, application programs, embedded software, and the like. For example, the storage unit 30 may store character information, a third code image, a third numeric image, and a background image acquired via the input / output interface 27.

[0047] The control unit 31 is configured to include at least one processor, at least one dedicated circuit, or a combination of these. The processor is a general-purpose processor such as a CPU or GPU, or a dedicated processor specialized for a specific process. The dedicated circuit may be, for example, an FPGA, an ASIC, or the like. The control unit 31 executes processes related to the operation of the third information processing device 26 while controlling each unit of the third information processing device 26.

[0048] The control unit 31 generates a first code image which is a graphic code. The first code image may be an analog signal or digital data. The control unit 31 may generate the first code image by encoding character information acquired by the input / output interface 27 and the input unit 29. Alternatively, the control unit 31 may generate character information by randomly listing a predetermined number of characters, and encode the character information to generate the first code image. The control unit 31 may perform encoding using any encoding algorithm.

[0049] The control unit 31 generates a discount image. The control unit 31 may generate the first numerical image by encoding character information acquired by the input / output interface 27 and the input unit 29. Alternatively, the control unit 31 may generate character information by randomly listing a predetermined number of characters, and then encode the character information to generate the first numerical image. The control unit 31 may perform encoding using any encoding algorithm.

[0050] The control unit 31 may generate learning data using a third code image in addition to the first code image. When the third code image is used to generate learning data, the control unit 31 generates the first code image. The number of first code images to be generated may be determined by the number of third code images to be acquired. The number of first code images and the number of third code images are the numbers of codes that can be decoded into independent specific information. The number of first code images to be generated may be the same as the number of third code images.

[0051] The control unit 31 may generate learning data using third numeric images separately from the first numeric images. When the control unit 31 uses third numeric images to generate learning data, the control unit 31 may determine the number of first numeric images to be generated based on the number of third numeric images to be acquired. The number of first numeric images and the number of third numeric images are the numbers of independent discount information. The number of first numeric images to be generated may be the same as the number of third numeric images.

[0052] The control unit 31 generates a second code image and a second numerical image by performing a first image processing on the first code image and the first numerical image, respectively. The second code image and the second numerical image may be analog signals or digital data. The first image processing may be processing to reproduce deformations such as distortion and curvature of the graphic code and the discount image that occur due to deformations such as distortion and curvature of the goods or packaging to which the graphic code and the discount image are attached. The first image processing may be processing to reproduce deformations of the graphic code and the discount image that occur when the goods or packaging to which the graphic code and the discount image are attached are placed on the placing table 16. The first image processing may be processing to reproduce various orientations of the graphic code and the discount image relative to the imaging device 14 that occur when the goods or packaging to which the graphic code and the discount image are attached are placed on the placing table 16. The first image processing may be processing that reproduces blurring caused by deviation from the focus position of the imaging device 14 due to the size of the item or package on which the graphical code and discount image are attached, and various sizes of the graphical code and discount image due to the distance from the imaging device 14. The first image processing may be processing that reproduces transparency caused by the material of the item or package on which the graphical code and discount image are attached. The first image processing may be processing that reproduces the current state according to the surrounding environment when the item or package on which the graphical code and discount image are attached is placed on the placing table 16, such as partial highlighting due to reflection from a light source, on the graphical code and discount image.

[0053] Therefore, the first image processing may include at least one of rotation, enlargement or reduction, distortion, blurring, transparency, and local discoloration. The first image processing may be a combination of at least two of rotation, enlargement or reduction, distortion, blurring, transparency, and local discoloration. The distortion may be a process of reproducing an appearance in which the graphic code and discount image are changed in accordance with the three-dimensional shape, such as curvature, of the product on which the code and discount image are depicted. The distortion may be a process of reproducing an appearance in which the graphic code and discount image are changed in accordance with the three-dimensional shape, such as distortion or curvature, of flexible packaging on which the graphic code and discount image are depicted, as shown in FIG. 8. The transparency may be a process of reproducing an appearance in which the graphic code and discount image are transparent, allowing one or both of the product and the packaging containing the product to be visible, as shown in FIG. 9 and the triangle. The transparency may also be a process of changing the transparency of at least a portion of the first code image, taking into account the material on which the graphic code is attached, to reproduce an appearance in which the graphic code, discount image, and pictures or letters depicted on the product or packaging appear to be mixed together. The local discoloration is, for example, a process for increasing brightness, such as the glossiness of the surface on which the graphic symbol and discount image are drawn in the actual captured image ci. The first image process may be the same for all first symbol images and first numeric images, or may be different for all first symbol images and first numeric images.

[0054] The control unit 31 may generate second code images and second numeric images by performing first image processing on the third code images and third numeric images, respectively. The first image processing may be the same for all third code images and third numeric images, or may be different for all third code images and third numeric images. When the control unit 31 has already generated first code images in excess of the number of third code images, the control unit 31 may adjust the total number of second code images based on the first code images to be the same as the total number of second code images based on the third code images by increasing the number of second code images generated for each third code image more than the number of second code images generated for each first code image. Also, the control unit 31 may adjust the total number of second code images based on the third code images to be the same as the total number of second code images based on the third code images, when the control unit 31 has already generated first code images in excess of the number of third numeric images. When the number of first numeric images generated exceeds the number of images, the number of second numeric images generated for each third numeric image may be increased to be greater than the number of second numeric images generated for each first numeric image, thereby adjusting the total number of second numeric images based on the first numeric images to be the same as the total number of second numeric images based on the third numeric images.

[0055] The control unit 31 generates a first image by superimposing both the second code image and the second numeric image on a background image. The first image may be an analog signal or digital data. The control unit 31 may superimpose both the second code image and the second numeric image on an object, particularly in the background image. The object may include, for example, an item. The object may include, for example, a package (an item and packaging containing the item). The packaging may be a packaging film or packaging container through which the contained item can be seen. The packaging may also be wrapping paper, packaging film, or packaging container through which the contained item cannot be seen. When the control unit 31 generates both the second code image and the second numeric image through transparency as the first image processing and the background image includes a package, the control unit 31 may generate a first image in a manner in which one or both of the item and the packaging containing the item can be seen in the background of the second code image and the second numeric image. The control unit 31 may generate both the second code image and the second numeric image through transparency as the first image processing. When the background image includes a package wrapped so that the contained items can be seen, the control unit 31 may generate a first image in a manner that allows the items inside the package and other objects placed underneath the package to be seen. When the control unit 31 performs processing including transparency as the first image processing to generate the second code image and the second numeric image and superimpose them on the objects, the control unit 31 may generate a first image in a manner that the second code image and the second numeric image are mixed with the objects. The control unit 31 may superimpose multiple background images for each of the second code image and the second numeric image, thereby generating multiple first images for each of the second code image and the second numeric image. The control unit 31 may generate a first image based on the third code image and the third numeric image. The first image based on the third code image and the third numeric image may include an image generated by superimposing, on a background image, each of the second code image and the second numeric image generated by performing the first image processing on the third code image and the third numeric image. Alternatively, the first image based on both the third code image and the third numeric image may include an image generated by superimposing, on a background image, both the third code image and the third numeric image without performing the first image processing on both the third code image and the third numeric image.When superimposing both the second code image and the second numeric image on the background image, the control unit 31 may recognize position information indicating the area where the second code image and the second numeric image are superimposed.

[0056] The control unit 31 may generate a second image by performing second image processing on the first image. The second image may be an analog signal or digital data. The second image processing may be processing that reproduces changes caused by the model of the imaging device 16 and settings at the time of shooting. It may be processing that reproduces changes caused by settings of the imaging device 16 at the time of shooting. The second image processing may be processing that reproduces changes in appearance due to the illuminance value when the imaging device 16 captures an image of a graphical code. Therefore, the second image processing is processing that changes at least one of the color and contrast of the entire first image. The color change refers to a change in hue, saturation, or brightness, for example. The second image processing may be the same for all second code images, or may be different.

[0057] The control unit 31 may associate the generated second image with position information indicating an area in the second image where both the second code image and the second numeric image are superimposed as training data, and store the associated training data in the storage unit 30. In generating training data, for the purpose of easily increasing the amount of training data while improving the accuracy of detection, the control unit 31 may associate the generated first image with position information indicating an area in the first image where both the second code image and the second numeric image are superimposed as training data, and store the associated training data in the storage unit 30.

[0058] Next, the decryption process executed by the control unit 20 of the first information processing device 18 in this embodiment will be described. The recognition process will be described with reference to the flowchart in Fig. 10. The decoding process starts every time the communication unit 19 of the first information processing device 18 acquires one frame of a captured image ci.

[0059] In step S100, the control unit 20 stores the acquired captured image ci in the storage unit 21. After storage, the process proceeds to step S101.

[0060] In step S101, the control unit 20 generates a low-resolution image lri by reducing the resolution of the entire captured image. After generation, the process proceeds to step S102.

[0061] In step S102, the control unit 20 detects the first region pia by inputting the low-resolution image lri generated in step S101 into the detection model. After detection, the process proceeds to step S103.

[0062] In step S103, the control unit 20 extracts a partial image in the area at the same position as the first area pia detected in step S102 from the captured image ci stored in the storage unit 21 in step S100. After the extraction, the process proceeds to step S104.

[0063] In step S104, the control unit 20 determines whether the reliability of the detection in step S102 is equal to or less than the reliability threshold. If it is equal to or less than the reliability threshold, the process proceeds to step S107. If it is not equal to or less than the reliability threshold, the process proceeds to step S105.

[0064] In step S105, the control unit 20 decodes the graphic code based on the partial image extracted in step S103. After decoding, the process proceeds to step S106.

[0065] In step S106, the control unit 20 determines whether the decoding in step S105 has failed. If the decoding has failed, the process proceeds to step S107. If the decoding has succeeded, the process proceeds to step S108.

[0066] In step S107, the control unit 20 controls the output device 15 to output a request to direct the graphic code toward the imaging unit 14. After the output, the decoding process ends.

[0067] In step S108, the control unit 20 inputs the low-resolution image lri generated in step S101 into the detection model, and determines whether or not the second region pib has been detected.

[0068] When the control unit 20 detects the second region pib by inputting the low-resolution image lri generated in step S101 into the detection model (step S108: YES), the process proceeds to step S109.

[0069] When the control unit 20 inputs the low-resolution image lri generated in step S101 into the detection model and does not detect the second region pib (step S108: NO), the decoding process ends.

[0070] In step S109, the control unit 20 extracts a partial image in the area at the same position as the second area pib from the captured image ci stored in the storage unit 21 in step S100. After the extraction, the process proceeds to step S110.

[0071] In step S110, the control unit 20 determines whether the reliability of the detection in step S108 is equal to or less than the reliability threshold. If it is equal to or less than the reliability threshold, the process proceeds to step S114. If it is not equal to or less than the reliability threshold, the process proceeds to step S111.

[0072] In step S111, the control unit 20 recognizes a discounted image based on the partial image extracted in step S109. After the recognition, the process proceeds to step S112.

[0073] In step S112, the control unit 20 determines whether the recognition in step S111 has failed. If the recognition has failed, the process proceeds to step S114. If the recognition has succeeded, the process proceeds to step S113.

[0074] In step S113, the control unit 20 generates new product identification information using both the product information obtained by decoding the graphic code in step S105 and the discount information obtained by recognizing the discount image in step S111. After generation, the decoding process and the recognition process are terminated.

[0075] In step S114, the control unit 20 controls the output device 15 to output a request to direct the discount image toward the imaging unit 14. After the output, the decoding process and the recognition process are completed.

[0076] In step S113, new product identification information is generated using both the product identification information obtained by decoding the graphical code in step S105 and the discount information obtained by recognizing the discount image in step S111, but this is not limited to this, and the decoding process and recognition process may be terminated when the product identification information and discount information are obtained.

[0077] Next, the learning data generation process executed by the control unit 31 of the third information processing device 26 in this embodiment will be described with reference to the flowchart in Fig. 11. The learning data generation process starts when the input unit 29 detects an operation input for generating learning data.

[0078] In step S200, the control unit 31 acquires third code images and third numeric images from a camera or other information processing device via the input / output interface 27, or from the storage unit 30. Furthermore, the control unit 31 counts the number of acquired third code images and the number of acquired third numeric images. After counting, the process proceeds to step S201.

[0079] In step S201, the control unit 31 determines the number of first code images to be created based on the number of third code images counted in step S200, and determines the number of first numeric images to be created based on the number of third numeric images counted. After the determination, the process proceeds to step S202.

[0080] In step S202, the control unit 31 generates each of a first code image and a first numeric image by encoding character information. The control unit 31 generates each of the first code image and the first numeric image using character information acquired by another information processing device via the input / output interface 27 and the input unit 29, character information stored in the storage unit 30, or character information generated by the control unit 31. The control unit 31 generates each of the first code images and first numeric images the number of which was determined in step S201. After generation, the process proceeds to step S203.

[0081] In step S203, the control unit 31 generates a second code image and a second numeric image by performing a first image processing on the third code image and the third numeric image acquired in step S200 and the first code image and the first numeric image generated in step S202. After generation, the process proceeds to step S204.

[0082] In step S204, the control unit 31 generates a first image by superimposing the second code image and the second numeric image generated in step S203 on the background image. The unit 31 may acquire the background image from another information processing device or a camera via the input / output interface 27, or from the storage unit 30. After generation, the process proceeds to step S205.

[0083] In step S205, the control unit 31 recognizes the position information of the area where the second code image is superimposed in the first image generated in step S204 and the area where the second numeric image is superimposed. After the recognition, the process proceeds to step S206.

[0084] In step S206, the control unit 31 generates a second image by performing second image processing on the first image generated in step S204. After generation, the process proceeds to step S207.

[0085] In step S207, the control unit 31 stores in the storage unit 30 the position information recognized in step S205 and the second image generated in step S206 in association with each other.

[0086] The third information processing device 26 of this embodiment configured as described above generates a first code image and a first numeric image, performs first image processing on the first code image and the first numeric image to generate a second code image and a second numeric image, and generates a first image by superimposing the second code image and the second numeric image on a background image. The decoding accuracy of the geometric code and the recognition accuracy of the discount image using the first information processing device 18 described above increases with the detection accuracy of the detection model. The detection accuracy of the detection model can be improved by learning using a large amount of supervised data. However, creating the supervised data requires the operator to identify the geometric code area and the discount information area after capturing an image of the object, which places a significant burden on the operator. On the other hand, the third information processing device 26 configured as described above does not require capturing and positioning the geometric code and the discount information, and can generate a large amount of supervised data for learning with low load. Therefore, the third information processing device 26 can improve the detection accuracy of the detection model, thereby contributing to the first information processing device 18 quickly and easily decoding the geometric code and recognizing the discount image.

[0087] Furthermore, in the third information processing device 26, the first image processing is at least one of rotation, enlargement or reduction, distortion, blurring, transparency, and local discoloration. When the imaging unit 14 captures the graphic code to be decoded and the discount image to be recognized, the partial images of the code and discount image contain various sizes, various orientations, distortion due to curvature of the product, distortion due to distortion and curvature of the packaging, blurring due to deviation from the focus position, transparency depending on the material to which the graphic code and discount image are attached, and partial highlighting due to reflection from the light source. In response to such phenomena, the third information processing device 26 having the above configuration can generate a second code image and a second numeric image that reflect phenomena that may be contained in the actual code of the partial image and the discount image of the partial image. Therefore, the third information processing device 26 can generate training data that further improves the detection accuracy of the detection model.

[0088] In addition, in the third information processing device 26, the first image processing changes the transmittance of the first code image and the first numeric image to generate a second code image in which the first code image is blended with the background image and a second numeric image in which the first numeric image is blended with the background image. When the imaging unit 14 captures the graphic code to be decoded and the discount image to be recognized, depending on the material to which the graphic code and the discount image are attached, the partial image of the code and the partial image of the discount image may include images of the background item and the packaging containing the item due to transparency. In response to such an event, the third information processing device 26 having the above configuration can generate a second code image and a second numeric image that reflect the event that may be included in the actual code of the partial image and the discount image of the partial image. Therefore, the third information processing device 26 can generate training data that further improves the detection accuracy of the detection model.

[0089] In the third information processing device 26, the background image includes an image of the product, and the first image processing generates a second code image and a second numerical value image in which the graphic code and the discount image are changed according to the three-dimensional shape of the product. When the imaging unit 14 captures the graphic code to be decoded and the discount image to be recognized, partial images are generated in which distortions due to distortion or curvature of the item occur in the code and the discount image. In response to such events, the third information processing device 26 having the above configuration can generate a second code image and a second numeric image that reflect the event that may be included in the actual code of the partial image and the discount image of the partial image. Therefore, the third information processing device 26 can generate learning data that further improves the detection accuracy of the detection model.

[0090] In addition, in the third information processing device 26, the background image includes an image of the packaging, and the first image processing generates a second code image and a second numerical image in which the graphic code and discount image are changed according to the three-dimensional shape of the packaging. When the imaging unit 14 captures the graphic code to be decoded and the discount image to be recognized, partial images are generated in which distortions due to distortion or curvature of the packaging occur in the code and discount image. In response to such events, the third information processing device 26 having the above configuration can generate a second code image and a second numerical image that reflect the events that may be included in the actual code and discount image of the partial image. Therefore, the third information processing device 26 can generate learning data that further improves the detection accuracy of the detection model.

[0091] Furthermore, the third information processing device 26 generates a second image by performing second image processing on the first image, where the second image processing is a change in at least one of the color and contrast of the entire first image. When the imaging unit 14 captures a graphic code to be decoded and a discount image to be recognized, the appearance may change depending on the illumination light illuminating the graphic. In response to such an event, the third information processing device 26 having the above configuration can generate a second image that reflects an event that may be contained in an actual partial image. Therefore, the third information processing device 26 can generate training data that further improves the detection accuracy of the detection model.

[0092] Furthermore, the third information processing device 26 acquires the third code image and the third numeric image, and generates the first image based on the third code image and the third numeric image. With this configuration, the third information processing device 26 can generate learning data that improves the detection accuracy of the area of ​​the code and the area of ​​the discount image in an image of a product or the like that actually includes the graphic code and the discount image.

[0093] Furthermore, the third information processing device 26 determines the number of first code images to be generated based on the number of acquired third code images, and determines the number of first numeric images to be generated based on the acquired third numeric images. With this configuration, the third information processing device 26 prevents unlimited generation of first code images and first numeric images relative to the number of third code images and third numeric images generated by actual imaging. Therefore, the third information processing device 26 can generate learning data that further improves the detection accuracy of the area of ​​the symbol and the discount image in an image actually captured of a product or the like including the symbol and the discount image.

[0094] Moreover, the third information processing device 26 generates a second code image and a second numeric image by performing the first image processing on the third code image and the third numeric image, respectively. With this configuration, the third information processing device 26 generates images by deforming actually captured images, and therefore can provide a variety of learning data. Therefore, the third information processing device 26 can generate learning data that further improves the detection accuracy of the detection model.

[0095] In this embodiment, the first information processing device 18 includes a communication unit 19 that acquires the captured image ci, and a control unit 20 that extracts a partial image of a graphic symbol and a partial image of a discount image by inputting the captured image ci into a detection model, decodes the symbol based on the extracted partial images, and recognizes the discount image, and the detection model is the learning model described above. Since the first information processing device 18 performs decoding and recognition based on the captured image ci, it does not require a dedicated scanner and does not require alignment or orientation adjustment, so that code decoding and recognition can be easily performed.

[0096] In addition, the first information processing device 18 detects a first region pia and a second region pib of a partial image in the low-resolution image lri, which is obtained by reducing the resolution of the captured image ci, by inputting the low-resolution image lri into the detection model, and decodes the code based on the detected partial image to recognize the partial image of the discount image. The first information processing device 18 uses the low-resolution image lri to detect the partial region of the graphic code and the partial image of the discount image, so that detection can be performed quickly.

[0097] In one embodiment, (1) the training data generation method includes: generating a first code image that is a code of the graphic shape; generating a first numeric image that is a discount image; generating a second code image by performing a first image processing on the first code image; generating a second numerical image by performing the first image processing on the first numerical image; A first image is generated by superimposing the second code image and the second numeric image on a background image.

[0098] (2) In the training data generation method described in (1) above, The first image processing is at least one of rotation, enlargement or reduction, distortion, blurring, transparency, and local discoloration.

[0099] (3) In the training data generation method (1) or (2) above, the background image includes an image of an item and a package containing the item; The first image processing generates the second code image in a manner that allows one or both of the product and the packaging, which form the background, to be visible through the graphical symbol.

[0100] (4) In the training data generation method described in (3) above, The first image processing changes the transparency of the first code image to generate the second code image in which the first code image is mixed with the background image.

[0101] (5) In the training data generation methods (1) to (4) above, the background image includes an image of an item; The first image processing generates the second code image by changing the graphic code in accordance with the three-dimensional shape of the article.

[0102] (6) In the training data generation method of (1) to (5) above, the background image includes an image of a package; The first image processing generates the second code image by changing the graphic code in accordance with the three-dimensional shape of the package.

[0103] (7) In the training data generation methods (1) to (6) above, generating a second image by performing second image processing on the first image; The second image processing is a change in at least one of color and contrast across the first image.

[0104] (8) In the training data generation method of (1) to (7), A third code image, which is a code of the figure shape, is obtained; The first image is generated based on the third code image.

[0105] (9) In the training data generation method of (8) above, The number of the first code images to be generated is determined based on the number of the third code images to be obtained.

[0106] (10) In the training data generation method of (8) or (9), The third code image is subjected to the first image processing to generate the second code image.

[0107] (11) In the training data generation method of (8) or (9), The first image is generated by superimposing the third code image on a background image.

[0108] (12) The trained model using the training data generation method in (7) above is The computer is caused to function so as to output a region of a partial image of a graphical symbol in an input image that has been trained using the second image generated by the training data generation method.

[0109] (13) A trained model using the training data generation methods (1) to (11) above is A trained model that is trained using a first image generated by the training data generation method, and that causes a computer to function so that, for an input image, it outputs a region of a partial image of a graphical symbol within the image.

[0110] In one embodiment, (14) the information processing device an acquisition unit that acquires the captured image; a control unit that extracts a region of a partial image of a graphical code by inputting the captured image into a detection model, and decodes the code based on the extracted partial image, The detection model is a trained model according to (12) or (13).

[0111] (15) In the information processing device of (14), The control unit detects the area of ​​the partial image in the low-resolution image by inputting a low-resolution image obtained by reducing the resolution of the captured image into the detection model, and decodes the code based on the detected partial image.

[0112] In one embodiment, (16) an information processing method includes: Acquire the captured image, The captured image is input to a detection model to extract a partial image of a graphic symbol; Decoding the code based on the extracted partial image; The detection model is a trained model according to (12) or (13).

[0113] In one embodiment, (17) the training data generation method includes: generating a first code image used to identify an attribute of the item; generating a second code image by performing a first image processing on the first code image; A method for generating a learning image by superimposing the second code image on a background image including the item and a package containing the item, The first image processing is performed to make the first code image visible through which at least one of the item and the packaging containing the item can be seen.

[0114] The above has described embodiments of the first information processing device 18 and the third information processing device 26, but embodiments of the present disclosure can also be embodied as a method or program for implementing the device, as well as a storage medium on which a program is recorded (for example, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a CD-RW, a magnetic tape, a hard disk, or a memory card, etc.).

[0115] The implementation form of the program is not limited to an application program such as an object code compiled by a compiler or a program code executed by an interpreter, but may be a program module incorporated into an operating system. The program may be configured so that all or part of the program is executed by another processing unit mounted on an expansion board or expansion unit added to the board as needed.

[0116] The drawings illustrating the embodiments of the present disclosure are schematic, and the dimensional ratios and the like in the drawings do not necessarily correspond to the actual ones.

[0117] Although the embodiments of the present disclosure have been described based on the drawings and examples, it should be noted that those skilled in the art could make various modifications or alterations based on the present disclosure. Therefore, it should be noted that these modifications or alterations are included in the scope of the present disclosure. For example, the functions included in each component can be rearranged so as not to cause logical inconsistencies, and multiple components can be combined or divided into one.

[0118] For example, in the above-described embodiment, the control unit 31 in the third information processing device 26 generates the second image based on the first code image and the third code image. However, the control unit 31 may generate the second image based on only either the first code image or the third code image.

[0119] For example, in the above-described embodiment, the control unit 31 in the third information processing device 26 generates the second image by performing the second image processing on the first image in which a background image is superimposed on the second code image after the first image processing. However, the control unit 31 may generate the second image by further performing the second image processing on the second code image without superimposing the background image on the second code image.

[0120] For example, in the above-described embodiment, a first code image is generated for the purpose of detecting a code on a graphic. However, the control unit 31 may generate a first code image of a code used to identify the attributes of an item, such as a price tag or a discount sticker, generate a second code image by performing a first image processing on the first code image, and generate a learning image by superimposing the second code image on a background image. In this case, a combination of an image including, as a partial image, a product having a code used to identify the attributes of the item attached to its surface and information indicating the position of the code may be used as training data.

[0121] All of the features described in this disclosure and / or all steps of all of the disclosed methods or processes may be combined in any combination except combinations in which these features are mutually exclusive. Furthermore, each feature described in this disclosure may be replaced by an alternative feature serving the same, equivalent, or similar purpose, unless expressly denied. Thus, unless expressly denied, each disclosed feature is only one example of a generic series of identical or equivalent features.

[0122] Furthermore, embodiments of the present disclosure are not limited to the specific configurations of any of the above-described embodiments, but rather extend to any novel feature or combination thereof described herein, or any novel method or process step or combination thereof described herein.

[0123] In this disclosure, descriptions such as "first" and "second" are identifiers for distinguishing the configuration. Configurations distinguished by descriptions such as "first" and "second" in this disclosure can exchange numbers in the configuration. For example, a first information processing device can exchange identifiers "first" and "second" with a second information processing device. The exchange of identifiers is performed simultaneously. The configurations remain distinguished even after the exchange of identifiers. Identifiers may be deleted. A configuration from which an identifier has been deleted is distinguished by a symbol. The descriptions of identifiers such as "first" and "second" in this disclosure should not be used solely to interpret the order of the configuration or to justify the existence of an identifier with a smaller number. [Explanation of symbols]

[0124] 10 Information Processing Systems 11 Terminal equipment 12 Network 13 Second information processing device 14 Imaging unit 15 Output Devices 16 Mounting table 17 Support pillar 18 First information processing device (information processing device) 19 Communication Department (Acquisition Department) 20 Control Unit 21 Memory section 22 Input section 23 Communications Department 24 Memory section 25 Control Unit 26 Third information processing device 27 Input / Output Interface 28 Output section 29 Input section 30 Storage section 31 Control Unit ci Captured image lri low resolution image pia Partial image area of ​​the figure shape code pib Discount image subimage area us top surface

Claims

1. generating a first code image which is a code of the graphic shape; generating a first numeric image that is a discount image; generating a second code image by performing a first image processing on the first code image; generating a second numerical image by performing the first image processing on the first numerical image; A first image is generated by superimposing the second code image and the second numeric image on a background image. Training data generation method.

2. The training data generation method according to claim 1 , The first image processing is at least one of rotation, enlargement or reduction, distortion, blurring, transparency, and local discoloration. Training data generation method.

3. The training data generation method according to claim 1 , the background image includes an image of an item and a package containing the item; the first image processing generates the second code image in a manner that allows one or both of the product and the packaging, which are background images, to be visible through the graphical symbol; Training data generation method.

4. The training data generation method according to claim 3, the first image processing generates the second code image in which the first code image is mixed with the background image by changing the transparency of the first code image; Training data generation method.

5. The training data generation method according to claim 1 , the background image includes an image of an item; the first image processing generates the second code image by changing the graphic code in accordance with the three-dimensional shape of the article; Training data generation method.

6. The training data generation method according to claim 1 , the background image includes an image of a package; the first image processing generates the second code image by changing the graphic code in accordance with the three-dimensional shape of the package; Training data generation method.

7. The training data generation method according to any one of claims 1 to 6, generating a second image by performing a second image processing on the first image; The second image processing is a change in at least one of color and contrast of the entire first image. Training data generation method.

8. The training data generation method according to claim 1 , obtaining a third code image which is a code of the graphic shape; generating the first image based on the third code image; Training data generation method.

9. A computer that outputs a partial image of a graphic symbol in an input image after learning using the second image generated by the learning data generation method according to claim 7. A trained model for making a computer function.

10. A trained model for causing a computer to function so as to output, for an input image, an area of ​​a partial image of a graphical symbol and an area of ​​a partial image of a discount image, the area being trained using a first image generated by the training data generation method described in any one of claims 1 to 6.

11. an acquisition unit that acquires the captured image; a control unit that inputs the captured image into a detection model to extract a partial image of a graphic symbol and a partial image of a discount image, decodes the symbol based on the extracted partial image of the graphic symbol, and recognizes the discount image based on the extracted partial image of the discount image, The detection model is a trained model according to claim 9. Information processing device.

12. 12. The information processing device according to claim 11, The control unit detects the area of ​​the partial image in the low-resolution image by inputting a low-resolution image obtained by reducing the resolution of the captured image into the detection model, and decodes the code based on the detected partial image. Information processing device.

13. Acquire the captured image, The captured image is input to a detection model to extract a partial image of a graphic symbol and a partial image of a discount image; Decoding the code based on the extracted partial image of the graphic code; Recognizing the discount image based on the extracted partial image of the discount image; The detection model is a trained model according to claim 9. Information processing methods.

14. generating a first code image used to identify an attribute of the item; generating a second code image by performing a first image processing on the first code image; A method for generating a learning image by superimposing the second code image on a background image including an image of the item and a package containing the item, comprising: The first image processing is a process of reproducing a state in which at least one of the item and a package containing the item can be seen through the first code image. Training data generation method.

Images