Image processing device, image processing method, and program

Abstract

An image processing device (10) processes an image containing a shelf label, and has an image processing unit (120) and a price attribute identifying unit (130). The image processing unit (120) processes the image containing the shelf label and thus identifies a feature item which is at least one of a first color that is the color of at least a partial region of the shelf label, a second color that is the color of characters (e.g., numbers indicating a price) in the shelf label, the size of the characters, and the size of the shelf label. Further, the image processing unit (120) identifies a price indicated on the shelf label by image processing (e.g., character recognition processing). The price attribute identifying unit (130) identifies the attribute of price using the feature item. The attribute of price at least indicates that the price is a normal price or a limited-time price.

Description

[Technical Field]

[0001] The present invention relates to an image processing device, an image processing method, and a program. [Background technology]

[0002] In a store, shelves on which products are placed are provided with shelf tags (price tags). If the information written on the shelf tag is incorrect, customers and store clerks will mistakenly recognize the information about the product. For this reason, there is a demand for a device that can read the information written on the shelf tag. For example, Patent Document 1 describes a device that recognizes the information written on the shelf tag by processing an image of the shelf tag. Specifically, ,shelf On the tag, the JAN (Japanese Article Number) code and the price are written in different colors. The matching determination device uses these colors to recognize the JAN code and the price and determine the correspondence between the recognized JAN code and the price. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2016-194834 Summary of the Invention [Problem to be solved by the invention]

[0004] In stores, the prices of items, such as merchandise, are sometimes reduced for a limited time. In this case, the label on the shelf must be changed to indicate that the price is for a limited time only, and then the label must be returned to its normal state after the period ends. However, if these changes are forgotten, customers may misinterpret the information about the item. To prevent this, it is preferable for staff to be able to determine the attributes of the price displayed on the shelf label (for example, whether it is the normal price or a limited-time price) with minimal effort.

[0005] An object of the present invention is to make it possible to determine the attributes of a price displayed on a shelf tag (for example, whether it is a regular price or a limited-time price) with little effort. [Means for solving the problem]

[0006] According to the present invention, by processing an image including a shelf tag, a first color which is the color of at least a part of the area of ​​the shelf tag, a second color which is the color of the characters included in the shelf tag, the size of the characters, and the size of the shelf tag can be determined. At least one of an image processing means for identifying the characteristic items and the price indicated on the shelf tag; a price attribute specifying means for specifying an attribute of the price using the characteristic item; An image processing apparatus is provided, comprising:

[0007] According to the present invention, a computer by processing an image including a shelf tag, identifying at least one of a first color that is the color of at least a partial area of ​​the shelf tag, a second color that is the color of characters included in the shelf tag, the size of the characters, and the size of the shelf tag, and identifying the price indicated on the shelf tag; An image processing method is provided that uses the feature items to identify the price attributes.

[0008] According to the present invention, a computer is provided with: a function of processing an image including a shelf tag to identify at least one of the following characteristic items: a first color that is the color of at least a partial area of ​​the shelf tag; a second color that is the color of characters included in the shelf tag; the size of the characters; and the size of the shelf tag, and to identify the price indicated on the shelf tag; a function of identifying attributes of the price using the feature items; A program to help them develop this skill will be provided. [Effects of the Invention]

[0009] According to the present invention, the attributes of the price displayed on the shelf tag (for example, whether it is a regular price or a limited-time price) can be determined with little effort. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram illustrating a functional configuration of an image processing apparatus according to an embodiment. [Figure 2] FIG. 4 is a diagram illustrating an example of information stored in a first storage unit. [Figure 3] FIG. 4 is a diagram illustrating an example of information stored in a second storage unit. [Figure 4] FIG. 1 is a block diagram illustrating a hardware configuration of an image processing apparatus. [Figure 5] 1 is a flowchart showing a first example of processing performed by the image processing device. [Figure 6] 10 is a flowchart showing a second example of processing performed by the image processing device. [Figure 7] 10 is a flowchart showing a third example of processing performed by the image processing device. [Figure 8] 10 is a flowchart showing a fourth example of processing performed by the image processing device. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, like components are designated by like reference numerals, and the description thereof will be omitted as appropriate.

[0012] FIG. 1 is a diagram illustrating the functional configuration of an image processing device 10 according to an embodiment. The image processing device 10 processes images including shelf tags and includes an image processing unit 120 and a price attribute identification unit 130. The image processing unit 120 processes images including shelf tags to identify at least one of the following features: a first color, which is the color of at least a portion of the shelf tag; a second color, which is the color of the characters (e.g., numbers indicating the price) included in the shelf tag; the size of the characters; and the size of the shelf tag. The image processing unit 120 also identifies the price indicated on the shelf tag through image processing (e.g., character recognition processing). The price attribute identification unit 130 identifies price attributes using at least one of the first color, second color, character size, and shelf tag size, i.e., the above-mentioned features. The price attributes include at least whether the price is a regular price or a limited-time price. As an example, the price attribute identification unit 130 determines whether the price indicated on the shelf tag is a regular price or a limited-time price. The image processing device 10 will be described in detail below.

[0013] The image processing device 10 has an acquisition unit 110, a first storage unit 140, a second storage unit 150, a price range identification unit 160, and an output unit 170, in addition to the image processing unit 120 and price attribute identification unit 130 described above.

[0014] The acquisition unit 110 acquires an image to be processed by the image processing unit 120, i.e., an image including a price tag, from the user terminal 20. The user terminal 20 is, for example, a portable terminal carried by a user of the image processing device 10, and has a photographing function. The user takes a picture of a shelf in a store to generate an image. This image includes items placed on the shelf (for example, a product: hereinafter referred to as a product) and shelf tags. The user terminal 20 transmits the generated image to the image processing device 10. Along with this image, the user terminal 20 transmits information identifying the store in which the shelf that was the subject of the photograph is installed (hereinafter referred to as store identification information), and the conditions under which the image was generated (hereinafter referred to as generation conditions). The generation conditions include at least the date and time the image was generated. The acquisition unit 110 also receives the store identification information and generation conditions.

[0015] The image processing unit 120 processes the image transmitted by the user terminal 20 to identify at least one (preferably all) of the first color, second color, character size, and shelf label size described above. For example, the image processing unit 120 identifies the shelf label area from the image by performing processing using feature amounts. Then, by processing this identified area, the first color, second color, character size, and shelf label size are identified. As described above, the first color is the color of at least a portion of the shelf label area, and this "at least a portion of the area" may be, for example, the edge of the shelf label or the entire shelf label. Note that at least a portion of the processing performed by the image processing unit 120 may be performed using the results of machine learning.

[0016] Furthermore, the image processing unit 120 performs character recognition processing on the area of ​​the shelf label to identify the type of product and the price of that product corresponding to that shelf label. For example, the image processing unit 120 identifies the product name or JAN code written on the shelf label through character recognition processing to identify the type of product (e.g., product name) corresponding to that shelf label. The image processing unit 120 also identifies the price of that product through character recognition processing.

[0017] As described above, the price attribute identification unit 130 identifies the attributes of the price written on the shelf tag. For example, the price attribute identification unit 130 stores in advance the first color, second color, character size, and shelf tag size for each price attribute. For example, for a regular price, the first and second colors are black, and the character size and shelf tag size are also in a relatively small range. In contrast, for a limited-time price, the first and second colors are warm colors (e.g., red or orange), and the character size and shelf tag size are larger than those for the regular price. Also, only the font size differs between the regular price and the limited time price. different In some cases, the price attribute identification unit 130 identifies the price attribute using this pre-stored information, as well as the first color, second color, character size, and shelf tag size identified by the image processing unit 120.

[0018] The first storage unit 140 stores the price attributes identified by the price attribute identification unit 130 in association with the store indicated by the store identification information acquired by the acquisition unit 110. First storage section 140 The first storage unit 140 also stores information generated by the image processing unit 120. The first storage unit 140 stores information indicating the transition of these pieces of information.

[0019] The second storage unit 150 stores the regular price and sale price of each product by store and by product type. These prices may or may not have a range. The second storage unit 150 is updated as needed, for example, by a store clerk.

[0020] The price range identification unit 160 identifies a price range by attribute of the price of a product (for example, a price range of regular prices and a price range of limited-time prices) by store and by product type, by processing the information stored in the first storage unit 140. For example, the price range identification unit 160 generates information for identifying a price range, including the highest and lowest prices within a predetermined period in the past, by price attribute, and stores the information in the first storage unit 140 as necessary.

[0021] The output unit 170 reads out the information stored in the first storage unit 140 and outputs it to the user terminal 20. The output unit 170 also outputs predetermined information (for example, warning information or error notification) to the user terminal 20 as necessary. Details of this processing will be described later using a flowchart.

[0022] FIG. 2 is a diagram illustrating an example of information stored in the first storage unit 140. In the example illustrated in this figure, the first storage unit 140 stores, for each store and each product, the images processed by the image processing unit 120 and their generation conditions (e.g., generation date and time), the processing results of the image processing unit 120, and the processing results of the price attribute identification unit 130. The processing results of the image processing unit 120 include, for example, the first color, second color, character size, shelf tag size, and price. The processing results of the price attribute identification unit 130 include price attributes. Although not illustrated, the first storage unit 140 also stores historical data (log data) of this information. Furthermore, the first storage unit 140 also stores price ranges by price attribute determined by the price range identification unit 160 (e.g., the highest and lowest prices over a predetermined period of time (e.g., one year) in the past).

[0023] 3 is a diagram showing an example of information stored in the second storage unit 150. As described above, the second storage unit 150 stores the regular price and sale price of each product for each store and each type of product.

[0024] 4 is a block diagram illustrating an example of the hardware configuration of the image processing device 10. The image processing device 10 includes a bus 1010, a processor 1020, a memory 1030, a storage device 1040, an input / output interface 1050, and a network interface 1060.

[0025] The bus 1010 is a data transmission path for transmitting and receiving data among the processor 1020, memory 1030, storage device 1040, input / output interface 1050, and network interface 1060. However, the method of connecting the processor 1020 and the like to each other is not limited to bus connection.

[0026] The processor 1020 is implemented by a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or the like.

[0027] The memory 1030 is a main storage device realized by a RAM (Random Access Memory) or the like.

[0028] The storage device 1040 is an auxiliary storage device realized by an HDD (Hard Disk Drive), an SSD (Solid State Drive), a memory card, a ROM (Read Only Memory), or the like. The storage device 1040 stores program modules that realize each function of the image processing device 10 (e.g., the acquisition unit 110, the image processing unit 120, the price attribute identification unit 130, the price range identification unit 160, and the output unit 170). The processor 1020 loads each of these program modules into the memory 1030 and executes them, thereby realizing each function corresponding to the program module. The storage device 1040 also functions as various storage units (e.g., the first storage unit 140 and the second storage unit 150).

[0029] The input / output interface 1050 is an interface for connecting the image processing device 10 to various input / output devices.

[0030] The network interface 1060 is an interface for connecting the image processing device 10 to other devices (for example, the user terminal 20) on the network.

[0031] 5 is a flowchart showing a first example of processing performed by the image processing device 10. The processing shown in this figure is processing for identifying a price attribute.

[0032] First, the user of the user terminal 20 photographs a product shelf in a desired store (for example, the store where the user works or supervises) and transmits the image generated by this photograph to the image processing device 10 together with the store identification information of the store and the conditions for generating the image (for example, the date and time of generation). This process may be performed each time an image is generated. Alternatively, the user of the user terminal 20 may photograph different locations on the product shelf and transmit multiple images generated by these photographs together to the image processing device 10.

[0033] When the user terminal 20 transmits the image and store identification information, the acquisition unit 110 of the image processing device 10 acquires the image, the image generation conditions, and the store identification information (step S10). The image processing unit 120 of the image processing device 10 then processes the image acquired by the acquisition unit 110 to identify the shelf label area (step S20). If the image contains multiple shelf labels, the image processing unit 120 identifies the areas of each of these multiple shelf labels. Next, the image processing unit 120 processes the identified shelf label area to identify the first color, second color, character size, shelf label size, and price (step S30).

[0034] Next, the price attribute specification unit 130 specifies the price attribute by processing the information specified in step S30 (step S40), and Attributes In this case, the image processing unit 120 or the price attribute specification unit 130 stores the image to be processed and its generation conditions (for example, generation date and time) in the first storage unit 140 (step S50). identification The first color, second color, character size, shelf tag size, and price are also stored in the first storage unit 140.

[0035] If multiple shelf label areas are identified in step S20, the processes shown in steps S30 to S50 are performed for each of these multiple shelf label areas.

[0036] Furthermore, if one image contains multiple shelf tags, in step S40, the price attribute specification unit 130 specifies at least one of the feature items of the first color, second color, character size, and shelf tag size of the shelf tag of the first product, and the feature items of the shelf tag of the second product. That is, The first color, second color, character size, and shelf tag size are used to create the first Product A price attribute for the shelf tag may be specified.

[0037] For example, if the price attribute of the second product is specified as the regular price, the price attribute specification unit 130 determines that the price of the first product is the regular price if the first color, second color, character size, and shelf tag size of the shelf tag of the first product match all of the first color, second color, character size, and shelf tag size of the shelf tag of the second product.On the other hand, if at least one of the first color, second color, character size, and shelf tag size is different, the price attribute specification unit 130 determines that the price of the first product is a limited-time price.

[0038] 6 is a flowchart showing a second example of the processing performed by the image processing device 10. The processing shown in this figure is processing for identifying price ranges by store and by price attribute.

[0039] First, the price range identification unit 160 acquires store identification information and information identifying the target product from the user terminal 20 (step S110). Then, the price range identification unit 160 reads out the price history corresponding to the combination of the acquired store identification information and information identifying the target product from the first storage unit 140 (step S120), and identifies the price range using the read history (step S130). As an example of this process, as described above, the highest and lowest prices within a predetermined period of time in the past are generated as information identifying the price range. However, here, the price range identification unit 160 may also generate a predetermined (e.g., second) highest and lowest prices as information identifying the price range.

[0040] The price range specification unit 160 then identification The result is output to the user terminal 20 (step S140).

[0041] The price range specification unit 160 receives the price range information from the user terminal 20. ofThe above-described price range specification process may be performed for predetermined stores and products (for example, all stores and products) at a timing unrelated to the input (for example, at regular intervals). In this case, the price range specification unit 160 associates the specified price range with store identification information, product identification information, and price attributes, and stores the associated price range in the first storage unit 140. Then, when the price range specification unit 160 receives the store identification information and product identification information from the user terminal 20, it reads out the price range of each attribute corresponding to the received store identification information and product identification information from the first storage unit 140 and transmits the price range to the user terminal 20.

[0042] 7 is a flowchart showing a third example of processing performed by the image processing device 10. In the example shown in this figure, the first storage unit 140 stores the price range of each attribute for each store identification information and product. The processing from steps S10 to S40 is the same as the example shown in FIG.

[0043] When the price attribute identification unit 130 identifies the price attributes (step S40), the output unit 170 reads out from the first storage unit 140 the price range corresponding to the combination of store identification information, information identifying the type of product, and price attributes. The output unit 170 then determines whether the price identified in step S30 is within the read price range. If it is within the price range (step S42: Yes), the first storage unit 140 is updated (step S50), as in the example shown in FIG. 5. On the other hand, if it is outside the price range (step S42: No), the price on the shelf label may be incorrect, and the output unit 170 therefore outputs a predetermined signal (e.g., an error notification) to the user terminal 20 (step S52). This prevents incorrect prices from being set.

[0044] Fig. 8 is a flowchart showing a fourth example of processing performed by the image processing device 10. The example shown in this figure is similar to the example shown in Fig. 7, except that step S44 is performed instead of the processing shown in step S42.

[0045] In step S44, the output unit 170 determines whether the price identified by the image processing unit 120 is the same as the price stored in the second storage unit 150 corresponding to the attribute identified by the price attribute identification unit 130. If they are the same (step S44: Yes), an update process for the first storage unit 140 is performed (step S50), as in the example shown in FIG. 5. If they are different, the price on the shelf tag may be incorrect, so the output unit 170 performs a predetermined output (for example, an error notification) to the user terminal 20 (step S52). This makes it possible to prevent an incorrect price from being set.

[0046] In step S44, there is a possibility that the limited-time price is not stored in the second storage unit 150. Therefore, if the result of identification by the price attribute identification unit 130 indicates that the product is limited to a certain time and the limited-time price is not stored in the second storage unit 150, the output unit 170 outputs the price identified by the image processing unit 120 and the regular price stored in the second storage unit 150. of If the price identified by the image processing unit 120 is lower than the regular price, the image processing device 10 proceeds to step S50, otherwise proceeds to step S52.

[0047] As described above, according to this embodiment, the attribute of the price written on the shelf tag (for example, whether it is a regular price or a limited-time price) can be determined with little effort. This makes it possible to prevent forgetting to change the price written on the shelf tag.

[0048] Although the embodiments of the present invention have been described above with reference to the drawings, these are merely examples of the present invention, and various other configurations can also be adopted.

[0049] In addition, in the flowcharts used in the above description, multiple steps (processes) are described in order, but the order of execution of the steps performed in each embodiment is not limited to the order described. In each embodiment, the order of the steps shown in the drawings can be changed to the extent that the content is not affected. Furthermore, the above-mentioned embodiments can be combined to the extent that the content is not contradictory.

[0050] Some or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes. 1. An image processing means for processing an image including a shelf tag to identify at least one of the following characteristic items: a first color which is the color of at least a partial area of ​​the shelf tag; a second color which is the color of characters included in the shelf tag; the size of the characters; and the size of the shelf tag, and to identify the price indicated on the shelf tag; a price attribute specifying means for specifying an attribute of the price using the characteristic item; An image processing device comprising: 2. In the image processing device described in 1 above, The image processing device, wherein the attributes include at least a regular price and a limited-time price. 3. In the image processing device described in 2 above, the image includes the shelf tag of a first item for which the attribute is to be determined and the shelf tag of a second item at a regular price; The price attribute specification means uses the feature items of the shelf tag of the first item and the feature items of the shelf tag of the second item to specify the price attribute of the first item. of goods An image processing device that identifies the price attribute of the shelf tag. 4. In the image processing device according to any one of the above items 1 to 3, the price attribute specification means stores the prices and the attributes in correspondence with each other for each type of product in a first storage means; The image processing device further comprises a price range specifying means for specifying a price range for each attribute of the item using the price and the attribute stored in the first storage means. 5. In the image processing device described in 4 above, The image processing device includes an output means for outputting a predetermined output when the price indicated on the shelf tag is outside the attribute-specific price range corresponding to the price. 6. In the image processing device according to any one of the above items 1 to 5, an error processing means for reading out a price corresponding to the attribute identified by the price attribute identification means from a second storage means storing prices by attribute, and for performing an error processing if the price differs from the price identified by the image processing means; An image processing device comprising: 7. The computer by processing an image including a shelf tag, identifying at least one of a first color that is the color of at least a partial area of ​​the shelf tag, a second color that is the color of characters included in the shelf tag, the size of the characters, and the size of the shelf tag, and identifying the price indicated on the shelf tag; An image processing method that uses the feature items to identify the price attribute. 8. In the image processing method described in 7 above, The image processing method, wherein the attributes include at least a regular price and a limited-time price. 9. In the image processing method described in 8 above, the image includes the shelf tag of a first item for which the attribute is to be determined and the shelf tag of a second item at a regular price; The computer uses the feature items of the shelf label of the first item and the feature items of the shelf label of the second item to calculate the first of goods An image processing method for identifying the price attribute of a shelf tag. 10. In the image processing method according to any one of the above items 7 to 9, The computer storing the prices and the attributes in correspondence with each other for each type of product in a first storage means; Furthermore, the image processing method specifies a price range for each attribute of the item using the price and the attribute stored in the first storage means. 11. In the image processing method according to claim 10, An image processing method in which the computer performs a predetermined output when the price indicated on the shelf tag is outside the attribute-specific price range corresponding to the price. 12. In the image processing method according to any one of the above items 7 to 11, The computer reads from a second storage means storing the prices by attribute. , special The image processing method reads out a price corresponding to the specified attribute, and performs error processing if the price differs from the specified price. 13. On the computer, a function of processing an image including a shelf tag to identify at least one of the following characteristic items: a first color that is the color of at least a partial area of ​​the shelf tag; a second color that is the color of characters included in the shelf tag; the size of the characters; and the size of the shelf tag, and to identify the price indicated on the shelf tag; a function of identifying attributes of the price using the feature items; A program that allows you to have 14. In the program according to 13 above, The program wherein the attributes include at least a regular price and a limited time price. 15. In the program according to 14 above, the image includes the shelf tag of a first item for which the attribute is to be determined and the shelf tag of a second item at a regular price; The computer uses the feature items of the shelf label of the first item and the feature items of the shelf label of the second item to calculate the first of goods A program that identifies attributes of the price of a shelf label. 16. In the program according to any one of 13 to 15 above, The computer, storing the prices and the attributes in correspondence with each other for each type of product in a first storage means; Furthermore, a program for specifying a price range for each attribute of the item using the price and the attribute stored in the first storage means. 17. In the program according to 16 above, A program that causes the computer to perform a predetermined output when the price indicated on the shelf tag is outside the attribute-specific price range corresponding to the price. 18. In the program according to any one of 13 to 17 above, The computer receives the price information from a second storage means storing the attribute-specific prices. , special a program that reads out a price corresponding to the specified attribute, and performs error processing if the price differs from the specified price. 19. Image processing means for processing an image including a shelf tag to identify the price displayed on said shelf tag; an output means for outputting a predetermined output when the price does not satisfy a predetermined standard; An image processing device comprising:

[0051] This application claims priority based on Japanese Patent Application No. 2019-174285, filed September 25, 2019, the disclosure of which is incorporated herein by reference in its entirety. [Explanation of symbols]

[0052] 10 Image processing device 20 User terminal 110 Acquisition Department 120 Image processing unit 130 Price attribute specification section 140 1st memory section 150 2nd memory section 160 Price Range Specific Section 170 Output section

Claims

1. an image processing means for identifying an image area of ​​the shelf tag based on feature amounts of an image including the shelf tag, and then identifying at least one feature item from among a first color that is the color of at least a portion of the image area, a second color that is the color of characters included in the image area, the size of the characters, and the size of the shelf tag, based on the feature amounts of the image area and the results of character recognition processing on the image area, and for identifying the price shown on the shelf tag; a price attribute specifying means for specifying an attribute of the price using the characteristic item; Equipped with The attributes include at least a regular price and a limited-time price; the price attribute specification means refers to first definition information indicating the characteristic item corresponding to the normal price and second definition information indicating the characteristic item corresponding to the limited-time price, and specifies that the price indicated on the shelf tag is the normal price if the specified characteristic item matches the characteristic item indicated by the first definition information, and specifies that the price indicated on the shelf tag is the limited-time price if the specified characteristic item matches the characteristic item indicated by the second definition information. Image processing device.

2. 2. The image processing device according to claim 1, When the image includes a first shelf label that is the shelf label of a first item and a second shelf label that is the shelf label of a second item, In response to the image processing means identifying an attribute of the price indicated on the first shelf tag based on the first feature item related to the first shelf tag, comparing the first characteristic item with a second characteristic item related to the second shelf label; If the first feature item and the second feature item match, the attribute of the price displayed on the second shelf label is determined to be the same attribute as the attribute of the price displayed on the first shelf label. Image processing device.

3. 3. The image processing device according to claim 1, the price attribute specification means stores the price specification results and the attribute specification results in a first storage means in association with each other for each type of product; The image processing device further includes a price range specification means for specifying a price range for the item by attribute using price trend information that indicates the price trends obtained from the price specification results and the attribute specification results stored in the first storage means by attribute.

4. 4. The image processing device according to claim 3, The image processing device is provided with an output means that, in response to the attribute of the price indicated on the shelf tag being identified by the price attribute identification means, acquires information indicating a price range by attribute corresponding to the attribute, and, when the price indicated on the shelf tag is outside the price range by attribute indicated by the information, outputs a notification indicating that the price may be set incorrectly.

5. 5. The image processing device according to claim 1, an error processing means for reading out a price corresponding to the attribute identified by the price attribute identification means from a second storage means storing prices by attribute, and outputting a notification indicating that the price may be set incorrectly if the price differs from the price identified by the image processing means; An image processing device comprising:

6. The computer an image area of ​​the shelf tag is identified based on a feature amount of an image including the shelf tag, and then, based on the feature amount of the image area and a result of character recognition processing on the image area, at least one feature item is identified from among a first color that is the color of at least a portion of the image area, a second color that is the color of characters included in the image area, a size of the characters, and a size of the shelf tag, and the price shown on the shelf tag is identified; using the feature to identify an attribute of the price; The attributes include at least a regular price and a limited-time price; the computer refers to first definition information indicating the feature item corresponding to the regular price and second definition information indicating the feature item corresponding to the limited-time price, and if the identified feature item matches the feature item indicated by the first definition information, identifies the price indicated on the shelf tag as the regular price, and if the identified feature item matches the feature item indicated by the second definition information, identifies the price indicated on the shelf tag as the limited-time price; Image processing methods.

7. On the computer, a function of identifying an image area of ​​the shelf tag based on a feature amount of an image including the shelf tag, and then identifying at least one feature item from among a first color that is the color of at least a portion of the image area, a second color that is the color of characters included in the image area, the size of the characters, and the size of the shelf tag, based on the feature amount of the image area and the results of character recognition processing on the image area, and also identifying the price shown on the shelf tag; a function of identifying attributes of the price using the feature items; Let them have The attributes include at least a regular price and a limited-time price; The function of identifying the price attribute refers to first definition information indicating the characteristic item corresponding to the normal price and second definition information indicating the characteristic item corresponding to the limited-time price, and identifies the price indicated on the shelf tag as the normal price if the identified characteristic item matches the characteristic item indicated by the first definition information, and identifies the price indicated on the shelf tag as the limited-time price if the identified characteristic item matches the characteristic item indicated by the second definition information. program.

Images