A defect detection parameter adjustment method, device, equipment and storage medium

Abstract

The embodiments of the present application provide a defect detection parameter adjustment method, device, equipment and storage medium, which relate to the field of machine vision technology. The method includes: in response to the parameter adjustment operation for the initial defect type in the defect display interface, displaying the defect parameter adjustment interface corresponding to the initial defect type; the defect parameter adjustment interface includes: multiple feature values ​​corresponding to multiple defect features of the abnormal area corresponding to the initial defect type, a defect selection control, and a data learning control; in response to the trigger operation for the data learning control, obtaining multiple initial defect true value ranges corresponding to the target defect type in the defect selection control, and adjusting the multiple initial defect true value ranges corresponding to the target defect type based on the multiple feature values ​​of the abnormal area corresponding to the initial defect type, to obtain multiple target defect true value ranges corresponding to the target defect type; based on the multiple target defect true value ranges, updating the defect judgment conditions corresponding to the target defect type.

Description

Technical Field

[0001] The present application relates to the field of machine vision technology, and in particular to a defect detection parameter adjustment method, device, equipment and storage medium. Background Art

[0002] During the production process, due to various reasons (such as material problems, process fluctuations, equipment failures, etc.), various defects may occur in products or parts. If these defects are not discovered and repaired in time, they will have an adverse effect on the performance, reliability and safety of the product. Therefore, it is necessary to collect images of products or parts and then perform defect detection on the images of products or parts in order to timely discover and eliminate problems in products or parts, thereby ensuring that the quality of products or parts meets the predetermined standards and requirements.

[0003] When performing defect detection, it is necessary to set a defect judgment condition for each defect type, and determine whether there is a defect in the product or component by judging whether the image of the product or component meets any defect judgment condition. However, the setting of the defect judgment condition depends on the experience of the staff, and is therefore easily affected by personal subjective consciousness, own experience and understanding, resulting in low accuracy of the defect judgment condition. Therefore, in the process of defect detection, it is necessary to continuously adjust the parameters in the defect judgment condition to make the judgment more accurate. Summary of the invention

[0004] The present application provides a defect detection parameter adjustment method, device, equipment and storage medium, which are used to provide a way to adjust the parameters in the defect judgment conditions during the defect detection process to improve the accuracy of defect detection.

[0005] A first aspect of an embodiment of the present application provides a defect detection parameter adjustment method, comprising: in response to a parameter adjustment operation for an initial defect type in a defect display interface, displaying a defect parameter adjustment interface corresponding to the initial defect type; the defect display interface is used to display the defect type obtained by detecting an image to be detected based on the defect judgment condition corresponding to each defect type in a plurality of defect types; the defect parameter adjustment interface comprises: a plurality of feature values ​​corresponding to a plurality of defect features of an abnormal area corresponding to the initial defect type, a defect selection control, and a data learning control; in response to a trigger operation for the data learning control, obtaining a plurality of initial defect true value ranges corresponding to a target defect type in the defect selection control, and adjusting a plurality of initial defect true value ranges corresponding to the target defect type based on a plurality of feature values ​​of the abnormal area corresponding to the initial defect type to obtain a plurality of target defect true value ranges corresponding to the target defect type; wherein the target defect true value range corresponding to each defect feature matches the feature value corresponding to the defect feature; and based on the plurality of target defect true value ranges, updating the defect judgment condition corresponding to the target defect type.

[0006] The defect detection parameter adjustment method provided in the embodiment of the present application can display the defect type obtained by detecting the image to be detected through the defect display interface after obtaining the defect detection result, so that the staff can check whether the detected initial defect type is consistent with the actual defect type. Furthermore, in the case of inconsistency, the staff can trigger the parameter adjustment control of the initial defect type in the defect display interface to display the defect parameter adjustment interface corresponding to the initial defect type, so that the staff can select the target defect type actually corresponding to the initial defect type based on the defect selection control in the defect parameter adjustment interface, and automatically adjust the initial defect true value range corresponding to multiple defect features of the target defect type through the data learning control in the defect parameter adjustment interface, and obtain the target defect true value range corresponding to the target defect type and matching the characteristic value of each defect feature. In this way, when re-detecting defects, the characteristic value of the abnormal area can match the defect judgment condition corresponding to the target defect type, that is, the defect type of the abnormal area is detected as the target defect type, thereby achieving the purpose of more accurate defect detection.

[0007] In combination with the first implementation method of the first aspect, multiple initial defect true value ranges corresponding to the target defect type are adjusted based on multiple characteristic values ​​of the abnormal area corresponding to the initial defect type to obtain multiple target defect true value ranges corresponding to the target defect type, including: inputting multiple characteristic values ​​of the abnormal area corresponding to the initial defect type and multiple initial defect true value ranges corresponding to the target defect type into a target parameter prediction model corresponding to the target defect type to obtain multiple target defect true value ranges corresponding to the target defect type; the target parameter prediction model is used to adjust multiple initial defect true value ranges based on multiple characteristic values ​​to obtain multiple target defect true value ranges.

[0008] In combination with the second implementation method of the first aspect, the target parameter prediction model is trained in the following manner: obtaining multiple sample data corresponding to the target defect type, wherein each sample data includes a historical feature value corresponding to each defect feature in multiple defect features, an initial historical defect true value range, and a target historical defect true value range; training the initial parameter prediction model based on the multiple sample data corresponding to the target defect type to obtain a target parameter prediction model corresponding to the target defect type.

[0009] In combination with the third implementation method of the first aspect, after updating the defect judgment conditions corresponding to the target defect type, the method also includes: obtaining multiple historical defect judgment conditions corresponding to the target defect type; determining the confidence of the updated defect judgment conditions corresponding to the target defect type based on the multiple historical defect judgment conditions; when the confidence is less than or equal to a preset confidence threshold, outputting a prompt message, the prompt message being used to prompt the staff to determine whether the updated defect judgment conditions are reasonable.

[0010] In combination with the fourth implementation method of the first aspect, the method also includes: determining the abnormal area in the image to be detected, and determining the feature values ​​of multiple defect features corresponding to the abnormal area; matching the defect judgment conditions corresponding to the defect type with the feature values ​​of multiple defect features corresponding to the abnormal area according to the order of defect types recorded in the defect priority to determine the defect type obtained by detecting the image to be detected; and displaying the defect type obtained by detecting the image to be detected through a defect display interface.

[0011] In combination with the fifth implementation method of the first aspect, the defect parameter adjustment interface also includes: a feature state corresponding to each defect feature; the feature state is used to indicate whether the feature value corresponding to the defect feature matches the initial defect true value range; and / or, display controls and adjustment controls corresponding to each initial defect true value range.

[0012] In combination with the sixth implementation method of the first aspect, the defect display interface also includes: an image to be detected and a display box of the abnormal area corresponding to the defect type obtained by detecting the image to be detected; and / or filtered defects corresponding to the image to be detected, the filtered defects are used to represent defects in the abnormal area in the image to be detected whose feature values ​​of multiple defect features of the abnormal area do not match multiple defect judgment conditions corresponding to multiple defect types.

[0013] A second aspect of an embodiment of the present application provides a defect detection parameter adjustment device, including: a display module, which is used to display a defect parameter adjustment interface corresponding to the initial defect type in a defect display interface in response to a parameter adjustment operation for the initial defect type in the defect display interface; the defect display interface is used to display the defect type obtained by detecting the image to be detected based on the defect judgment condition corresponding to each defect type in multiple defect types; the defect parameter adjustment interface includes: multiple feature values ​​corresponding to multiple defect features of the abnormal area corresponding to the initial defect type, a defect selection control, and a data learning control; an adjustment module, which is used to obtain multiple initial defect true value ranges corresponding to the target defect type in the defect selection control in response to a trigger operation for the data learning control, and adjust the multiple initial defect true value ranges corresponding to the target defect type based on the multiple feature values ​​of the abnormal area corresponding to the initial defect type to obtain multiple target defect true value ranges corresponding to the target defect type; wherein the target defect true value range corresponding to each defect feature matches the feature value corresponding to the defect feature; an update module, which is used to update the defect judgment condition corresponding to the target defect type based on the multiple target defect true value ranges.

[0014] A third aspect of an embodiment of the present application provides an electronic device, comprising: one or more processors; one or more memories; wherein the one or more memories are used to store computer program codes, the computer program codes include computer instructions, and when the one or more processors execute the computer instructions, the electronic device executes the defect detection parameter adjustment method provided by the first aspect and its possible implementation methods.

[0015] The fourth aspect of an embodiment of the present application provides a computer-readable storage medium, which stores computer execution instructions. When the computer execution instructions are run on a computer, the computer executes the defect detection parameter adjustment method provided by the first aspect and its possible implementation methods.

[0016] The fifth aspect of an embodiment of the present application provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the defect detection parameter adjustment method provided in the first aspect and its possible implementation methods.

[0017] Among them, the beneficial effects described in the second to fifth aspects can refer to the beneficial effect analysis of the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0019] Figure 1 A schematic diagram of the structure of a defect detection and parameter adjustment system provided in an embodiment of the present application;

[0020] Figure 2 A schematic diagram of a defect display interface provided in an embodiment of the present application;

[0021] Figure 3 A method flow of a defect detection parameter adjustment method provided in an embodiment of the present application Figure 1 ;

[0022] Figure 4 A schematic diagram of a defect parameter adjustment interface provided in an embodiment of the present application;

[0023] Figure 5 A flow chart of a method for training a target parameter prediction model provided in an embodiment of the present application;

[0024] Figure 6 A method flow of a defect detection parameter adjustment method provided in an embodiment of the present application Figure 2 ;

[0025] Figure 7A schematic diagram of the structure of a defect detection parameter adjustment device provided in an embodiment of the present application;

[0026] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions 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 ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0029] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "connected" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances. In addition, when describing a pipeline, the "connected" and "connection" used in this application have the meaning of conduction. The specific meaning needs to be understood in conjunction with the context.

[0030] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0031] During the production process, due to various reasons (such as material problems, process fluctuations, equipment failures, etc.), various defects may occur in products or parts. If these defects are not discovered and repaired in time, they will have an adverse effect on the performance, reliability and safety of the product. Therefore, it is necessary to collect images of products or parts and then perform defect detection on the images of products or parts in order to timely discover and eliminate problems in products or parts, thereby ensuring that the quality of products or parts meets the predetermined standards and requirements.

[0032] When performing defect detection, you first need to use industrial cameras, lenses, light sources and other hardware equipment to collect images of the products (or parts) to be inspected. Then preprocess the image to improve image quality, remove noise, and enhance defect features. Then extract feature information related to the defect from the preprocessed image. For example, the features in the image can be extracted in the following ways: use edge detection algorithms such as the Canny operator and the Sobel operator to extract image edge information; extract shape parameters of defects, such as area, perimeter, circularity, etc.; extract grayscale mean, grayscale variance, grayscale entropy and other features of the defect area. Then, based on the extracted feature information and the pre-set defect judgment conditions, identify and classify the defects to determine whether there are defects in the product to be inspected.

[0033] However, the setting of defect judgment conditions depends on the experience of the staff, and is therefore easily affected by personal subjective consciousness, experience and understanding, resulting in low accuracy of defect judgment conditions, which means that false detection is very likely to occur, such as misdetecting actual defect type A as defect type B. Therefore, in the process of defect detection, the parameters in the defect judgment conditions need to be continuously adjusted to make the defect types detected in the defect detection process more accurate.

[0034] Based on this, the embodiment of the present application provides a defect detection parameter adjustment method, which displays the defect type obtained through the defect display interface after detecting the image to be detected based on the defect judgment condition corresponding to each defect type in multiple defect types. If the staff finds that the initial defect type detected is inconsistent with the actual defect type, they can trigger the parameter adjustment operation of the initial defect type in the defect display interface to adjust the parameters.

[0035] In response to the triggering operation of the parameter adjustment control for the initial defect type in the defect display interface, the defect parameter adjustment interface corresponding to the initial defect type is displayed, and the defect parameter adjustment interface includes: multiple feature values ​​corresponding to multiple defect features of the abnormal area corresponding to the initial defect type, a defect selection control, and a data learning control. Then, the staff can select the target defect type actually corresponding to the initial defect type based on the defect selection control in the defect parameter adjustment interface, and select the data learning control to automatically adjust the parameters.

[0036] In response to a trigger operation on a data learning control, a plurality of initial defect true value ranges corresponding to a target defect type in a defect selection control are obtained, and the plurality of initial defect true value ranges corresponding to the target defect type are adjusted based on a plurality of characteristic values ​​of an abnormal area corresponding to the initial defect type to obtain a plurality of target defect true value ranges corresponding to the target defect type; wherein the target defect true value range corresponding to each defect feature matches the characteristic value corresponding to the defect feature; based on the plurality of target defect true value ranges, the defect judgment condition corresponding to the target defect type is updated so that defect detection can be re-performed on the image to be inspected.

[0037] It can be seen that the defect detection parameter adjustment method provided in the embodiment of the present application can display the defect type obtained by detecting the image to be detected through the defect display interface after obtaining the defect detection result, so that the staff can check whether the initial defect type detected is consistent with the actual defect type. Furthermore, in the case of inconsistency, the staff can trigger the parameter adjustment control of the initial defect type in the defect display interface to display the defect parameter adjustment interface corresponding to the initial defect type, so that the staff can select the target defect type actually corresponding to the initial defect type based on the defect selection control in the defect parameter adjustment interface, and automatically adjust the initial defect true value range corresponding to multiple defect features of the target defect type through the data learning control in the defect parameter adjustment interface, and obtain the target defect true value range corresponding to the target defect type and matching the feature value of each defect feature.

[0038] In this way, when re-detecting defects, the characteristic value of the abnormal area can match the defect judgment condition corresponding to the target defect type, that is, the defect type of the abnormal area is detected as the target defect type, thereby achieving the purpose of more accurate defect detection. Without the need for manual adjustments based on the staff's own experience, errors and delays caused by human factors can be avoided, thereby improving the accuracy and reliability of defect detection. At the same time, it can reduce the manual operation and judgment time of the staff in defect detection, so as to improve the detection efficiency in the defect detection process.

[0039] It should be understood that the defect detection parameter adjustment method provided in the embodiment of the present application can be applied to Figure 1 The defect detection parameter adjustment system shown in Figure 1 is shown in Figure 1. Figure 1 The defect detection parameter adjustment system 10 may include: a collection device 100 and a detection device 200. The collection device 100 and the detection device 200 may be connected via a wired network or a wireless network.

[0040] In some embodiments, the acquisition device 100 may be a device with image acquisition function such as an industrial area array camera or a line scan camera, which is used to acquire images of the product to be inspected and send them to the inspection device 200 for defect detection.

[0041] In some embodiments, a defect detection algorithm can be deployed in the detection device 200, which can determine whether there are defects in the image of the product to be inspected (hereinafter referred to as the image to be inspected) through the defect judgment conditions corresponding to each defect type, and display the defect type obtained by detecting the image to be inspected through a defect display interface.

[0042] When the staff determines in the defect display interface that the actual defect type in the image to be detected does not match the initial defect type detected, they can adjust the defect judgment conditions of the actual defect type to make the defect judgment conditions of the actual defect type more accurate, so that the actual defect type in the image to be detected can be more accurately determined during defect detection.

[0043] Specifically, when the staff determines in the defect display interface that the initial defect type of the detected abnormal area does not match the actual defect type, the staff can select the parameter adjustment control of the initial defect type in the defect display interface, so that the detection device 200 displays the defect parameter adjustment interface corresponding to the initial defect type. The staff can determine the target defect type (actual defect type) corresponding to the abnormal area in the defect selection control in the interface, and then select the data learning control.

[0044] The detection device 200 can obtain multiple initial defect true value ranges corresponding to the target defect type in the defect selection control, and adjust the multiple initial defect true value ranges corresponding to the target defect type based on the multiple characteristic values ​​of the abnormal area corresponding to the initial defect type to obtain multiple target defect true value ranges corresponding to the target defect type; wherein the target defect true value range corresponding to each defect feature matches the characteristic value corresponding to the defect feature. Then, based on the multiple target defect true value ranges, the defect judgment condition corresponding to the target defect type is updated to re-perform defect detection on the image to be detected.

[0045] In this way, when re-detecting defects, the characteristic value of the abnormal area can match the defect judgment condition corresponding to the target defect type, that is, the defect type of the abnormal area is detected as the target defect type, thereby achieving the purpose of more accurate defect detection.

[0046] It should be understood that the detection device 200 in the embodiment of the present application can be an electronic device such as a personal computer (PC), a notebook computer, a mobile device, a tablet computer, a laptop computer, etc., and the embodiment of the present application does not limit the specific form of the electronic device. Alternatively, the detection device 200 can also be a single server, or a server cluster composed of multiple servers. In some implementations, the server cluster can be a distributed cluster server. The embodiment of the present application does not impose any restrictions on this.

[0047] It should be understood that the defect detection parameter adjustment method provided in the embodiment of the present application can be applied to Figure 1 The detection device 200 in the defect detection parameter adjustment system is shown.

[0048] In some embodiments, the defect detection parameter adjustment method provided in the embodiments of the present application is performed as follows during defect detection: based on the defect judgment conditions corresponding to each defect type among multiple defect types, the defect type corresponding to the abnormal area in the image to be detected is determined, and the defect type detected in the image to be detected is displayed through a defect display interface.

[0049] The defect judgment condition includes a defect true value range corresponding to each defect feature among multiple defect features.

[0050] It is understandable that the image to be detected can be an image of the product to be detected captured by the acquisition device 100, or it can be an image of the product to be detected pre-stored in the detection device 200 or other memory. The embodiment of the present application does not limit the source of the image to be detected.

[0051] It should be understood that when the products to be inspected corresponding to the images to be inspected are different, the corresponding multiple defect types are also different. When the images to be inspected are images of lithium electrode sheets, that is, when inspecting defects of lithium electrode sheets, the multiple defect types may include: joints, leaking foil, black spots, white spots, dark marks, scratches, etc. Among them, each defect type corresponds to a defect judgment condition. When performing defect detection, the characteristic values ​​of multiple defect features of the abnormal area in the image to be inspected can be matched with multiple defect judgment conditions to obtain the defect type obtained by inspecting the image to be inspected.

[0052] Exemplarily, as a feasible implementation method, the multiple defect features of the abnormal area may include: area, rectangularity, short side, average grayscale and polarity. When performing defect detection, the characteristic value of each defect feature in the multiple defect features of the abnormal area is determined, and then the multiple characteristic values ​​are matched with the defect judgment conditions corresponding to each defect type in the multiple defect types to determine the initial defect type of the abnormal area.

[0053] As a feasible implementation method, defect detection can be performed on the image to be detected through the following steps: determine the abnormal area in the image to be detected, and determine the characteristic values ​​of multiple defect features corresponding to the abnormal area; according to the order of defect types recorded in the defect priority, match the defect judgment conditions corresponding to the defect type with the characteristic values ​​of multiple defect features corresponding to the abnormal area to determine the defect type obtained by detecting the image to be detected.

[0054] That is to say, when performing defect detection, first identify the abnormal area in the image to be detected, and then determine the characteristic value of the defect feature corresponding to each abnormal area, and then match the defect judgment conditions corresponding to multiple defect types with the characteristic values ​​of multiple defect features corresponding to the abnormal area according to the order of defect types recorded in the defect priority. If any defect judgment condition matches, it indicates that there is a defect of the defect type corresponding to the defect judgment condition in the image to be detected.

[0055] It is understandable that there are some more important defects among multiple defect detection types. For example, in lithium electrode sheet defect detection, defects such as joints and foil leakage are more important than defects such as scratches and bright lines. Therefore, when performing defect detection, it is necessary to determine the defect detection for the image to be inspected based on the order of defect types recorded in the defect priority.

[0056] Among them, the foil leakage problem refers to the gap between the metal foil between the separator layer and the positive and negative electrodes of the battery, which may cause electrolyte leakage or short circuit. Electrolyte leakage will directly affect the internal structure and chemical balance of the battery, while short circuit may cause serious safety problems such as battery heating, fire and even explosion. Therefore, the foil leakage problem poses a serious threat to the safety and stability of the battery. Poor or broken joints will affect the integrity and continuity of the pole piece, which in turn affects the performance and life of the battery. These defects are directly related to the safety and performance of the battery, so these defects need to be strictly controlled during the production process. Once these problems are discovered, the production line may need to be stopped immediately and repaired, which will seriously affect production efficiency and cost.

[0057] Although defects such as scratches and bright lines will also have a certain impact on battery performance (such as reducing the contact area between the electrode sheet and the electrolyte, affecting the discharge performance, etc.), they usually do not immediately lead to battery failure or safety accidents. Therefore, during the inspection process, these defects may be regarded as minor issues, but they still need to be paid attention to and measures should be taken to improve them.

[0058] In summary, in the defect detection of lithium electrode sheets, defects such as joints and foil leakage are more important than defects such as scratches and bright lines. This is because they have a more direct and significant impact on the performance, safety, production efficiency and cost of the battery. Therefore, these defects should be given higher priority and stricter control standards during the detection process. That is to say, in the defect detection process, according to the order of defect types recorded in the defect priority, more important defect types can be identified first, which makes it easier for staff to deal with important defect types and ensure the performance, safety, production efficiency and cost of the products to be tested.

[0059] The defect display interface includes the defect types obtained by detecting the image to be detected, so that the staff can timely check the defects in the product to be detected corresponding to the image to be detected. In addition, as a feasible implementation method, the defect display interface also includes the adjustment control corresponding to each defect type, so that the staff can select the adjustment control corresponding to any defect type for adjustment when it is determined that any defect type is not a real defect.

[0060] For example, see Figure 2 , Figure 2 This is a schematic diagram of a defect display interface provided in an embodiment of the present application. Figure 2 As shown in the figure, when performing defect detection on the image A to be detected, abnormal area 1 and abnormal area 2 are detected, so the defect type corresponding to each abnormal area is displayed through the defect display interface. For example, the defect type corresponding to abnormal area 1 represented by serial number 1 is white spot, and the defect type corresponding to abnormal area 2 represented by serial number 2 is classification filtering. In order to facilitate the staff to check, the defect display interface can also display the characteristic values ​​of the defect characteristics of each abnormal area. For example, the defect characteristics corresponding to abnormal area 1 are: area 225; long side 15.4; short side 15; grayscale... The defect characteristics corresponding to abnormal area 2 are: area 0.19; long side 0.4; short side 0.5; grayscale...

[0061] In some embodiments, in order to facilitate the staff to adjust the defect type, such as Figure 2 As shown, each defect type corresponds to a parameter adjustment control to facilitate the staff to perform parameter adjustment operations.

[0062] In some embodiments, in order to facilitate the staff to check whether the defect type obtained by detecting the image to be detected is a real defect, such as Figure 2 As shown, the defect display interface may also include an image to be detected and a display box of an abnormal area corresponding to a defect type obtained by detecting the image to be detected.

[0063] In this way, in the defect display interface, the staff can better determine whether the defect type is a real defect and whether parameter adjustment is required based on the defect type existing in the image to be detected and the corresponding display box in the image to be detected.

[0064] As a feasible implementation method, Figure 2 As shown, the defect display interface may also include a basic setting area, which is used to select a way to obtain the image to be detected ( Figure 2The worker can choose to use the image captured by the camera as the image to be detected, or use local data (the image stored in the machine) as the image to be detected. The worker can select the camera and output to facilitate defect detection. At the same time, the worker can choose single execution or continuous execution to detect a single image to be detected or multiple images to be detected at the same time.

[0065] It is understandable that in the process of defect detection, since the setting of defect judgment conditions depends on the experience of the staff, it is easily affected by personal subjective consciousness, own experience and understanding, resulting in misjudgment. Therefore, it is necessary to adjust the parameters of the defect judgment conditions in the event of misjudgment.

[0066] Based on this, see Figure 3 The defect detection parameter adjustment method provided in the embodiment of the present application includes the following steps:

[0067] S201. In response to a parameter adjustment operation for an initial defect type in a defect display interface, a defect parameter adjustment interface corresponding to the initial defect type is displayed.

[0068] Among them, the defect parameter adjustment interface includes: multiple feature values ​​corresponding to multiple defect features of the abnormal area corresponding to the initial defect type, defect selection controls, and data learning controls.

[0069] It is understandable that since the defect judgment conditions used in defect detection are usually set by the staff based on their own work experience, they are easily affected by personal subjective consciousness, experience and understanding, resulting in low accuracy of the defect judgment conditions. That is, the defect type of the abnormal area detected by the defect may not match the actual defect type in the product to be detected. The staff is required to make a secondary judgment to check whether the detected defect type matches the actual defect type. If not, the parameters in the defect judgment conditions need to be adjusted to make the detection result of the initial defect type more accurate.

[0070] In some embodiments, Figure 2 As shown, the defect display interface includes a parameter adjustment control corresponding to each defect type. If the staff determines that the initial defect type in the defect display interface does not match the corresponding real defect type, they can select the parameter adjustment control corresponding to the initial defect type to implement the parameter adjustment operation.

[0071] After receiving the parameter adjustment operation for the initial defect type in the defect display interface, the detection device displays the defect parameter adjustment interface corresponding to the initial defect type. Figure 4As shown, the defect parameter adjustment interface includes: multiple feature values ​​corresponding to multiple defect features of the abnormal area corresponding to the initial defect type, a defect selection control, and a data learning control.

[0072] It should be understood that a defect type includes multiple defect features, such as area, long side, short side, rectangularity, roundness, grayscale, etc. Each defect feature corresponds to a detected feature value, and the defect judgment condition corresponding to the defect type includes the initial defect true value range corresponding to each defect feature in the multiple defect features of the defect type.

[0073] For example, Figure 4 As shown in , when the initial defect type is white spot, its corresponding defect features include: area, rectangularity, short side, average grayscale and polarity. Each defect feature corresponds to a feature value and a judgment specification (defect true value range). For example, Figure 4 As shown, the eigenvalue corresponding to the defect feature "area" is 225.5; the eigenvalue corresponding to the defect feature "rectangularity" is 1; the eigenvalue corresponding to the defect feature "short side" is 15; the eigenvalue corresponding to the defect feature "average grayscale" is 123.9; and the eigenvalue corresponding to the defect feature "polarity" is 0.

[0074] As a feasible implementation method, Figure 4 As shown, the defect display interface may also include a defect true value range display control corresponding to each defect feature. It should be understood that when the staff does not select the target defect type in the defect selection control, the defect true value range display control may display the defect true value range corresponding to the initial defect type. When the staff selects the target defect type in the defect selection control, the defect true value range display control may display the defect true value range corresponding to the target defect type.

[0075] As a feasible implementation method, Figure 4 As shown, the defect display interface can also include the feature status corresponding to each defect feature ( Figure 4 It should be understood that the feature state is used to indicate whether the feature value corresponding to the defect feature matches the initial defect true value range. Figure 4 As shown, when the characteristic value corresponding to the defect feature matches the initial defect true value range, the corresponding characteristic state is OK. When the characteristic value corresponding to the defect feature does not match the initial defect true value range, the corresponding characteristic state is NG.

[0076] As a feasible implementation method, Figure 4 As shown, the defect display interface may also include an adjustment control for the initial defect true value range corresponding to each defect feature, so that the staff can manually adjust the initial defect true value range corresponding to the defect feature based on the adjustment control.

[0077] S202. In response to a trigger operation on a data learning control, a plurality of initial defect true value ranges corresponding to a target defect type in a defect selection control are obtained.

[0078] It should be noted that when the staff has not selected the target defect type based on the defect selection control, the data learning control can be grayed out to prevent the staff from accidentally touching the data learning control. After the staff has selected the target defect type based on the defect selection control, the data learning control can return to normal to facilitate the staff to trigger the data learning control.

[0079] It can be understood that the target defect type is the real defect type of the abnormal area determined by the staff. During the defect detection process, the defect judgment conditions (multiple initial defect true value ranges) of the target defect type are inaccurate, resulting in the abnormal area being detected as the initial defect type. Therefore, it is necessary to obtain the multiple initial defect true value ranges corresponding to the target defect type in the defect selection control and adjust them.

[0080] S203 . Adjust multiple initial defect true value ranges corresponding to the target defect type based on multiple characteristic values ​​of the abnormal area corresponding to the initial defect type to obtain multiple target defect true value ranges corresponding to the target defect type.

[0081] Among them, the target defect true value range corresponding to each defect feature matches the feature value corresponding to the defect feature.

[0082] It can be understood that when it is determined that the actual defect type of the abnormal area is the target defect type, the characteristic values ​​of the multiple defect features of the abnormal area should match the defect true value range of the target defect type. Therefore, it is necessary to adjust the multiple initial defect true value ranges corresponding to the target defect type based on the multiple characteristic values ​​of the abnormal area corresponding to the initial defect type to obtain the target defect true value range corresponding to the target defect type that matches the characteristic value of each defect feature.

[0083] S204. Based on multiple target defect true value ranges, update defect judgment conditions corresponding to the target defect types.

[0084] After obtaining multiple target defect true value ranges corresponding to multiple defect features in the target defect type, the defect judgment conditions corresponding to the target defect type can be updated to make the defect judgment conditions corresponding to the target defect type more accurate, and then when defect detection is performed on the image to be inspected based on the updated defect judgment conditions, the abnormal area can be accurately identified as the target defect type.

[0085] It can be seen that the defect detection parameter adjustment method provided in the embodiment of the present application can display the defect type obtained by detecting the image to be detected through the defect display interface after obtaining the defect detection result, so that the staff can check whether the initial defect type detected is consistent with the actual defect type. Furthermore, in the case of inconsistency, the staff can trigger the parameter adjustment control of the initial defect type in the defect display interface to display the defect parameter adjustment interface corresponding to the initial defect type, so that the staff can select the target defect type actually corresponding to the initial defect type based on the defect selection control in the defect parameter adjustment interface, and automatically adjust the initial defect true value range corresponding to multiple defect features of the target defect type through the data learning control in the defect parameter adjustment interface, and obtain the target defect true value range corresponding to the target defect type and matching the feature value of each defect feature.

[0086] In this way, when re-detecting defects, the characteristic value of the abnormal area can match the defect judgment condition corresponding to the target defect type, that is, the defect type of the abnormal area is detected as the target defect type, thereby achieving the purpose of more accurate defect detection. The defect detection parameter adjustment method provided in the embodiment of the present application does not require the staff to manually adjust according to their own experience, can avoid errors and delays caused by human factors, thereby improving the accuracy and reliability of defect detection. At the same time, it can reduce the manual operation and judgment time of the staff in defect detection, so as to improve the detection efficiency in the defect detection process.

[0087] In some embodiments, since different defect types correspond to different defect judgment conditions, the basis for adjusting parameters is also different. Therefore, in practical applications, a parameter prediction model can be trained for each defect type. When the staff selects the data learning control and needs to adjust the parameters, the target parameter prediction model corresponding to the defect type is used to determine the adjusted target defect true value range.

[0088] Specifically, as a feasible implementation method, S203 can be implemented as: inputting multiple characteristic values ​​of the abnormal area corresponding to the initial defect type and multiple initial defect true value ranges corresponding to the target defect type into the target parameter prediction model corresponding to the target defect type to obtain multiple target defect true value ranges corresponding to the target defect type.

[0089] Among them, the target parameter prediction model is used to adjust multiple initial defect true value ranges based on multiple characteristic values ​​to obtain multiple target defect true value ranges.

[0090] As a feasible implementation method, the target parameter prediction model can be a linear regression model, which is a statistical analysis method used to establish a linear relationship between independent variables (input) and dependent variables (output). In linear regression, it is assumed that the dependent variable (target defect true value range) is a linear combination of independent variables (characteristic values ​​and initial defect true value range), and the best linear relationship is found through data fitting to predict the new dependent variable value.

[0091] The characteristic values ​​corresponding to multiple defect features represent multiple factors that affect the true value of the target defect. In the target parameter prediction model, each feature can have a corresponding weight coefficient to indicate the degree of influence of the feature on the target variable. Then, multiple target defect true value ranges are calculated based on the data input to the model and the corresponding weight coefficients.

[0092] Specifically, as a feasible implementation method, the characteristic value corresponding to each defect feature among multiple defect features and the upper limit value and lower limit value of the initial defect true value range can be used as the input of the target parameter prediction model, and the output of the target parameter prediction model is the upper limit value and lower limit value of the target defect true value range.

[0093] In some embodiments, see Figure 5 The target parameter prediction model provided in the embodiment of the present application can be trained in the following way:

[0094] S501. Acquire multiple sample data corresponding to the target defect type.

[0095] Each sample data includes a historical feature value corresponding to each defect feature among multiple defect features, an initial historical defect true value range, and a target historical defect true value range.

[0096] When training the target parameter prediction model corresponding to the initial defect type, it is necessary to obtain a plurality of sample data corresponding to the initial defect type.

[0097] It should be understood that as a feasible implementation method, when the staff manually adjusts the parameters of the target defect type, the historical feature values ​​corresponding to each detected defect feature, as well as the unadjusted defect judgment conditions (multiple initial historical defect true value ranges) and the manually adjusted defect judgment conditions (multiple target historical defect true value ranges) can be saved as sample data corresponding to the target defect type.

[0098] S502 : Training an initial parameter prediction model based on a plurality of sample data corresponding to the target defect type to obtain a target parameter prediction model corresponding to the target defect type.

[0099] After obtaining multiple sample data corresponding to the target defect type, the historical feature values ​​corresponding to the multiple defect features in the sample data and the initial historical defect true value range can be input into the initial parameter prediction model, and then the loss function is calculated based on the error between the predicted value output by the initial parameter prediction model and the expected value (multiple target historical defect true value ranges). The initial parameter prediction model is trained by minimizing the loss function until the preset iteration stop condition is met, and the target parameter prediction model corresponding to the initial defect type is obtained.

[0100] As a feasible implementation method, the loss function can be calculated by calculating the square difference between the predicted value and the expected value output by the initial parameter prediction model.

[0101] It should be understood that the preset iteration stop condition may be reaching a preset number of iterations, reaching a preset training time, a loss function value being lower than a preset threshold, etc., and the embodiments of the present application do not impose any restrictions on this.

[0102] It can be seen that the defect detection parameter adjustment method provided in this embodiment obtains multiple sample data corresponding to the target defect type to train the target parameter prediction model corresponding to the target defect type. The obtained target parameter prediction model can adjust parameters more accurately, and thus can obtain more accurate defect judgment conditions for the target defect type.

[0103] In some embodiments, whether parameter adjustment is needed is determined by the staff based on their own experience, so there may be misjudgment. At this time, the updated defect judgment conditions of the target defect type obtained after adjusting the initial defect true value range may not be reasonable.

[0104] Therefore, as a feasible implementation method, in order to avoid the phenomenon of misadjustment of parameters, please refer to Figure 6 , the defect detection parameter adjustment method provided in the embodiment of the present application, after updating the defect judgment condition corresponding to the target defect type, the method further includes:

[0105] S601. Acquire multiple historical defect judgment conditions corresponding to the target defect type.

[0106] It can be understood that the historical defect judgment conditions corresponding to the target defect type, that is, the multiple initial defect true value ranges corresponding to the target defect type each time the defect judgment conditions for the target defect type are updated.

[0107] S602: Determine the confidence of the updated defect judgment condition corresponding to the target defect type based on multiple historical defect judgment conditions.

[0108] It should be understood that the confidence level can be used to indicate the degree of similarity between the updated defect judgment condition and a plurality of historical defect judgment conditions.

[0109] As a feasible implementation method, the confidence of a single defect feature in the updated defect judgment condition can be calculated first: for each feature, the confidence of the defect true value range in the updated defect judgment condition and the defect true value range in each historical defect judgment condition is calculated. Interval overlap, Jaccard similarity and other methods can be used for calculation. For example, interval overlap can be defined as the ratio of the length of the intersection of two intervals to the length of their union.

[0110] Furthermore, since the importance of different features in the judgment conditions may be different, a weight can be assigned to each feature. The weight can be determined according to the actual situation, for example, by expert scoring, historical data analysis, etc. Then, the similarity of each feature is multiplied by its corresponding weight, and the sum is obtained to obtain the confidence of the updated defect judgment condition and each historical defect judgment condition. Then, the confidence of the updated defect judgment condition is obtained based on the confidence of the updated defect judgment condition and multiple historical defect judgment conditions by methods such as averaging.

[0111] S603: When the confidence level is less than or equal to a preset confidence level threshold, output a prompt message.

[0112] Among them, the prompt information is used to prompt the staff to determine whether the updated defect judgment conditions are reasonable.

[0113] It should be understood that the preset confidence threshold is pre-set and can be set according to needs during actual application, and the embodiments of the present application do not limit this.

[0114] When the calculated confidence level is less than or equal to the preset confidence threshold, it usually means that the result may not be reliable enough or further analysis is needed. In this case, a prompt message needs to be output to prompt the staff to intervene manually to avoid unreasonable defect judgment conditions.

[0115] It should be understood that the prompt information should clearly and unambiguously convey that the confidence level is less than or equal to the preset confidence threshold, and may include recommended actions (such as collecting more data, reconsidering the analysis method, etc.). The embodiments of the present application do not limit the specific content of the prompt information.

[0116] It is understandable that the defect detection parameter adjustment method provided in the above embodiment is mainly used for the phenomenon of false detection, that is, in the process of defect detection, the abnormal area that does not belong to the initial defect type is mistakenly identified as the initial defect type, so the defect judgment condition of the target defect type is adjusted so that the initial defect type can be more accurately identified in the defect detection process. However, in the process of defect detection, there will not only be false detection, but also missed detection, that is, multiple feature values ​​of multiple defect features of the abnormal area do not match multiple defect judgment conditions. At this time, it can be determined that the defect type corresponding to the abnormal area is a classification filtering defect.

[0117] That is, as a feasible implementation method, when the characteristic values ​​of multiple defect features in the abnormal area do not match the defect judgment conditions of other defect types in multiple defect types, the abnormal area is determined to be a classified filtering defect. The abnormal area is filtered out, and it is considered that it does not belong to other defect types during the defect detection process, that is, a phenomenon of missed detection occurs.

[0118] At this time, assuming that the staff believes that any defect type exists in the abnormal area, they can select the parameter adjustment control corresponding to the classification and filtering defects in the defect display interface to display the defect parameter adjustment interface corresponding to the classification and filtering defects, so that the staff can select the target defect type corresponding to the abnormal area and adjust the parameters. The specific adjustment method can be referred to the above embodiment, and this embodiment will not be repeated here.

[0119] The present application also provides a defect detection parameter adjustment device, such as Figure 7 As shown, the defect detection and parameter adjustment device 70 includes: a display module 71, an adjustment module 72 and an update module 73.

[0120] Among them, the display module 71 is used to display the defect parameter adjustment interface corresponding to the initial defect type in response to the parameter adjustment operation for the initial defect type in the defect display interface; the defect display interface is used to display the defect type obtained by detecting the image to be detected based on the defect judgment conditions corresponding to each defect type in multiple defect types; the defect parameter adjustment interface includes: multiple feature values ​​corresponding to multiple defect features of the abnormal area corresponding to the initial defect type, defect selection controls, and data learning controls.

[0121] The adjustment module 72 is used to obtain multiple initial defect true value ranges corresponding to the target defect type in the defect selection control in response to a trigger operation on the data learning control, and adjust the multiple initial defect true value ranges corresponding to the target defect type based on multiple characteristic values ​​of the abnormal area corresponding to the initial defect type to obtain multiple target defect true value ranges corresponding to the target defect type; wherein the target defect true value range corresponding to each defect feature matches the characteristic value corresponding to the defect feature.

[0122] The updating module 73 is used to update the defect judgment conditions corresponding to the target defect types based on multiple target defect true value ranges.

[0123] In some embodiments, the adjustment module 72 is specifically used to input multiple characteristic values ​​of the abnormal area corresponding to the initial defect type and multiple initial defect true value ranges corresponding to the target defect type into a target parameter prediction model corresponding to the target defect type to obtain multiple target defect true value ranges corresponding to the target defect type; the target parameter prediction model is used to adjust the multiple initial defect true value ranges based on the multiple characteristic values ​​to obtain multiple target defect true value ranges.

[0124] In some embodiments, the defect detection parameter adjustment device 70 also includes: an acquisition module, used to acquire multiple historical defect judgment conditions corresponding to the target defect type; the determination module is also used to determine the confidence of the updated defect judgment condition corresponding to the target defect type based on multiple historical defect judgment conditions; the output module is used to output a prompt message when the confidence is less than or equal to a preset confidence threshold, and the prompt message is used to prompt the staff to determine whether the updated defect judgment condition is reasonable.

[0125] In some embodiments, the defect detection parameter adjustment device 70 also includes: a determination module, which is used to determine the abnormal area in the image to be detected, and determine the feature values ​​of multiple defect features corresponding to the abnormal area; a matching module, which is used to match the defect judgment conditions corresponding to the defect type with the feature values ​​of multiple defect features corresponding to the abnormal area according to the defect type order recorded in the defect priority, so as to determine the defect type obtained by detecting the image to be detected; the display module 71 is also used to display the defect type obtained by detecting the image to be detected through a defect display interface.

[0126] In some embodiments, the defect parameter adjustment interface also includes: a feature state corresponding to each defect feature; the feature state is used to indicate whether the feature value corresponding to the defect feature matches the initial defect true value range; and / or, display controls and adjustment controls corresponding to each initial defect true value range.

[0127] In some embodiments, the defect display interface also includes: an image to be detected and a display box of an abnormal area corresponding to the defect type obtained by detecting the image to be detected; and / or filtered defects corresponding to the image to be detected, the filtered defects are used to represent defects in the abnormal area in the image to be detected whose feature values ​​of multiple defect features of the abnormal area do not match multiple defect judgment conditions corresponding to multiple defect types.

[0128] The present application also provides an electronic device. Figure 8The electronic device 201 includes: one or more memories 121, one or more processors 122, a communication bus 123 and a communication interface 124. The processor 122 is connected to the memory 121 via the communication bus 123; the one or more memories 121 are used to store computer program codes, and the computer program codes include computer instructions; when the one or more processors 122 execute the computer instructions, the electronic device 201 executes the defect detection parameter adjustment method provided in the above embodiment.

[0129] Optionally, the memory 121 may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc., and the embodiments of the present application do not impose any restrictions on this.

[0130] The processor 122 may be a central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof, and the embodiments of the present application do not impose any limitation on this.

[0131] The communication bus 123 may be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus. The communication bus 123 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Just one thick line is used, but it does not mean that there is only one bus or one type of communication bus.

[0132] The communication interface 124 uses any transceiver or other device for communicating with other devices or communication networks, such as control systems, radio access networks (RAN), wireless local area networks (WLAN), etc.

[0133] The embodiments of the present application also provide a computer program product including one or more instructions, where the one or more instructions are stored in a memory of a computer device and executed by a processor to complete the various processes of the above embodiments.

[0134] An embodiment of the present application also provides a computer-readable storage medium, which includes computer execution instructions. When the computer execution instructions are executed on a computer, the computer executes the defect detection parameter adjustment method provided in the above embodiment.

[0135] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0136] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0137] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0138] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0139] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a device or processor to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.

[0140] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A defect detection parameter adjustment method, characterized in that: include: In response to the parameter adjustment operation for the initial defect type in the defect display interface, display the defect parameter adjustment interface corresponding to the initial defect type; The defect display interface is used to display the defect type obtained by detecting the image to be detected based on the defect judgment condition corresponding to each defect type in the multiple defect types; The defect display interface also includes the image to be detected and a display frame of an abnormal area corresponding to the defect type obtained by detecting the image to be detected; The defect parameter adjustment interface includes: a plurality of feature values ​​corresponding to a plurality of defect features of the abnormal area corresponding to the initial defect type, a defect selection control, and a data learning control; In response to a trigger operation on the data learning control, a plurality of initial defect true value ranges corresponding to a target defect type in the defect selection control are obtained, and a plurality of characteristic values ​​of an abnormal region corresponding to the initial defect type and a plurality of initial defect true value ranges corresponding to the target defect type are input into a target parameter prediction model corresponding to the target defect type to obtain a plurality of target defect true value ranges corresponding to the target defect type; wherein the target defect type is a real defect type of an abnormal region corresponding to the initial defect type; a target defect true value range corresponding to each defect feature matches a characteristic value corresponding to the defect feature; the target parameter prediction model is used to adjust the plurality of initial defect true value ranges based on the plurality of characteristic values ​​to obtain the plurality of target defect true value ranges; Based on the multiple target defect true value ranges, the defect judgment condition corresponding to the target defect type is updated.

2. The method according to claim 1, characterized in that The target parameter prediction model is trained in the following way: Acquire a plurality of sample data corresponding to the target defect type, wherein each of the sample data includes a historical feature value corresponding to each defect feature in a plurality of defect features, an initial historical defect true value range, and a target historical defect true value range; An initial parameter prediction model is trained based on a plurality of sample data corresponding to the target defect type to obtain a target parameter prediction model corresponding to the target defect type.

3. The method according to claim 1, characterized in that After the defect judgment condition corresponding to the target defect type is updated, the method further includes: Acquire multiple historical defect judgment conditions corresponding to the target defect type; Determining the confidence of the updated defect judgment condition corresponding to the target defect type based on the multiple historical defect judgment conditions; When the confidence level is less than or equal to a preset confidence threshold, a prompt message is output, where the prompt message is used to prompt the staff to determine whether the updated defect judgment condition is reasonable.

4. The method according to claim 1, characterized in that The method further comprises: Determine an abnormal area in the image to be detected, and determine feature values ​​of multiple defect features corresponding to the abnormal area; According to the defect type order recorded in the defect priority, the defect judgment condition corresponding to the defect type is matched with the feature values ​​of multiple defect features corresponding to the abnormal area to determine the defect type obtained by detecting the image to be detected; The defect type obtained by detecting the image to be detected is displayed through the defect display interface.

5. The method according to any one of claims 1 to 4, characterized in that: The defect parameter adjustment interface also includes: a feature state corresponding to each of the defect features; the feature state is used to indicate whether the feature value corresponding to the defect feature matches the initial defect true value range; and / or, display controls and adjustment controls corresponding to each of the initial defect true value ranges.

6. The method according to any one of claims 1 to 4, characterized in that: The defect display interface also includes: filtered defects corresponding to the image to be detected, and the filtered defects are used to represent defects in the abnormal area in the image to be detected whose feature values ​​of multiple defect features of the abnormal area do not match multiple defect judgment conditions corresponding to the multiple defect types.

7. A defect detection parameter adjustment device, characterized in that: include: A display module, configured to respond to a parameter adjustment operation for an initial defect type in a defect display interface and display a defect parameter adjustment interface corresponding to the initial defect type; The defect display interface is used to display the defect type obtained by detecting the image to be detected based on the defect judgment condition corresponding to each defect type in the multiple defect types; The defect display interface also includes the image to be detected and a display frame of an abnormal area corresponding to the defect type obtained by detecting the image to be detected; The defect parameter adjustment interface includes: a plurality of feature values ​​corresponding to a plurality of defect features of the abnormal area corresponding to the initial defect type, a defect selection control, and a data learning control; An adjustment module, for obtaining, in response to a trigger operation on the data learning control, a plurality of initial defect true value ranges corresponding to a target defect type in the defect selection control, and inputting a plurality of characteristic values ​​of an abnormal region corresponding to the initial defect type and a plurality of initial defect true value ranges corresponding to the target defect type into a target parameter prediction model corresponding to the target defect type, to obtain a plurality of target defect true value ranges corresponding to the target defect type; wherein the target defect type is a real defect type of an abnormal region corresponding to the initial defect type; the target defect true value range corresponding to each defect feature matches the characteristic value corresponding to the defect feature; the target parameter prediction model is used to adjust the plurality of initial defect true value ranges based on the plurality of characteristic values, to obtain the plurality of target defect true value ranges; An updating module is used to update the defect judgment condition corresponding to the target defect type based on the multiple target defect true value ranges.

8. An electronic device, characterized in that: include: one or more processors; one or more memories; Wherein, the one or more memories are used to store computer program codes, and the computer program codes include computer instructions. When the one or more processors execute the computer instructions, the electronic device executes the defect detection parameter adjustment method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer execution instructions, and when the computer execution instructions are executed on a computer, the computer executes the defect detection parameter adjustment method according to any one of claims 1 to 6.

Images