Corner defect detection method and device for copper-plated plate and storage medium

Abstract

The invention provides a bevel defect detection method and device for a copper-plated plate and a storage medium, and the method comprises the steps: obtaining a to-be-detected image which comprises a hanger clamping region; judging whether a copper-plated plate is clamped in the hanging frame clamping area in the to-be-detected image or not; and if the to-be-detected image is clamped with the copper-plated plate, generating a bevel defect identification result corresponding to the copper-plated plate according to the to-be-detected image. According to the technical scheme provided by the invention, the bevel defects of the copper-plated plate can be quickly and automatically judged, and tedious manual check one by one and judgment of bevel conditions by naked eyes are not needed. The detection period is greatly shortened, the copper-plated plate with the break angle defect can be found in time in scenes such as the production process, defective products are prevented from flowing into subsequent procedures or markets, and the product quality is guaranteed.

Description

Technical Field

[0001] The present application relates to the technical field of defect detection, and in particular to a method, device and storage medium for detecting corner defects of copper-plated plates. Background Art

[0002] The vertical continuous copper electroplating production line used for electroplating of circuit boards has good electroplating distribution, hole filling and hole filling capabilities, and stable electroplating quality.

[0003] At present, the problems of product defects and equipment defects in vertical continuous copper electroplating production lines are all monitored by manual visual inspection, and the loading position, copper plating pool, and unloading position are set in different areas, resulting in a single person being unable to fully monitor the problems of product defects and equipment defects in vertical continuous copper electroplating production lines. The current inspection intensity and persistence cannot continuously identify and detect, and cannot find and deal with problems in a timely manner.

[0004] The inventors found that among the product defects involved in the vertical continuous copper electroplating production line, corner defects are particularly common. In view of this, a method for detecting corner defects of copper-plated plates is urgently needed to timely identify products with corner defects on the vertical continuous copper electroplating production line. Summary of the invention

[0005] In view of this, the present application provides a method, device and storage medium for detecting corner defects of copper-plated plates, so as to timely identify copper-plated plate materials with corner defects on a vertical continuous copper electroplating production line.

[0006] In a first aspect, the present application provides a method for detecting corner defects of a copper-plated plate, which is applied to a vertical continuous copper electroplating production line, and the method comprises:

[0007] Acquire an image to be detected, wherein the image to be detected includes a hanger clamping area;

[0008] Determine whether the material clamping area of ​​the rack in the image to be detected clamps a copper-plated plate;

[0009] If a copper-plated plate is clamped, a corner defect recognition result corresponding to the copper-plated plate is generated according to the image to be detected.

[0010] Preferably, the generating of the corner defect recognition result corresponding to the copper-plated plate according to the image to be detected includes:

[0011] Identify the copper-plated plate in the image to be detected, and generate an actual contour corresponding to the copper-plated plate;

[0012] Generating a standard outline corresponding to the copper-plated plate according to the actual outline;

[0013] Determining whether the actual contour completely overlaps with the standard contour;

[0014] If the actual profile completely coincides with the standard profile, it is determined that the copper-plated plate does not have a corner defect;

[0015] If the actual contour does not completely coincide with the standard contour, it is determined that the copper-clad plate has a corner defect.

[0016] Preferably, the step of generating a corner defect recognition result corresponding to the copper-plated plate according to the image to be detected further includes:

[0017] After determining that the copper-plated plate has a corner defect, determining the area where the actual contour and the standard contour do not overlap, and determining the corner position corresponding to each non-overlapping area;

[0018] The corner positions include upper left, lower left, upper right and lower right.

[0019] Preferably, the step of generating a corner defect recognition result corresponding to the copper-plated plate according to the image to be detected further includes:

[0020] Based on the standard contour, determining a standard area corresponding to each non-overlapping area;

[0021] Cut out images from the image to be inspected in sequence according to each standard area to obtain a set of small images of corner defects;

[0022] Based on the trained corner type recognition model, the corner defect thumbnails are identified in turn, and the corner types corresponding to the defect thumbnails are generated, wherein the corner types include inner fold and outer fold.

[0023] Preferably, the generating of the corner defect recognition result corresponding to the copper-plated plate according to the image to be detected includes:

[0024] Based on the trained corner defect recognition model, identify all corner defects in the image to be detected and the corner type corresponding to each corner defect;

[0025] The corner position corresponding to each corner defect is determined, and the corner type corresponding to each corner defect is combined to generate a corner defect recognition result corresponding to the copper-plated plate.

[0026] Preferably, determining the angle position corresponding to each angle defect includes:

[0027] According to the image coordinates corresponding to each folding corner defect, the target folding corner position corresponding to each folding corner defect is determined;

[0028] The corner positions include upper left, lower left, upper right and lower right, and each corner position is preset with a corresponding coordinate range.

[0029] Preferably, it also includes:

[0030] If the hanger clamping area holds two copper-plated plates, then corner defect recognition results corresponding to the two copper-plated plates are generated one by one according to the image to be detected.

[0031] In a second aspect, the present application provides a device for detecting corner defects of a copper-plated plate, which is applied to a vertical continuous copper electroplating production line, comprising:

[0032] An image acquisition module, used for acquiring an image to be detected, wherein the image to be detected includes a hanger clamping area;

[0033] A board holding judgment module, used for judging whether the material clamping area of ​​the rack in the image to be detected is clamping a copper-plated board;

[0034] The corner recognition module is used to generate a corner defect recognition result corresponding to the copper-plated plate according to the image to be detected when a copper-plated plate is clamped in the clamping area of ​​the hanger.

[0035] In a third aspect, the present application provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to implement the method for detecting corner defects of copper-plated plates described in the first aspect.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method for detecting corner defects of copper-plated plates described in the first aspect is implemented.

[0037] The method, device and storage medium for detecting corner defects of copper-plated plates provided in the present application have at least the following beneficial effects:

[0038] The technical solution provided by this application can quickly and automatically determine the corner defects of copper-plated plates, without the need for tedious manual inspections and visual judgment of the corner conditions. This greatly shortens the detection cycle and helps to promptly detect copper-plated plates with corner defects in production processes and other scenarios, preventing defective products from flowing into subsequent processes or the market, thereby ensuring product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the specific implementation methods or the prior art descriptions. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings without creative work. It should be noted that the drawings described below are schematic and should not be understood as any limitation to the present application. In the drawings:

[0040] Figure 1 A schematic diagram of a method for detecting corner defects of a copper-plated plate in one embodiment of the present application is shown;

[0041] Figure 2 A schematic diagram showing an embodiment of the present application in which a copper-plated plate is not clamped is shown;

[0042] Figure 3 A schematic diagram of a copper-plated plate clamped in one embodiment of the present application is shown;

[0043] Figure 4 A partial schematic diagram of a corner defect in one embodiment of the present application is shown;

[0044] Figure 5 A schematic diagram of a device for detecting corner defects of a copper-plated plate in one embodiment of the present application is shown;

[0045] Figure 6 A schematic diagram of a computer device in one embodiment of the present application is shown. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0047] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present application. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0048] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, it can also be the internal connection of two components, it can be a wireless connection, or it can be a wired connection. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0049] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0050] Although the processes described below include multiple operations that appear in a specific order, it should be clearly understood that these processes may also include more or fewer operations, and these operations may be performed sequentially or in parallel.

[0051] Example 1

[0052] See also Figure 1 A method for detecting corner defects of copper-plated plates provided in one embodiment of the present application is applied to a vertical continuous copper electroplating production line and may include the following steps.

[0053] S101, acquiring an image to be detected, wherein the image to be detected includes a hanger clamping area.

[0054] Specifically, in a vertical continuous copper electroplating production line, a plate to be copper-plated is clamped by a rack, and then the plate on the rack is subjected to copper electroplating through the copper electroplating production line to obtain a copper-plated plate. A camera is set and the lens is aimed at the rack clamping area to capture the rack clamping area.

[0055] S102, determining whether the material clamping area of ​​the rack in the image to be detected clamps a copper-plated plate.

[0056] Specifically, in the collected image to be detected, there is an obvious difference in color levels between the copper-plated plate and the background. A simple threshold method can be used to calculate whether a copper-plated plate is clamped in the image to be detected. For example, it is determined whether the pixel grayscale mean of the target area is within the preset grayscale threshold corresponding to the copper-plated plate. If it is within the threshold, it means that the pixel grayscale in the target area is consistent with the pixel grayscale of the copper-plated plate, and it can be determined that a copper-plated plate is clamped at this time. Otherwise, it means that the copper-plated plate is not clamped and there is no background in the target area.

[0057] Specifically, since the copper-plated board has obvious edges, it is also possible to use edge detection-based methods, such as using the Sobel operator or the Canny edge detection operator, to determine whether the edge of the copper-plated board can be detected, whether the detected edge can form a closed shape, and whether the closed shape is the copper-plated board.

[0058] Specifically, it is also possible to determine whether a copper-plated plate is clamped in the image to be detected through a deep learning method, for example, through a convolutional neural network CNN, automatically learn the features of the copper-plated plate in the image, and build multiple convolutional layers, pooling layers and fully connected layers. The neural network learns the feature representation of the copper-plated plate from a large amount of image data, and detects the presence or absence of the copper-plated plate through the trained neural network model. It should be noted that commonly used models such as Faster R-CNN, YOLO, etc. can directly locate and determine whether there is a target object in the image, which will not be repeated here.

[0059] See also Figure 2 As shown, the copper-plated board is not clamped in the image to be detected, see Figure 3 As shown, a copper-plated board is clamped in the image to be inspected.

[0060] S103: If a copper-plated plate is clamped, a corner defect recognition result corresponding to the copper-plated plate is generated according to the image to be detected.

[0061] Specifically, the occurrence of the copper-plated plate corner defect requires the existence of a copper-plated plate. If there is no copper-plated plate in the image to be detected, it means that the rack has dropped material. In the case of material drop, there is no copper-plated plate, and there is no corner defect. Therefore, if there is a copper-plated plate in the image to be detected, it can be identified whether there is a corner defect in the copper-plated plate in the image to be detected based on the image to be detected.

[0062] In this embodiment, by first determining whether the rack clamping area in the image to be detected has a copper-plated plate, it is possible to accurately distinguish whether there is a copper-plated plate object that needs to be detected for corner defects. This avoids the invalid subsequent detection process when there is no copper-plated plate, effectively saves detection resources and time, improves the pertinence and efficiency of the overall detection work, and ensures that each detection action is carried out for the actual copper-plated plate. After confirming that the rack clamping area has a copper-plated plate, the corresponding corner defect recognition result can be quickly generated according to the image to be detected. This makes it possible to quickly and automatically determine the corner defects of the copper-plated plate without the need for manual tedious inspections and visual judgment of the corners. The detection cycle is greatly shortened, which helps to timely detect copper-plated plates with corner defects in scenes such as production processes, avoid defective products from flowing into subsequent processes or markets, and ensure product quality. The entire detection process is carried out by obtaining the image to be detected, which has the characteristics of non-contact detection. No secondary damage such as scratches and wear will be caused to the surface of the copper-plated plate, which well protects the appearance integrity of the copper-plated plate, which is particularly important for copper-plated plate products with high surface quality requirements. At the same time, image detection can accurately record the appearance of the copper-plated board, providing a clear and intuitive basis for subsequent quality tracing and analysis of the causes of defects, and facilitating enterprises to continuously optimize production processes and quality control measures. The efficiency and accuracy of this detection method help to achieve real-time monitoring of the corner defects of copper-plated boards on the production line. Once a defective copper-plated board is discovered in time, corresponding measures can be taken quickly, such as adjusting the production equipment and optimizing the production process parameters. Overall, it can effectively reduce product rework and scrapping caused by corner defects of copper-plated boards, reduce production costs, improve production efficiency, and enhance the economic benefits and market competitiveness of enterprises in the field of copper-plated board production.

[0063] In an optional implementation, generating a corner defect recognition result corresponding to the copper-plated plate according to the image to be detected includes:

[0064] Identify the copper-plated plate in the image to be detected, and generate an actual contour corresponding to the copper-plated plate;

[0065] Generating a standard outline corresponding to the copper-plated plate according to the actual outline;

[0066] Determining whether the actual contour completely overlaps with the standard contour;

[0067] If the actual profile completely coincides with the standard profile, it is determined that the copper-plated plate does not have a corner defect;

[0068] If the actual contour does not completely coincide with the standard contour, it is determined that the copper-clad plate has a corner defect.

[0069] In this embodiment, the actual contour of the copper-plated plate is generated for the identified copper-plated plate, and then the standard contour corresponding to the actual contour is generated. Specifically, the corresponding standard contour generated is the circumscribed rectangular contour of the actual contour. Because in actual production applications, different types of copper-plated plate materials may have different size specifications, and the same type of copper-plated plate materials may also have slight deviations in size. If a fixed standard contour is used for comparison to determine whether there is a corner defect on the copper-plated plate, it is easy to cause misjudgment. And if it is reused for other vertical continuous electroplating copper production lines, due to the setting of the camera position, it is necessary to reset the fixed standard contour parameters. In fact, in the actual production line, it is impossible to ensure that each hanger is a standard vertical hanging and grabbing copper-plated plate, that is, the copper-plated plate may be tilted. If a fixed standard contour is used to determine whether the tilted copper-plated plate has this defect, it is also easy to cause misjudgment.

[0070] In this embodiment, a standard contour corresponding to the actual contour of the copper-plated plate is generated and overlapped with the actual contour of the copper-plated plate to determine whether the copper-plated plate has defects. This method has high accuracy and high reusability for copper-plated corner defects, and can ignore the tilt problem of the copper-plated plate, thereby improving the detection efficiency of corner defects of the copper-plated plate.

[0071] Preferably, the step of generating a corner defect recognition result corresponding to the copper-plated plate according to the image to be detected further includes:

[0072] After determining that the copper-plated plate has a corner defect, determining the area where the actual contour and the standard contour do not overlap, and determining the corner position corresponding to each non-overlapping area;

[0073] The corner positions include upper left, lower left, upper right and lower right.

[0074] In this embodiment, by determining the area where the actual contour and the standard contour do not overlap, the specific part of the copper-plated plate where the difference exists can be found in a relatively accurate manner, thereby providing a clear target area for subsequent targeted treatment of the corner defect based on the accurate position.

[0075] The corresponding angle position (upper left, lower left, upper right and lower right) of each non-overlapping area is further clarified, making the positioning of angle defects more detailed and accurate. In actual production or testing, this precise location information helps maintenance personnel or related equipment to quickly and directly repair or adjust defects at specific angles, improve repair efficiency, and reduce the time wasted on repeated inspections due to unclear defect locations.

[0076] Further, based on these detailed information on the location of the corner defects, the frequency of defects at various corners of different batches of copper-plated plates can be counted, and then the weak links that may exist in the production process can be analyzed, such as whether a certain production process link is prone to defects at a specific position (such as the upper right corner), so as to optimize and adjust the production process in a timely manner and improve the overall quality of the product. Improve the production efficiency of the entire production line. At the same time, by accurately repairing defective products, the number of products scrapped due to defects is reduced. In the past, some products may have been misjudged as unrepairable and had to be scrapped because the location of the corner defects could not be accurately determined. Now, more defective products can be effectively repaired, reducing the waste of raw materials, reducing production costs, and improving the economic benefits of the enterprise.

[0077] Preferably, the step of generating a corner defect recognition result corresponding to the copper-plated plate according to the image to be detected further includes:

[0078] Based on the standard contour, determining a standard area corresponding to each non-overlapping area;

[0079] Cut out images from the image to be inspected in sequence according to each standard area to obtain a set of small images of corner defects;

[0080] Based on the trained corner type recognition model, the corner defect thumbnails are identified in turn, and the corner types corresponding to the defect thumbnails are generated, wherein the corner types include inner fold and outer fold.

[0081] In this embodiment, by sequentially cutting out images from the image to be tested according to each standard area, each part related to the folded corner in the copper-plated plate image can be extracted separately to form a collection of small images of folded corner defects. This is like decomposing a complex whole into small units that are easy to study, so that subsequent analysis can focus on these specific folded corner areas, avoiding interference factors that may occur when the entire image is processed indiscriminately, and improving the pertinence and accuracy of the analysis.

[0082] In this embodiment, the corner defect sub-image is identified based on the trained corner type recognition model, which can give full play to the recognition ability of the model for different corner type features accumulated in the process of training with a large amount of data.

[0083] Preferably, the generating of the corner defect recognition result corresponding to the copper-plated plate according to the image to be detected includes:

[0084] Based on the trained corner defect recognition model, identify all corner defects in the image to be detected and the corner type corresponding to each corner defect;

[0085] The corner position corresponding to each corner defect is determined, and the corner type corresponding to each corner defect is combined to generate a corner defect recognition result corresponding to the copper-plated plate.

[0086] After targeted training, the model has been able to keenly capture the unique features of different types of folds, such as inward folds and outward folds, in the image. For example, the lines of inward folds may be concave, while those of outward folds may be convex. This allows the model to accurately classify and identify each corner defect image and generate the corresponding corner type. Based on the trained corner type recognition model, the corner defect images are identified one by one, which can make full use of the rich knowledge and discrimination rules about corner features learned by the model during the training stage. After training with a large number of samples, the model has been able to accurately capture the subtle differences in the images of different types of folds, such as inward folds and outward folds, thereby achieving accurate judgment of the corner type.

[0087] By generating accurate data on the type of folded corners, statistical analysis can be easily performed. Enterprises can count the number and proportion of internal and external folded defects in different batches of copper-plated plates to evaluate the stability of the production process, the packaging protection effect, and other aspects, providing strong data support for the continuous improvement of production and management processes.

[0088] Preferably, determining the angle position corresponding to each angle defect includes:

[0089] According to the image coordinates corresponding to each folding corner defect, the target folding corner position corresponding to each folding corner defect is determined;

[0090] The corner positions include upper left, lower left, upper right and lower right, and each corner position is preset with a corresponding coordinate range.

[0091] In this embodiment, the target corner position corresponding to each corner defect is determined by the image coordinates corresponding to the corner defect, that is, the position of the corner defect relative to the standard contour is determined. In the image to be detected, the image coordinate information corresponding to the corner defect only expresses the information of the defect relative to the image to be detected, and cannot express the position information of the corner defect relative to the copper-plated plate. Therefore, if the specific information of the corner defect on the copper-plated plate needs to be clarified, it is necessary to convert it based on the generated standard contour of the copper-plated plate, so as to obtain the position of the corner defect based on the standard contour of the copper-plated plate. It should be noted that the positions of the above-mentioned corner defects include the upper left, lower left, upper right and lower right. At the same time, the position of the corner defect can also include specific coordinate information relative to the standard contour. See. Figure 4 As shown, the corner defect is located at the lower right, the starting adjacent corner (lower side) is 20.00 mm (the length of the lower dotted line) away from the lower right point of the standard contour, and the ending adjacent corner (right side) is 18.00 mm (the length of the right dotted line) away from the lower right point of the standard contour.

[0092] In this embodiment, by converting the image coordinates corresponding to the corner defect into the positional relationship of the corner defect relative to the standard contour, the specific information of the corner defect can be accurately understood, and then the accurate determination of the corner position, adjacent angle and other information can be further achieved, further improving the detection accuracy and efficiency of the corner defect.

[0093] Preferably, it also includes:

[0094] If the hanger clamping area holds two copper-plated plates, then corner defect recognition results corresponding to the two copper-plated plates are generated one by one according to the image to be detected.

[0095] In this embodiment, see Figure 3 As shown in the figure, if there are two copper-plated plates in the image to be inspected, the corner defects of the two copper-plated plates can be detected and identified simultaneously in an asynchronous manner. This improves the inspection efficiency and the applicability of the production line. It provides strong data support for the continuous improvement and management process of the double-row production line.

[0096] Example 2

[0097] This embodiment provides a device for detecting corner defects of a copper-plated plate, and describes the method for detecting corner defects of a copper-plated plate provided in the above-mentioned embodiment 1. Figure 5 As shown, a device for detecting corner defects of copper-plated plates provided in one embodiment of the present application is applied to a vertical continuous copper electroplating production line and may include the following multiple modules.

[0098] An image acquisition module, used for acquiring an image to be detected, wherein the image to be detected includes a hanger clamping area;

[0099] A board holding judgment module, used for judging whether the material clamping area of ​​the rack in the image to be detected is clamping a copper-plated board;

[0100] The corner recognition module is used to generate a corner defect recognition result corresponding to the copper-plated plate according to the image to be detected when a copper-plated plate is clamped in the clamping area of ​​the hanger.

[0101] The device for detecting corner defects of copper-plated plates provided in the embodiment of the present application can be applied to the method for detecting corner defects of copper-plated plates provided in the above-mentioned embodiment 1. For relevant details, refer to the above-mentioned method embodiment. The implementation principles and technical effects are similar and will not be repeated here.

[0102] It should be noted that: when the device for detecting corner defects of copper-plated boards provided in the embodiments of the present application performs corner defect detection of copper-plated boards, only the division of the above-mentioned functional modules / functional units is used as an example. In practical applications, the above-mentioned functions can be assigned to different functional modules / functional units as needed, that is, the internal structure of the device for detecting corner defects of copper-plated boards is divided into different functional modules / functional units to complete all or part of the functions described above. In addition, the implementation method of the method for detecting corner defects of copper-plated boards provided in the above-mentioned method embodiment 1 and the implementation method of the device for detecting corner defects of copper-plated boards provided in this embodiment 2 belong to the same concept. The specific implementation process of the device for detecting corner defects of copper-plated boards provided in this embodiment 2 is detailed in the above-mentioned method embodiment 1, and will not be repeated here.

[0103] Example 3

[0104] See also Figure 6 As shown, one embodiment of the present application also provides a computer device, which can be a computer device such as a desktop computer, a laptop computer, a handheld computer, and a cloud server. The computer device can include, but is not limited to, a processor and a memory. The processor and the memory are connected via a bus or other means.

[0105] The processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, graphics processing units (GPU), embedded neural network processors (NPU) or other dedicated deep learning coprocessors, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0106] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the methods in the above-mentioned embodiments of the present application. The processor executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory, that is, implementing the methods in the above-mentioned method embodiments.

[0107] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0108] One embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program. When the computer program is executed by a processor, the method in the above method embodiment is implemented.

[0109] Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned implementation methods of the present application can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the implementation methods of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0110] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0111] Although the embodiments of the present application are described in conjunction with the accompanying drawings, they cannot be understood as limiting the scope of the patent application. It should be pointed out that for ordinary technicians in this field, other different forms of changes or modifications can be made on the basis of the above description without departing from the concept of the present application. It is not necessary and impossible to list all the embodiments here. The obvious changes or modifications derived from this are still within the scope of protection created by the present application. Therefore, the scope of protection of the patent application shall be based on the attached claims.

Claims

1. A method for detecting corner defects of a copper-plated plate, characterized in that: The method comprises: Acquire an image to be detected, wherein the image to be detected includes a hanger clamping area; Determine whether the material clamping area of ​​the rack in the image to be detected clamps a copper-plated plate; If a copper-plated plate is clamped, a corner defect recognition result corresponding to the copper-plated plate is generated according to the image to be detected.

2. The method for detecting corner defects of copper-plated plates according to claim 1, characterized in that: The step of generating a corner defect recognition result corresponding to the copper-plated plate according to the image to be detected includes: Identify the copper-plated plate in the image to be detected, and generate an actual contour corresponding to the copper-plated plate; Generating a standard outline corresponding to the copper-plated plate according to the actual outline; Determining whether the actual contour completely overlaps with the standard contour; If the actual profile completely coincides with the standard profile, it is determined that the copper-plated plate does not have a corner defect; If the actual contour does not completely coincide with the standard contour, it is determined that the copper-clad plate has a corner defect.

3. The method for detecting corner defects of copper-plated plates according to claim 2, characterized in that: The step of generating a corner defect recognition result corresponding to the copper-plated plate according to the image to be detected further includes: After determining that the copper-plated plate has a corner defect, determining the area where the actual contour and the standard contour do not overlap, and determining the corner position corresponding to each non-overlapping area; The corner positions include upper left, lower left, upper right and lower right.

4. The method for detecting corner defects of copper-plated plates according to claim 3, characterized in that: The step of generating a corner defect recognition result corresponding to the copper-plated plate according to the image to be detected further includes: Based on the standard contour, determining a standard area corresponding to each non-overlapping area; Cut out images from the image to be inspected in sequence according to each standard area to obtain a set of small images of corner defects; Based on the trained corner type recognition model, the corner defect thumbnails are identified in turn, and the corner types corresponding to the defect thumbnails are generated, wherein the corner types include inner fold and outer fold.

5. The method for detecting corner defects of copper-plated plates according to claim 1, characterized in that: The step of generating a corner defect recognition result corresponding to the copper-plated plate according to the image to be detected includes: Based on the trained corner defect recognition model, identify all corner defects in the image to be detected and the corner type corresponding to each corner defect; The corner position corresponding to each corner defect is determined, and the corner type corresponding to each corner defect is combined to generate a corner defect recognition result corresponding to the copper-plated plate.

6. The method for detecting corner defects of copper-plated plates according to claim 5, characterized in that: Determining the angle position corresponding to each angle defect includes: According to the image coordinates corresponding to each folding corner defect, the target folding corner position corresponding to each folding corner defect is determined; The corner positions include upper left, lower left, upper right and lower right, and each corner position is preset with a corresponding coordinate range.

7. The method for detecting corner defects of a copper-plated plate according to any one of claims 1 to 6, characterized in that: Also includes: If the hanger clamping area holds two copper-plated plates, then corner defect recognition results corresponding to the two copper-plated plates are generated one by one according to the image to be detected.

8. A device for detecting corner defects of copper-plated plates, characterized in that: include: An image acquisition module, used for acquiring an image to be detected, wherein the image to be detected includes a hanger clamping area; A board holding judgment module, used for judging whether the material clamping area of ​​the rack in the image to be detected is clamping a copper-plated board; The corner recognition module is used to generate a corner defect recognition result corresponding to the copper-plated plate according to the image to be detected when a copper-plated plate is clamped in the clamping area of ​​the hanger.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor implements the method for detecting corner defects of copper-plated plates as described in any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method for detecting corner defects of a copper-plated plate according to any one of claims 1 to 7 is implemented.

Images