Image processing methods, systems, electronic devices, and storage media based on edge control

By using an edge-controlled image processing method, target images are generated and judged using an image feeder, server, and edge vision controller. This solves the problem of wasting idle image resources and achieves efficient product quality supervision and cost savings.

CN115564963BActive Publication Date: 2026-11-17SHENZHEN BAIMAI TECH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202211130661.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-09-15
Publication Date
2026-11-17
Estimated Expiration
2042-09-15

AI Technical Summary

Technical Problem

In existing factory equipment systems, image resources are left idle after completing visual tasks, resulting in resource waste and excessive costs. How can these idle images be reused and used to monitor product quality?

Method used

An edge-controlled image processing method is adopted, which generates target images and performs image feature determination through an image feeder, an image server and an edge vision controller, thereby realizing the supervision of product quality.

Benefits of technology

This enables the reuse of idle images, reduces resource waste, improves the efficiency and economy of product quality supervision, and lowers labor costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115564963B_ABST
    Figure CN115564963B_ABST
Patent Text Reader

Abstract

This application provides an image processing method, system, electronic device, and storage medium based on edge control. The method is applied to an image processing system including an image feeder, an image server, and an edge vision controller. The method includes: the image feeder sending an original image of a target product to the image server; the image server generating a target image based on the original image and sending the target image to the edge vision controller; and the edge vision controller determining the image features of the target image to obtain a determination result and outputting the determination result. This application enables image processing based on edge control, allowing for the reuse of images that have already completed visual tasks.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of data processing, and more particularly to an image processing method, system, electronic device, and storage medium. Background Technology

[0002] The field of edge vision controller technology based on edge control is currently untapped in the existing technology market, as existing factory equipment systems often focus on data acquisition based on a single device or a single workstation.

[0003] Currently, after a factory acquires product images, they are uploaded to the Manufacturing Execution System (MES) or transmitted to a server or central server using a file transfer protocol. After completing the vision task for that process segment, the image resources become idle, resulting in wasted resources and excessive costs. Therefore, how to reuse idle images while simultaneously monitoring product quality in the factory is a problem that needs to be solved in this field. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide an image processing method, system, electronic device and storage medium to solve or partially solve the above-mentioned technical problems.

[0005] As one aspect of this application, an edge-controlled image processing method is provided, applied to an image processing system including an image feeder, an image server, and an edge vision controller, wherein the method includes: The image feeder sends the original image of the target product to the image server; The image server generates a target image based on the original image and sends the target image to the edge vision controller; The edge vision controller determines the image features of the target image to obtain a determination result, and outputs the determination result.

[0006] Optionally, the image server receives the original image sent by the image feeder, generates the target image, and sends the target image to the edge vision controller, including: An image analysis module located in the image server receives the raw image sent by the image feeder and preprocesses the raw image to generate the target image; An image storage module located in the image server receives the target image sent by the image analysis module and stores the target image in the image storage module; and The image storage module sends the target image to the edge vision controller.

[0007] Optionally, the image analysis module preprocesses the original image, including: the image analysis module performs at least one of the following on the original image: unified naming, unified format, hierarchical nesting, rule sorting, and classified storage.

[0008] Optionally, the edge vision controller determines the image features of the target image to obtain a determination result, and outputs the determination result, including: The edge vision controller pre-constructs a set of sample image features corresponding to the features of the target product; The edge vision controller extracts image features from the target image; The edge vision controller compares the image features with the sample image features corresponding to the image features in the sample image feature set; If the image features match the sample image features, the edge vision controller outputs a successful match result; If the image features do not match the sample image features, the edge vision controller outputs a matching failure result.

[0009] Optionally, before the edge vision controller extracts the image features of the target image, it further includes: The edge vision controller processes the target image; wherein the processing steps include at least one of contrast enhancement, shadow gradient processing, brightness correction, interference removal, noise removal, and blurring.

[0010] Optionally, the method further includes: The edge vision controller constructs a virtual coordinate system; The edge vision controller maps each sample image feature in the sample image feature set to the virtual coordinate system, and each sample image feature has a corresponding coordinate value; The edge vision controller determines the coordinate values ​​of the image features corresponding to the sample image features based on the coordinate values ​​of each sample image feature. Each sample image feature corresponds to at least one coordinate value of an image feature, and among the coordinate values ​​of the at least one image feature, there is at least one coordinate value of an image feature that carries a determination result. The edge vision controller outputs the coordinate values ​​of the image features.

[0011] Optionally, the system further includes a data server, wherein the data server performs the following steps: Receive the determination result and coordinate values ​​of the image features sent by the edge vision controller; The determination results and coordinate values ​​are statistically analyzed, and the statistical results are displayed.

[0012] Based on the same inventive concept, a second aspect of this application provides an image processing system, comprising: An image feeder is configured to send the original image of the target product to an image server. An image server is configured to generate a target image based on the original image and send the target image to the edge vision controller. An edge vision controller is configured to: determine the image features of the target image to obtain a determination result, and output the determination result.

[0013] Based on the same inventive concept, a third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the program to implement the image processing method described in the first aspect above.

[0014] Based on the same inventive concept, a fourth aspect of this application provides a non-transitory computer-readable storage medium, characterized in that the non-transitory computer-readable storage medium stores computer instructions for causing the computer to execute the image processing method described in the first aspect above.

[0015] As can be seen from the above, the image processing method, system, electronic device, and storage medium provided in this application utilize the original images already captured by the image feeder in the factory, thus reusing images that have already completed visual tasks. Furthermore, the image server processes these images to generate the target image required for this application. The process is simple, and finally, only the edge vision controller needs to determine the features of the target image. The determination result is used to judge the product quality of the factory, thereby enabling further supervision. This process is highly feasible and procedurally economical. Therefore, this application utilizes existing image resources that have already completed image tasks, achieving resource conservation. This application only needs to extract image features to achieve product quality supervision, making the process simple and more efficient than manual methods. Finally, the processing system of this application only contains three main devices, making its structure simple and practical. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of an image system device structure based on edge control provided in an embodiment of this application.

[0018] Figure 2A This is a schematic flowchart of an image processing method based on edge control provided in an embodiment of this application.

[0019] Figure 2B This is a schematic flowchart of an image processing method provided by an image processor according to an embodiment of this application.

[0020] Figure 2C This is a schematic flowchart illustrating a method for determining image features of a target image using an edge vision controller, as provided in an embodiment of this application.

[0021] Figure 2D This is a schematic flowchart of an image processing method for another edge vision controller provided in an embodiment of this application.

[0022] Figure 2E This is a schematic flowchart illustrating a method for determining image features of a target image using an edge vision controller, as provided in an embodiment of this application.

[0023] Figure 3A This is a schematic flowchart of another image processing method based on edge control provided in an embodiment of this application.

[0024] Figure 3B This is a schematic diagram of another edge-controlled image system device provided in an embodiment of this application.

[0025] Figure 4 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0027] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by those skilled in the art to which this application pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects.

[0028] Currently, cloud computing accounts for a significant portion of factory data processing. However, cloud computing is often limited by network transmission constraints, thus edge computing is gradually gaining attention. As an important supplement to cloud computing, edge computing is playing an increasingly important role in building interconnected factories. Edge computing enables data analysis, processing, and storage at the network edge, not only reducing reliance on the cloud but also improving data security. Edge controllers will be able to... programming A Programmable Logic Controller (PLC), a personal computer (PC), and a motion controller are integrated into a single device, combining data processing and logic control. These two tasks can be performed simultaneously without interference. However, edge computing is a relatively new field, and edge vision computing is virtually nonexistent.

[0029] Meanwhile, the applicant also noted that factories often generate a large number of images during the production process. After the images are collected at the factory, they are generally uploaded to the Manufacturing Execution System (MES) or transmitted to a server or central server using file transfer protocols. After the central server completes the vision task for that process segment via cloud computing, the image resources become idle.

[0030] Therefore, this application proposes an image processing method based on edge control, which can utilize the image resources captured by the factory using an edge vision controller, and use edge computing to extract image features and judge them to detect the quality of factory products, achieving multiple benefits in one go.

[0031] Figure 1 A schematic diagram of the structure of an image system device based on edge control provided in an embodiment of this application is shown.

[0032] Figure 2A A schematic flowchart of an image processing method based on edge control provided in an embodiment of this application is shown.

[0033] like Figure 1 As shown in Figure A, in some embodiments, the edge-controlled image processing system may include an image feeder 100, an image server 200, an edge vision controller 300, and a data server 400.

[0034] like Figure 2A As shown, in some embodiments, the edge-controlled image processing method applied to this image processing system includes the following steps: S101: The image feeder 100 sends the original image of the target product to the image server 200; S102: The image server 200 generates a target image based on the original image and sends the target image to the edge vision controller 300; S103: The edge vision controller 300 determines the image features of the target image to obtain a determination result and outputs the determination result.

[0035] In some embodiments, the image feeder 100 may be one or more third-party devices providing images in a factory workshop, the original images being images captured by the third-party devices to detect product quality. As an alternative embodiment, the factory may be a mobile phone assembly factory, which includes two types of image feeders: the first is an image captured by an assembly machine, the original image generated by which is used to detect scratches on the product surface; the second is an image captured by a detection machine, the original image generated by which is used to detect anomalies in the product's color and size.

[0036] As another optional embodiment, the manufacturing plant can be a factory assembling mobile phones and tablets, which includes two types of image feeders: the first is an image captured by a machine assembling mobile phones, the raw image captured by this machine is used to detect whether the mobile phone assembly is complete; the second is an image captured by a machine assembling tablets, the raw image captured by this machine is used to detect whether the tablet assembly is complete. It is conceivable that the machine assembling mobile phones can include multiple sub-machines as sub-image feeders, each of which can capture the raw image generated at each step of the mobile phone assembly process. Similarly, the machine assembling tablets can also include multiple sub-machines as sub-image feeders, which will not be elaborated further here. The method provided in this application can be adapted to various image feeders and has strong universality.

[0037] In some embodiments, the image feeder 100 can send the original image to the image server 200 via online transmission. For example, the image feeder 100 can send the original image to the image server 200 via a gigabit or 10-gigabit network port.

[0038] Figure 2B A schematic flowchart of an image processing method provided by an image processor according to an embodiment of this application is shown.

[0039] like Figure 2B As shown, in some embodiments, the steps of image processor 200 receiving the raw image sent by image feeder 100, generating a target image, and sending the target image to edge vision controller 300 include: S1022: The image analysis module 2002 set in the image server 200 receives the original image sent by the image feeder, and preprocesses the original image to generate the target image; S1024: The image storage module 2004, located in the image server, receives the target image sent by the image analysis module and stores the target image in the image storage module; and the image storage module sends the target image to the edge vision controller.

[0040] In some embodiments, after the image server 200 receives the original image sent from the image feeder 100, the image processing module 2002 set in the image server 200 will preprocess the original image.

[0041] As an optional embodiment, the image processing module 2002 can preprocess the original image to unify the image format. It is conceivable that the original images sent by different image providers 100 may have different formats, and the image server 200 will convert the images of different formats, for example, convert them all to JPG format, in order to adapt them.

[0042] As another optional embodiment, the image processing module 2002 can perform preprocessing on the original image using a unified image naming method. For example, the images can be named according to the same source or according to the same time period in which they were generated.

[0043] Similarly, the image processing module 2002 can perform nested preprocessing on the original image, for example, nesting similar images from the same source. The preprocessing process can also involve sorting the images according to certain rules, such as sorting them by their creation time. Furthermore, the preprocessing process can involve classifying and storing the images, for example, storing them in different storage devices based on their source; these storage devices can be manually configured. Through the above preprocessing of the original image, classifying and storing the images facilitates centralized image storage later, and the naming and sorting according to rules allows for distributed distribution of images based on factory needs.

[0044] In some embodiments, the image processing module 2002 stores the target image generated after preprocessing the original image in the image storage module 2004. The image storage module 2004 then sends the target image to the edge vision controller 300. It is understood that network failures are inevitable in online transmission. Therefore, if the image provider 100 loses connection with the image server 200, the image storage module 2004, used for image storage, can still send the pre-stored image to the edge vision controller 300, ensuring the execution of the transmission task.

[0045] As an alternative embodiment, the image processing module 2002 may also directly send the target image to the edge vision controller 300 instead of sending the target image to the image storage module for storage.

[0046] Figure 2C This illustration shows a flowchart of a method for determining image features of a target image using an edge vision controller, as provided in an embodiment of this application.

[0047] like Figure 2C As shown, in some embodiments, the edge vision controller 300 determines the image features of the target image, including the following steps: S031: The edge vision controller 300 pre-constructs a set of sample image features that can reflect the characteristics of the target product; S1032: The edge vision controller 300 extracts the image features of the target image; S1033: The edge vision controller 300 compares the image features with the sample image features corresponding to the image features in the sample image feature set; S1034: If the image features match the sample image features, the edge vision controller 300 outputs a successful matching result; S1035: If the image features do not match the sample image features, the edge vision controller 300 outputs a matching failure result.

[0048] In some embodiments, the sample image feature set pre-built by the edge vision controller 300 can be a sample feature set that reflects the normal characteristics of the target product, and the sample image features can be features reflecting product quality. Continuing with the example of assembling a mobile phone, the sample feature set may include sample image features showing that the phone's edges are not warped, sample image features showing aligned holes, sample image features showing that the screen has no cracks, and so on. Similarly, when the edge vision controller 300 acquires a target image of a mobile phone casing, it extracts features such as whether the phone casing has warped edges and whether the alignment is accurate as image features of the target image. Then, the edge vision controller 300 determines the image features and outputs the determination result.

[0049] For example, the edge vision controller 300 can compare the target image features that reflect whether the collected image does not have warped edges with the corresponding sample image features. If a match is found, the edge vision controller 300 considers the target product reflected by the image features to be good, and sends the successful match result to the data server 400. The display method of this result can be manually set, such as "OK", "Y (YES)", "Normal", etc. Similarly, if a match is found to be unsuccessful, the target product reflected by the image features is considered to be unsuccessful, and the edge vision controller 300 sends the unsuccessful match result to the data server 400. The display method of this result can also be manually set, such as "NG (NOT GOOD)", "N (NO)", "Abnormal", etc., which will not be elaborated further here.

[0050] This application enables quality control of products through the extraction and judgment of image features, greatly reducing manual operations in factories and saving labor costs, while machine operation is also more efficient.

[0051] Figure 2D This illustration shows a schematic flowchart of an image processing method for another edge vision controller provided in an embodiment of this application.

[0052] As an optional embodiment, such as Figure 2D As shown, the edge vision controller 300 may include multiple sub-edge vision controllers. The edge vision controller 300 can collect the judgment results of multiple sub-edge vision controllers and output the judgment result in a unified manner.

[0053] It is understood that the aforementioned edge controller 300 may not collect the judgment results of all sub-edge vision controllers, but rather have multiple sub-edge vision controllers output their judgment results separately. This application embodiment provides two different operating modes of the edge vision controller 400 for factories to choose from in actual use. By flexibly utilizing different operating modes, the adaptability of the edge vision controller 400 to the factory can be further improved.

[0054] In some embodiments, the edge vision controller 300 only needs to be equipped with two network ports: the first port is used to receive images, and the second port is used to output data. Furthermore, the edge vision controller 300 can output the judgment results via wired communication methods such as Ethernet and fiber optics, or wireless communication methods such as wireless local area networks (WLANs). Therefore, the edge vision controller 300 achieves image processing without the need for additional communication interfaces, and by sending images through a data server, it also eliminates the need for acquisition hardware, resulting in high processing efficiency and energy savings.

[0055] In some embodiments, after receiving the target image sent by the image server 200 through an agreed communication port and transmission rules, the edge vision controller 300 processes the target image to facilitate feature extraction. It is understood that the image processing by the edge vision controller 300 may include contrast enhancement to increase the contrast between the target features and the background, shadow gradation to make the uneven image background uniform, and brightness correction to upscale the overall darkened image to the target grayscale. Simultaneously, the image processing by the edge vision controller 300 can also include interference removal, noise removal, blurring, or edge processing—any image processing method that can make the image features clearer—which will not be elaborated further here. After image processing by the edge vision controller 300, the image features of the target image become more apparent, facilitating subsequent feature determination by the edge vision controller 300.

[0056] Figure 2E This is a schematic flowchart illustrating a method for determining image features of a target image using an edge vision controller, as provided in an embodiment of this application.

[0057] like Figure 2E As shown, the edge vision controller 300 also constructs a virtual coordinate system, and the specific steps are as follows: S1036: The edge vision controller 300 constructs a virtual coordinate system; S1037: The edge vision controller 300 maps each sample image feature in the sample image feature set to the virtual coordinate system, and each sample image feature has a corresponding coordinate value; S1038: The edge vision controller 300 determines the coordinate values ​​of the image features corresponding to the sample image features based on the coordinate values ​​of each sample image feature, wherein each sample image feature corresponds to at least one coordinate value of an image feature, and among the coordinate values ​​of the at least one image feature, there is at least one coordinate value of an image feature carrying a determination result; S1039: The edge vision controller 300 outputs the coordinate values ​​of the image features.

[0058] In some embodiments, the edge vision controller 300 constructs a virtual coordinate system. This virtual coordinate system can be constructed with different origins, such as the camera of an image feeder or the location of a product. Different construction methods depend on the factory's needs and will not be elaborated further here. After constructing the virtual coordinate system, the edge vision controller 300 maps each sample image feature in the sample image feature set to the virtual coordinate system, with each sample image feature having corresponding coordinate values. Then, based on the coordinate values ​​of each sample image feature, the edge vision controller 300 determines the coordinate values ​​of at least one image feature carrying a judgment result corresponding to that sample image feature, and then outputs the coordinate values ​​of the image features. As an optional embodiment, referring to the example of assembling a mobile phone, the edge vision controller 300 collects the features of samples without warped edges and generates coordinate values ​​(x, y, z) in a virtual coordinate system. During the subsequent judgment of the target image, the edge vision controller 300 determines that the target image contains an image feature indicating a warped edge. Therefore, the edge vision controller 300 outputs the coordinates (x, y, z) as the coordinate values ​​of this target image feature along with the output of the matching failure result. This application, by constructing a virtual coordinate system, can clearly record the location of the determined image feature result, facilitating subsequent tracing of the cause of product defects in the factory.

[0059] Figure 3A This illustration shows a schematic flowchart of another edge-controlled image processing method provided in an embodiment of this application.

[0060] like Figure 3A As shown, in some embodiments, the system further includes a data server 400, wherein the data server performs the following steps: S104: Receive the determination result and coordinate values ​​of the image features sent by the edge vision controller; S105: Perform statistics on the determination results and coordinate values, and display the statistical results.

[0061] In some embodiments, the system described above may further include a data server 400. The data server 400 can receive judgment results and coordinate values ​​sent from the edge vision controller 300, and then summarize and statistically analyze the judgment results. As an optional embodiment, the results can be summarized in a tabular format, with each column displaying different data. For example, the first column might summarize the types of image features with all output images having poor judgment results; the second column might display the ratio of each type of poor judgment to the total number of matching results; and the third column might display the coordinate values ​​of each type of poor judgment. It is conceivable that the data server 400's classification and statistical display of the data can be manually configured, which will not be elaborated upon here.

[0062] By analyzing statistics from the 400 data server, factory employees can determine the volatility of the factory's product manufacturing process based on changes in the product defect rate. They can also determine the concentration of defects by analyzing the percentage of different defect types. Furthermore, by linking the calculated defects with pre-entered raw image time periods and equipment, they can determine if equipment malfunctions. Continuing with the example of assembling mobile phones, if the data server shows that the defect rate of peeling edges on the phone casing accounts for more than 50% of the total defects, factory employees can pinpoint a potential malfunction in the image feeder used for casing assembly, thus effectively resolving the problem and reducing factory losses.

[0063] Through the above method, this application realizes the process of supervising product quality using idle images in factory production under edge control. At the same time, the statistics of defects can help employees control product quality. The statistics of defect types can also enable factory employees to judge whether the equipment is malfunctioning. The two-pronged approach greatly improves the processing efficiency of the factory.

[0064] It should be noted that the method in this embodiment can be executed by a single device, such as a computer or server. The method can also be applied in a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method in this embodiment, and the multiple devices will interact with each other to complete the method described.

[0065] It should be noted that the above description describes some embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0066] Figure 1 B shows a schematic diagram of another edge-controlled image system device provided in an embodiment of this application.

[0067] Based on the same technical concept, corresponding to any of the above embodiments, such as Figure 1 As shown in Figure A, this application embodiment also provides an image processing system, including: Image feeder 100 is configured to send the original image of the target product to image server 200; Image server 200 is configured to generate a target image based on the original image and send the target image to edge vision controller 300; The edge vision controller 300 is configured to: determine the image features of the target image to obtain a determination result, and output the determination result.

[0068] Figure 3B A schematic diagram of the device structure of an image server provided in an embodiment of this application is shown.

[0069] In some embodiments, such as Figure 3B The image server 200 shown includes: Image analysis module 2002 is configured to: preprocess the original image to generate a target image; The image storage module 2004 is configured to store the target image and send the target image to the edge vision controller 300.

[0070] Understandably, this system can be applied to factory production lines that generate images, such as factories that assemble mobile phones, tablets, or even cars.

[0071] Meanwhile, the edge vision controller 300 provided in this application embodiment requires no display or acquisition hardware, only two communication interfaces, and built-in embedded standard vision system software capable of implementing the above methods. Different edge controller deployment schemes can also meet customized on-site needs. It can operate as long as there is an image, and batch processing of images can be performed on different production lines. It makes OK / NG judgments on the detected images and provides data content, which greatly simplifies the vision deployment structure. It also simplifies the system structure. Only a standardized controller is needed to reuse images. It can start transmitting images by connecting to the network port, which is convenient to operate. It can monitor multiple process sections, providing a monitoring platform for the factory, while also reducing manufacturer costs, achieving multiple benefits.

[0072] The system described above is used to implement the corresponding image processing methods in the foregoing embodiments and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0073] Based on the same technical concept, corresponding to the methods of any of the above embodiments, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the image processing method described in any of the above embodiments.

[0074] Figure 4 A schematic diagram of a more specific electronic device hardware structure provided in an embodiment of this application is shown.

[0075] like Figure 4 As shown, the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected within the device via the bus 1050.

[0076] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0077] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0078] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0079] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0080] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0081] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0082] The electronic devices described above are used to implement the corresponding image processing methods in any of the foregoing embodiments and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0083] Based on the same technical concept, corresponding to the methods of any of the above embodiments, this application also provides a non-transitory computer-readable storage medium that stores computer instructions for causing the computer to perform the image processing method as described in any of the above embodiments.

[0084] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0085] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the image processing method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0086] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application (including the claims) is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in the details for the sake of brevity.

[0087] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0088] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0089] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.

Claims

1. An image processing method based on edge control, characterized in that, An image processing system including an image feeder, an image server, and an edge vision controller, wherein the method includes: The image feeder sends the original image of the target product to the image server; wherein, the original image is an idle image acquired by the image feeder for detecting product quality, and is obtained after the image feeder has completed the visual task of the process segment corresponding to the original image. The image server generates a target image based on the original image and sends the target image to the edge vision controller; The edge vision controller determines the image features of the target image to obtain a determination result, and outputs the determination result; The edge vision controller determines the image features of the target image to obtain a determination result, including: The edge vision controller pre-constructs a set of sample image features corresponding to the features of the target product; The edge vision controller extracts image features from the target image; The edge vision controller compares the image features with the sample image features corresponding to the image features in the sample image feature set; If the image features match the sample image features, the edge vision controller outputs a successful match result; If the image features do not match the sample image features, the edge vision controller outputs a matching failure result; The image server generates a target image based on the original image and sends the target image to the edge vision controller, including: An image analysis module located in the image server receives the raw image sent by the image feeder and preprocesses the raw image to generate the target image; An image storage module located in an image server receives the target image sent by the image analysis module and stores the target image in the image storage module; Furthermore, the image storage module sends the target image to the edge vision controller; The image analysis module preprocesses the original image, including: the image analysis module performs at least one of the following on the original image: unified naming, unified format, hierarchical nesting, rule sorting, and classified storage; The method further includes: The edge vision controller constructs a virtual coordinate system; The edge vision controller maps each sample image feature in the sample image feature set to the virtual coordinate system, and each sample image feature has a corresponding coordinate value; The edge vision controller determines the coordinate values ​​of the image features corresponding to the sample image features based on the coordinate values ​​of each sample image feature. Each sample image feature corresponds to at least one coordinate value of an image feature, and among the coordinate values ​​of the at least one image feature, there is at least one coordinate value of an image feature that carries a determination result. The edge vision controller outputs the coordinate values ​​of the image features.

2. The method according to claim 1, characterized in that, Before the edge vision controller extracts the image features of the target image, it also includes: The edge vision controller processes the target image; wherein the processing steps include at least one of contrast enhancement, shadow gradient processing, brightness correction, interference removal, noise removal, and blurring.

3. The method according to claim 1, characterized in that, The system also includes a data server, wherein the data server performs the following steps: Receive the determination result and coordinate values ​​of the image features sent by the edge vision controller; The judgment results and coordinate values ​​are statistically analyzed, and the statistical results are displayed.

4. An image processing system based on edge control, characterized in that, include: An image feeder is configured to send an original image of a target product to an image server; wherein the original image is an idle image acquired by the image feeder for detecting product quality, and is obtained after the image feeder has completed the visual task of the process segment corresponding to the original image. An image server is configured to generate a target image based on the original image and send the target image to an edge vision controller. An edge vision controller is configured to: determine the image features of the target image to obtain a determination result, and output the determination result; The edge vision controller determines the image features of the target image to obtain a determination result, including: The edge vision controller pre-constructs a set of sample image features corresponding to the features of the target product; The edge vision controller extracts image features from the target image; The edge vision controller compares the image features with the sample image features corresponding to the image features in the sample image feature set; If the image features match the sample image features, the edge vision controller outputs a successful match result; If the image features do not match the sample image features, the edge vision controller outputs a matching failure result; The image server generates a target image based on the original image and sends the target image to the edge vision controller, including: An image analysis module located in the image server receives the raw image sent by the image feeder and preprocesses the raw image to generate the target image; An image storage module located in an image server receives the target image sent by the image analysis module and stores the target image in the image storage module; Furthermore, the image storage module sends the target image to the edge vision controller; The image analysis module preprocesses the original image, including: the image analysis module performs at least one of the following on the original image: unified naming, unified format, hierarchical nesting, rule sorting, and classified storage; The image processing system also includes: The edge vision controller constructs a virtual coordinate system; The edge vision controller maps each sample image feature in the sample image feature set to the virtual coordinate system, and each sample image feature has a corresponding coordinate value; The edge vision controller determines the coordinate values ​​of the image features corresponding to the sample image features based on the coordinate values ​​of each sample image feature. Each sample image feature corresponds to at least one coordinate value of an image feature, and among the coordinate values ​​of the at least one image feature, there is at least one coordinate value of an image feature that carries a determination result. The edge vision controller outputs the coordinate values ​​of the image features.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the image processing method as described in any one of claims 1 to 3.

6. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions for causing the computer to perform the image processing method according to any one of claims 1 to 3.

Citation Information

Patent Citations

  • Automatic container position identification system and identification method thereof

    CN113979367A