A method and device for detecting product information

Abstract

The present application discloses a method and device for detecting product information, including: determining an information template corresponding to a target product, and determining a first positioning tag in the information template; photographing an image of the target product to be detected in a detection area; locating a target area in the image to be detected according to the first positioning tag; determining product information of the target product in the target area using the information template; locating the target area in the image to be detected according to the first positioning tag in the information template; determining product information of the target product in the target area using the information template; realizing automatic extraction of various types of product information, avoiding the problem in the prior art that only barcodes and QR codes can be used for information recognition, and improving detection performance.

Description

Technical Field

[0001] The present application relates to the field of image analysis technology, and in particular to a method and device for detecting product information. Background Art

[0002] In the production and logistics process of industrial products, product information needs to be detected in many links to facilitate automated information identification, entry and management. Product information may exist on the outer packaging of the product or on the outer shell of the product; and it can be presented in the form of labels, icons, barcodes, QR codes, etc.

[0003] At the current stage, product information is usually detected automatically. However, in existing product information detection solutions, information recognition is usually performed on parts of images with very obvious features such as barcodes and QR codes to extract product information. In other words, the existing technology has limited recognition and detection capabilities for product information such as labels or icons. Summary of the invention

[0004] The present application provides a method and device for detecting product information to at least solve the above technical problems existing in the prior art.

[0005] In a first aspect, the present application provides a method for detecting product information, comprising:

[0006] Determine an information template corresponding to the target product, and determine a first positioning tag in the information template;

[0007] Capturing an image of the target product to be inspected in the inspection area;

[0008] Locating a target area in the image to be detected according to the first positioning tag;

[0009] The product information of the target product is determined in the target area using the information template.

[0010] Preferably, before determining the information template corresponding to the target product, the method further includes:

[0011] Generate the corresponding information template according to a packaging design or product design corresponding to at least one candidate product;

[0012] The candidate products include the target product; the information template includes a first positioning tag, a first information tag and a first identification icon.

[0013] Preferably, the information template corresponding to the target product is determined to include:

[0014] Determining the product type of the target product;

[0015] According to the product type of the target product, an information template corresponding to the target product is determined.

[0016] Preferably, locating the target area in the image to be detected according to the first positioning tag includes:

[0017] Based on image recognition technology, determining a second positioning tag corresponding to the first positioning tag in the image to be detected;

[0018] Performing position matching using the first positioning tag and the second positioning tag to determine an edge contour line of the target product;

[0019] The target area is determined according to the edge contour line of the target product.

[0020] Preferably, the using the first positioning tag and the second positioning tag to perform position matching to determine the edge contour line of the target product includes:

[0021] In the information template, determining the relative position relationship between the first positioning label and the product outline;

[0022] The first positioning tag and the second positioning tag are overlapped, and according to the relative position relationship, the product contour is projected onto the image to be detected to determine the edge contour line.

[0023] Preferably, the using the information template to determine the product information of the target product in the target area includes:

[0024] Based on image recognition technology, determining a second information tag corresponding to the first information tag in the target area;

[0025] The product information of the target product is determined from the second information tag according to the information distribution position in the first information tag.

[0026] Preferably, the using the information template to determine the product information of the target product in the target area includes:

[0027] Based on the image recognition technology, it is determined whether there is a second identification icon matching the first identification icon in the target area.

[0028] In a second aspect, the present application provides a device for detecting product information, comprising:

[0029] A template determination module, used to determine the information template corresponding to the target product, and determine the first positioning tag in the information template;

[0030] An image determination module, used for capturing and obtaining an image of the target product to be detected in the detection area;

[0031] A positioning module, used for locating a target area in the image to be detected according to the first positioning tag;

[0032] The information detection module is used to determine the product information of the target product in the target area by using the information template.

[0033] In a third aspect, the present application provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the product information detection method described in the present application.

[0034] In a fourth aspect, the present application provides an electronic device, including:

[0035] processor;

[0036] a memory for storing instructions executable by the processor;

[0037] The processor is used to read the executable instructions from the memory and execute the instructions to implement the product information detection method described in this application.

[0038] Compared with the prior art, the present application provides a method and device for detecting product information, which locates a target area in the image to be detected according to a first positioning tag in an information template; determines the product information of a target product in the target area by using the information template; and realizes automatic extraction of various types of product information, avoiding the problem in the prior art that only barcodes and QR codes can be used for information recognition, thereby improving detection performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A flowchart of a method for detecting product information provided in one embodiment of the present application;

[0040] Figure 2 A schematic diagram of an information template in a method for detecting product information provided in an embodiment of the present application;

[0041] Figure 3 A schematic diagram of an image to be detected in a method for detecting product information provided in an embodiment of the present application;

[0042] Figure 4 A flowchart of another method for detecting product information provided in an embodiment of the present application;

[0043] Figure 5 A schematic diagram of the structure of a device for detecting product information provided in one embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to make the purpose, features, and advantages of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0045] Application Overview

[0046] The product information of industrial products may be on the outer packaging of the product or on the outer shell of the product. For example, on the outer packaging of industrial products, there may be certain labels attached or sprayed; the label displays the product model, serial number, production batch and other specific information. In addition, there may also be various barcodes, QR codes and other labels; as well as fireproof labels, fragile labels, energy labels and other common labels.

[0047] In the prior art, product information can be obtained through automatic detection, so as to facilitate automated information recognition, entry and management. However, in the existing product information detection scheme, information recognition is usually performed on parts with very obvious image features such as barcodes and QR codes to extract product information. In other words, the prior art has limited recognition and detection capabilities for product information such as labels or icons.

[0048] Exemplary Methods

[0049] Therefore, the present application embodiment will provide a method for detecting product information to at least solve the above technical problems existing in the prior art. Figure 1 As shown, the method in this embodiment includes the following steps:

[0050] Step 101: Determine an information template corresponding to a target product, and determine a first positioning tag in the information template.

[0051] The target product is the industrial product whose product information needs to be detected in this embodiment. The product information is various specific information about the target product. The product information can be present on the outer packaging of the product or on the outer shell of the product.

[0052] In order to realize the recognition and detection of product information such as labels or icons, an information template can be manually established before the implementation of step 101. The information template can reflect the specific position of each label or icon on the product packaging (or product shell); at the same time, the format of the label can also be set in the information template, that is, the position and content of various types of product information in the label column.

[0053] However, the process of manually establishing information templates is relatively inefficient, so it is preferred that before determining the information template corresponding to the target product, a corresponding information template can be generated based on a packaging design or product design corresponding to at least one candidate product. In other words, the specific location of each label or icon, as well as the necessary information in various information templates such as the label format, can be determined based on the packaging design or product design, so as to automatically establish the information template. Among them, the candidate products may include multiple types, that is, information templates corresponding to multiple industrial products are established to facilitate subsequent wider application. The candidate products will include the target product.

[0054] The information template may include a first positioning tag, a first information tag, and a first identification icon. The information template may be specifically as follows: Figure 2 As shown. Figure 2 In the figure, the rectangular box in the lower left corner represents the first information tag, which is a tag that reflects product information. The first information tag presents product information in a table-like manner, and the three tag columns are respectively filled with the product name, product model, and SN number of the target product. The first positioning tag can be a tag with a fixed position and obvious image features, which can be used to locate the target product in subsequent steps to determine the specific location of the target product. In this embodiment, the first positioning tag can be as follows: Figure 2 The fireproof mark shown in the upper right corner. The first identification icon can refer to other icons that appear on the product packaging or shell, such as the fragile mark, energy mark, etc.

[0055] After establishing at least one information template of the candidate product, the present embodiment will also determine the information template corresponding to the target product. Specifically, the product type of the target product can be determined. For example, first scan the barcode, QR code or other obvious mark on the product packaging or shell to intuitively confirm the product type, that is, determine the specific model of the product. Then, according to the product type of the target product, determine the information template corresponding to the target product.

[0056] Step 102: photograph and obtain an image of the target product to be inspected in the inspection area.

[0057] After the target product arrives at the detection area for product information detection, the camera in the detection area can be used to shoot the target product to obtain the corresponding image to be detected. The detection area may be located in a production line, a logistics transportation line, or any other scene where product information detection is required. The detection area has a certain spatial range, and when each target product is placed in the detection area, there may be some discrepancies in the specific placement position.

[0058] The image to be detected is Figure 3As shown in the figure, the dotted rectangle in the image represents the target product. It can be seen that the actual placement of the target product is not located in the center of the detection area, and it is not an orthogonal angle. It is also understandable that due to the shooting effect, the edge contour of the target product may be somewhat blurred.

[0059] Step 103: locate the target area in the image to be detected according to the first positioning tag.

[0060] pass Figure 3 It can be seen that the actual placement of the target product is not located in the center of the detection area, nor is it an orthogonal angle; and due to the shooting effect, the edge contour of the target product may be somewhat blurred. Therefore, after determining the image to be detected, the first positioning tag mentioned above will be used to further locate the target product in the image to be detected, so as to determine the range where the target product is located, that is, the target area in the image to be detected.

[0061] Specifically, based on image recognition technology, the second positioning tag corresponding to the first positioning tag can be determined in the image to be detected. Taking the first positioning tag as a fire prevention label as an example, in this step, the position of the fire prevention label in the image to be detected can be determined by image recognition. Figure 3 In the example, the fireproof mark is located at the position of the dotted circle. Further, the first positioning tag and the second positioning tag can be used for position matching to determine the edge contour line of the target product; and the target area can be determined according to the edge contour line of the target product. Figure 3 The determined edge contour is shown as a dotted rectangle.

[0062] That is to say, it can be considered that the position of the positioning label (i.e., fire prevention label) in the information template and in the target area should be relatively unchanged. Therefore, for the position matching of the first positioning label and the second positioning label, the following specific method can be adopted: in the information template, determine the relative position relationship between the first positioning label and the product contour; overlap the first positioning label and the second positioning label, and project the product contour onto the image to be detected based on the relative position relationship to determine the edge contour line. That is to say, after the first positioning label in the information template and the second positioning label in the image to be detected are overlapped, it can be determined based on the relative position relationship that the projection of the product contour falls on the image to be detected, thus forming the dotted rectangle.

[0063] Then, the range of the dotted rectangle in the image to be detected can be extracted as the target area. The target area represents the image area where the target product is located in the image to be detected.

[0064] Step 104: Determine the product information of the target product in the target area using the information template.

[0065] After the target area is determined, subsequent product information detection can be performed on the target area. In this embodiment, product information detection can be performed in the following specific manner:

[0066] Based on the image recognition technology, the second information tag corresponding to the first information tag is determined in the target area; according to the information distribution position in the first information tag, the product information of the target product is determined from the second information tag. In other words, it can also be considered that the position of the information tag in the information template and in the target area should be relatively unchanged, so according to the position of the first information tag in the information template, the second information tag in the target area can be found.

[0067] At the same time, it can be considered that the specific formats of the first information label and the second information label are also unchanged. According to the setting of the first information label, it can be considered that the three label columns of the second information label are filled with the product name, product model and SN number of the target product respectively. That is, in fact, the product name of the target product is "laptop computer", the product model is "T100", and the SN number is "R90TLP".

[0068] So far, the present embodiment has realized the detection and acquisition of specific product information of the target product.

[0069] Through the above technical scheme, it can be seen that the beneficial effects of this embodiment are: according to the first positioning label in the information template, the target area is located in the image to be detected; the product information of the target product is determined in the target area using the information template; and the automatic extraction of various types of product information is realized, avoiding the problem in the prior art that only barcodes and QR codes can be used for information recognition, thereby improving the detection performance.

[0070] Figure 1 What is shown is only a basic embodiment of the method described in this application. By performing certain optimization and expansion on this basis, other preferred embodiments of the method can be obtained.

[0071] like Figure 4 As shown, another specific embodiment of the method for detecting product information described in this application is shown. This embodiment is further expanded on the basis of the previous embodiment. The method specifically includes the following steps:

[0072] Step 401: Determine the information template corresponding to the target product, and determine the first positioning tag in the information template.

[0073] Step 402: photograph and obtain an image of the target product to be inspected in the inspection area.

[0074] Step 403: locate the target area in the image to be detected according to the first positioning tag.

[0075] The contents of steps 401 to 403 above are the same as Figure 1 The embodiments shown are consistent and will not be repeated here.

[0076] Step 404: Based on image recognition technology, determine a second information tag corresponding to the first information tag in the target area.

[0077] Step 405: Determine the product information of the target product from the second information tag according to the information distribution position in the first information tag.

[0078] In step 404 to step 405, the detection of product information in the information tag is realized. That is, it can be considered that the position of the information tag in the information template and in the target area should be relatively unchanged, so according to the position of the first information tag in the information template, the second information tag in the target area can be found. At the same time, it is considered that the specific formats of the first information tag and the second information tag are also unchanged. According to the setting of the first information tag, it can be considered that the three label columns of the second information tag are filled in with the product name, product model and SN number of the target product respectively. At this point, the recognition of various basic product information such as product name, product model and SN number in the information tag is realized.

[0079] Step 406: Determine whether there is a second identification icon matching the first identification icon in the target area based on image recognition technology.

[0080] In other cases, the information template may also include other content, such as a first identification icon. The first identification icon may be other specific identifications such as a fragile label, an energy label, etc. included in the information target (i.e., the design of the product packaging or the product shell). Such identifications are usually attached to a specific position of the product in a specific direction. In this step, it will be further determined whether the information of such identifications is correct.

[0081] Therefore, in this embodiment, based on image recognition technology, it can be determined whether there is a second identification icon matching the first identification icon in the target area. When the content and attachment orientation of the second identification icon in the target area are the same as the first identification icon, it means that the actual icon attachment on the product is correct. If the second identification icon has incorrect content, incorrect attachment orientation, or is damaged or warped, it can be regarded as a mismatch, that is, the second identification icon information is incorrect. Therefore, in this embodiment, it can be further determined whether the attachment of this type of identification in the product is qualified.

[0082] Exemplary Devices

[0083] like Figure 5 The device of this embodiment is used to perform Figures 1 to 4 The physical device of the method. Its technical solution is essentially consistent with the above embodiment, and the corresponding description in the above embodiment is also applicable to this embodiment. The device in this embodiment includes:

[0084] The template determination module 501 is used to determine the information template corresponding to the target product and determine the first positioning tag in the information template.

[0085] The image determination module 502 is used to capture and obtain an image of the target product to be detected in the detection area.

[0086] The positioning module 503 is used to locate the target area in the image to be detected according to the first positioning tag.

[0087] The information detection module 504 is used to determine the product information of the target product in the target area by using the information template.

[0088] In addition Figure 5 Based on the embodiment shown, preferably, it also includes:

[0089] Also includes:

[0090] The template generation module 505 is used to generate a corresponding information template according to a packaging design drawing or a product design drawing corresponding to at least one candidate product; the candidate products include the target product; the information template includes a first positioning tag, a first information tag and a first identification icon.

[0091] The template determination module 501 includes:

[0092] The template selection unit 511 is used to determine the product type of the target product; and determine the information template corresponding to the target product according to the product type of the target product.

[0093] The first positioning tag determining unit 512 is configured to determine a first positioning tag in the information template.

[0094] The positioning module 503 includes:

[0095] The second positioning tag determining unit 531 is used to determine the second positioning tag corresponding to the first positioning tag in the image to be detected based on the image recognition technology.

[0096] The edge contour line determination unit 532 is used to perform position matching using the first positioning tag and the second positioning tag to determine the edge contour line of the target product.

[0097] The target area determination unit 533 is used to determine the target area according to the edge contour line of the target product.

[0098] The edge contour determination unit 532 includes:

[0099] The position relationship subunit 5321 is used to determine the relative position relationship between the first positioning label and the product outline in the information template;

[0100] The edge contour line determination subunit 5322 is used to overlap the first positioning tag and the second positioning tag, and project the product contour onto the image to be detected according to the relative position relationship to determine the edge contour line.

[0101] The information detection module 504 includes:

[0102] The label detection unit 541 is used to determine the second information label corresponding to the first information label in the target area based on the image recognition technology; and determine the product information of the target product from the second information label according to the information distribution position in the first information label.

[0103] The identification icon detection unit 542 is used to determine whether there is a second identification icon matching the first identification icon in the target area based on image recognition technology.

[0104] Exemplary computer program products and computer-readable storage media

[0105] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

[0106] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0107] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the method according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0108] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0109] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0110] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0111] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0112] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0113] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for detecting product information, characterized in that: include: Determine an information template corresponding to the target product, and determine a first positioning tag in the information template; Capturing an image of the target product to be inspected in the inspection area; Locating a target area in the image to be detected according to the first positioning tag; Determining product information of the target product in the target area using the information template; The step of locating a target area in the image to be detected according to the first positioning tag comprises: Based on image recognition technology, determining a second positioning tag corresponding to the first positioning tag in the image to be detected; Performing position matching using the first positioning tag and the second positioning tag to determine an edge contour line of the target product; The target area is determined according to the edge contour line of the target product.

2. The method according to claim 1, characterized in that: Before determining the information template corresponding to the target product, it also includes: Generate the corresponding information template according to a packaging design or product design corresponding to at least one candidate product; The candidate products include the target product; the information template includes the first positioning tag, the first information tag and the first identification icon.

3. The method according to claim 2, characterized in that: The information template corresponding to the target product is determined to include: Determining the product type of the target product; According to the product type of the target product, an information template corresponding to the target product is determined.

4. The method according to claim 3, characterized in that: The using the first positioning tag and the second positioning tag to perform position matching to determine the edge contour line of the target product includes: In the information template, determining the relative position relationship between the first positioning label and the product outline; The first positioning tag and the second positioning tag are overlapped, and according to the relative position relationship, the product contour is projected onto the image to be detected to determine the edge contour line.

5. The method according to any one of claims 2 to 4, characterized in that: Determining the product information of the target product in the target area by using the information template includes: Based on image recognition technology, determining a second information tag corresponding to the first information tag in the target area; The product information of the target product is determined from the second information tag according to the information distribution position in the first information tag.

6. The method according to any one of claims 2 to 4, characterized in that: Determining the product information of the target product in the target area by using the information template includes: Based on the image recognition technology, it is determined whether there is a second identification icon matching the first identification icon in the target area.

7. A device for detecting product information, characterized in that: include: A template determination module, used to determine the information template corresponding to the target product, and determine the first positioning tag in the information template; An image determination module, used for capturing and obtaining an image of the target product to be detected in the detection area; A positioning module, used for locating a target area in the image to be detected according to the first positioning tag; An information detection module, used to determine the product information of the target product in the target area using the information template; The positioning module also includes: A second positioning tag determining unit, configured to determine, based on image recognition technology, a second positioning tag corresponding to the first positioning tag in the image to be detected; An edge contour line determining unit, configured to perform position matching using the first positioning tag and the second positioning tag to determine an edge contour line of the target product; The target area determination unit is used to determine the target area according to the edge contour line of the target product.

8. A computer-readable storage medium storing a computer program, wherein the computer program is used to execute the product information detection method according to any one of claims 1 to 6.

9. An electronic device, comprising: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the product information detection method described in any one of claims 1 to 6.

Images