Copper foil surface defect detection method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of copper foil detection, and provides a copper foil surface defect detection method and device, computer equipment and a storage medium, and the method comprises the steps: adjusting the real-time collection speed of a camera according to the real-time movement speed of a to-be-detected copper foil and a preset reference collection speed, and obtaining the upper and lower surface images of the to-be-detected copper foil; acquiring corresponding feature point pairs in the upper and lower surface images; identifying potential defect areas in the upper and lower surface images according to the corresponding feature point pairs; performing surface defect detection on the potential defect area to obtain a hidden defect detection result; performing surface defect detection on the upper and lower surface images to obtain upper and lower surface defect detection results; and generating a copper foil surface defect detection result according to the hidden defect detection result and the upper and lower surface defect detection results. According to the invention, the upper and lower surfaces and hidden defects of the copper foil can be detected at the same time, and the accuracy and comprehensiveness of the detection effect are improved.

Description

Technical Field

[0001] The present application relates to the technical field of copper foil detection, and in particular to a method, device, computer equipment and storage medium for detecting surface defects of copper foil. Background Art

[0002] In the production process of copper foil, surface defects are one of the important indicators to measure its quality and performance. With the rapid development of image processing technology, an automatic copper foil surface defect detection system based on this technology has emerged, which not only reduces the burden of manual detection, but also improves detection efficiency.

[0003] However, most existing copper foil inspection methods based on image processing technology only focus on a single surface image of the copper foil, that is, they either only inspect defects on the upper surface image or only inspect defects on the lower surface image, ignoring the possible correlation information between the upper and lower surfaces of the copper foil. This inspection method limited to a single perspective cannot fully capture all defect features on the copper foil surface, which in turn affects the accuracy and comprehensiveness of the inspection effect. Summary of the invention

[0004] Based on this, a copper foil surface defect detection method, device, computer equipment and storage medium are proposed, aiming to solve the technical problem that the existing technology is based on a single-viewing angle detection method and cannot fully capture all defects on the copper foil surface.

[0005] A first aspect of the present application provides a method for detecting copper foil surface defects, the method comprising:

[0006] The real-time acquisition speed of the first group of linear array CCD cameras and the second group of linear array CCD cameras is adjusted according to the real-time moving speed of the copper foil to be tested and the preset reference acquisition speed;

[0007] Acquire an upper surface image of the copper foil to be tested acquired by the first group of linear array CCD cameras at the real-time acquisition speed, and acquire a lower surface image acquired by the second group of linear array CCD cameras at the real-time acquisition speed;

[0008] Acquire corresponding feature point pairs in the upper surface image and the lower surface image;

[0009] Identify potential defect areas in the upper surface image and the lower surface image according to the corresponding feature point pairs;

[0010] Performing surface defect detection on the potential defect area to obtain hidden defect detection results;

[0011] Performing surface defect detection on the upper surface image to obtain an upper surface defect detection result, and performing surface defect detection on the lower surface image to obtain a lower surface defect detection result;

[0012] A copper foil surface defect detection result is generated according to the hidden defect detection result, the upper surface defect detection result and the lower surface defect detection result.

[0013] Optionally, adjusting the real-time acquisition speeds of the first group of linear array CCD cameras and the second group of linear array CCD cameras according to the real-time moving speed of the copper foil to be tested and a preset reference acquisition speed includes:

[0014] The moving speed ratio is calculated according to the real-time moving speed of the copper foil to be tested and the preset reference moving speed;

[0015] Determining the quality grade according to the model parameters of the copper foil to be tested;

[0016] Obtaining the micro-texture change rate of the copper foil to be tested;

[0017] The real-time acquisition speeds of the first group of linear array CCD cameras and the second group of linear array CCD cameras are adjusted according to the moving speed ratio, the quality level, the micro texture change rate and the preset reference acquisition speed.

[0018] Optionally, acquiring corresponding feature point pairs in the upper surface image and the lower surface image includes:

[0019] Performing feature point detection on the upper surface image to obtain a first key feature point;

[0020] Performing feature point detection on the lower surface image to obtain second key feature points;

[0021] Feature matching is performed on the first key feature point and the second key feature point to obtain corresponding feature point pairs.

[0022] Optionally, the identifying potential defect areas in the upper surface image and the lower surface image according to the corresponding feature point pairs includes:

[0023] Calculating a displacement vector between the corresponding feature point pairs;

[0024] Determining whether there is a displacement between the upper surface image and the lower surface image according to the displacement vector;

[0025] When it is determined that there is displacement, the area corresponding to the displacement vector in the upper surface image and the lower surface image is identified as a potential defect area.

[0026] Optionally, performing surface defect detection on the upper surface image to obtain an upper surface defect detection result, and performing surface defect detection on the lower surface image to obtain a lower surface defect detection result includes:

[0027] Performing differential processing on the upper surface image and a reference upper surface image to obtain a first differential image;

[0028] Performing surface defect detection based on the upper surface image to obtain a first upper surface defect detection result;

[0029] Performing surface defect detection based on the first differential image to obtain a second upper surface defect detection result;

[0030] Correcting the first upper surface defect detection result according to the second upper surface defect detection result to obtain the upper surface defect detection result;

[0031] performing a difference process on the lower surface image and a reference lower surface image to obtain a second difference image;

[0032] Performing surface defect detection based on the lower surface image to obtain a first lower surface defect detection result;

[0033] Performing surface defect detection based on the second differential image to obtain a second lower surface defect detection result;

[0034] The first lower surface defect detection result is corrected according to the second lower surface defect detection result to obtain the lower surface defect detection result.

[0035] Optionally, the method further includes:

[0036] Determine the defect location according to the copper foil surface defect detection result;

[0037] The defect position is sent to a labeling machine, so that the labeling machine labels the area corresponding to the defect position on the copper foil to be tested.

[0038] Optionally, the first group of linear array CCD cameras is used to capture the upper surface of the copper foil to be tested to obtain the upper surface image under the lighting environment provided by the upper surface detection light source and the high-brightness backlight source; the second group of linear array CCD cameras is used to capture the lower surface of the copper foil to be tested to obtain the lower surface image under the lighting environment provided by the lower surface detection light source.

[0039] A second aspect of the present application provides a copper foil surface defect detection device, the device comprising:

[0040] A camera adjustment module, used for adjusting the real-time acquisition speed of the first group of linear array CCD cameras and the second group of linear array CCD cameras according to the real-time moving speed of the copper foil to be tested and a preset reference acquisition speed;

[0041] An image acquisition module, used to acquire an upper surface image of the copper foil to be tested acquired by the first group of linear array CCD cameras at the real-time acquisition speed, and to acquire a lower surface image acquired by the second group of linear array CCD cameras at the real-time acquisition speed;

[0042] A feature acquisition module, used to acquire corresponding feature point pairs in the upper surface image and the lower surface image;

[0043] A region recognition module, used for identifying potential defect regions in the upper surface image and the lower surface image according to the corresponding feature point pairs;

[0044] A first detection module is used to perform surface defect detection on the potential defect area to obtain a hidden defect detection result;

[0045] A second detection module is used to perform surface defect detection on the upper surface image to obtain an upper surface defect detection result, and to perform surface defect detection on the lower surface image to obtain a lower surface defect detection result;

[0046] The result generating module is used to generate the copper foil surface defect detection result according to the hidden defect detection result, the upper surface defect detection result and the lower surface defect detection result.

[0047] A third aspect of the present application provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the copper foil surface defect detection method when executing the computer program.

[0048] A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the copper foil surface defect detection method are implemented.

[0049] The embodiment of the present application can dynamically adjust the real-time acquisition speed of the first group and the second group of linear array CCD cameras according to the real-time moving speed of the copper foil to be tested and the preset reference acquisition speed. This dynamic adjustment mechanism ensures that the camera can always capture images at the optimal frame rate, avoids image blur or frame loss, thereby improving the acquisition quality of the copper foil surface image, and can avoid unnecessary image acquisition and storage, reducing the waste of computing resources and storage space. Two groups of linear array CCD cameras are used to respectively collect the upper surface and lower surface images of the copper foil to ensure that the two are synchronized in time, so that the detection process can cover the entire surface of the copper foil, and improve the comprehensiveness of the detection. The corresponding feature point pairs in the upper surface image and the lower surface image are obtained through the image processing algorithm. The feature point pairs can accurately capture the slight changes in the upper and lower surfaces of the copper foil, thereby more accurately identifying the potential defect area. Surface defect detection is performed on the potential defect area, the upper surface image and the lower surface image respectively, and the hidden defect detection results, the upper surface defect detection results and the lower surface defect detection results are obtained. This multi-dimensional detection can more comprehensively discover various defect types on the copper foil surface, and improve the accuracy and reliability of the detection. Finally, based on the hidden defect detection results, upper surface defect detection results and lower surface defect detection results, the copper foil surface defect detection results are comprehensively generated. The comprehensive detection results can fully reflect the quality status of the copper foil surface. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 It is a schematic flow chart of the copper foil surface defect detection method provided in the embodiment of the present application.

[0052] Figure 2 It is a schematic diagram of the interface for copper foil surface defect detection provided in an embodiment of the present application.

[0053] Figure 3 It is a functional module diagram of the copper foil surface defect detection device provided in an embodiment of the present application.

[0054] Figure 4 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] 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 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.

[0056] Figure 1 A schematic flow chart of a copper foil surface defect detection method provided in an embodiment of the present application, the copper foil surface defect detection method comprises the following steps.

[0057] S11, adjusting the real-time acquisition speed of the first group of linear array CCD cameras and the second group of linear array CCD cameras according to the real-time moving speed of the copper foil to be tested and the preset reference acquisition speed.

[0058] The copper foil to be tested refers to the copper foil material that needs to be tested for surface defects. During the production process of copper foil, there may be defects or contamination on the upper and lower surfaces of the copper foil, so it is necessary to perform defect detection on the upper and lower surface images of the copper foil at the same time. The first group of linear array CCD cameras is used to acquire the upper surface image of the copper foil to be tested, and the second group of linear array CCD cameras is used to acquire the lower surface image of the copper foil to be tested.

[0059] In an optional embodiment, the first group of linear array CCD cameras is used to capture the upper surface of the copper foil to be tested to obtain the upper surface image under the lighting environment provided by the upper surface detection light source and the high-brightness backlight source; the second group of linear array CCD cameras is used to capture the lower surface of the copper foil to be tested to obtain the lower surface image under the lighting environment provided by the lower surface detection light source.

[0060] During the production process of copper foil, the copper foil will move through the detection system at a certain speed. This speed may be variable or constant, and the moving speed of the copper foil (real-time moving speed) needs to be obtained in real time. A speed sensor or encoder can be installed at a suitable position on the copper foil moving path to monitor the moving speed of the copper foil on the production line in real time. The speed sensor can be a photoelectric sensor, laser sensor, etc.

[0061] The preset reference acquisition speed is set according to the optimal performance or detection requirements of the system design. It is the default acquisition speed of the system when the actual movement speed difference of the copper foil is not considered.

[0062] The real-time acquisition speed of a linear array CCD camera refers to the number of image frames (FPS, Frames Per Second) that a linear array CCD camera can acquire per second. The relationship between the acquisition speed of the camera and the moving speed of the copper foil will directly affect the quality of the surface image and the integrity of the information. When the acquisition speed of the camera is too slow and the moving speed of the copper foil is too fast, the shutter of the camera is open for too long, and the copper foil has moved a certain distance during this time, resulting in image tailing or blurring. In addition, due to the slow acquisition speed, the camera may not be able to capture all the details of the copper foil moving process, resulting in information loss. When the acquisition speed of the camera is too fast and the moving speed of the copper foil is too slow, the camera captures a large number of images in a short time, but many of the images may be similar or repeated, resulting in a large amount of data storage space and processing resources being wasted. Therefore, in order to obtain high-quality images and complete information, and save storage space and processing resources, it is necessary to adjust the real-time acquisition speed of the first group of linear array CCD cameras and the second group of linear array CCD cameras according to the real-time moving speed of the copper foil to be tested and the preset reference acquisition speed.

[0063] In an optional embodiment, adjusting the real-time acquisition speed of the first group of linear array CCD cameras and the second group of linear array CCD cameras according to the real-time moving speed of the copper foil to be tested and the preset reference acquisition speed includes:

[0064] The moving speed ratio is calculated according to the real-time moving speed of the copper foil to be tested and the preset reference moving speed;

[0065] Determining the quality grade according to the model parameters of the copper foil to be tested;

[0066] Obtaining the micro-texture change rate of the copper foil to be tested;

[0067] The real-time acquisition speeds of the first group of linear array CCD cameras and the second group of linear array CCD cameras are adjusted according to the moving speed ratio, the quality level, the micro texture change rate and the preset reference acquisition speed.

[0068] When the production line is running stably and the copper foil quality is stable, use a speed sensor to measure and record the average moving speed of the copper foil over a period of time, and use this speed as the benchmark moving speed. The benchmark moving speed represents the standard or expected moving speed on the production line. The preset benchmark acquisition speed is the default acquisition speed of the system when factors such as the actual moving speed, quality grade, and micro-texture change rate of the copper foil are not considered. According to the performance parameters of the linear array CCD camera (such as maximum frame rate, resolution, etc.), determine a matching benchmark acquisition speed (F_benchmark). The benchmark acquisition speed matches the performance of the linear array CCD camera to ensure that high-quality images can be captured at the benchmark moving speed.

[0069] During the operation of the production line, the real-time moving speed of the copper foil is monitored by a speed sensor or encoder, and the real-time moving speed is transmitted to the camera control system. The control system calculates the ratio between the real-time moving speed of the copper foil and the reference moving speed. The ratio reflects the difference between the actual moving speed of the copper foil and the expected moving speed (reference moving speed) when the system is designed. If the ratio is greater than 1, it means that the real-time moving speed is faster than the reference moving speed; if the ratio is less than 1, it means that the real-time moving speed is slower than the reference moving speed.

[0070] According to the model parameters of the copper foil to be tested, the corresponding database can be searched to determine the quality grade and micro-texture change rate of the copper foil to be tested.

[0071] Quality grade refers to the grade of the same type of goods determined by the degree to which they meet the commodity quality standards. Copper foils of different quality grades differ in physical and chemical properties, such as hardness, strength, corrosion resistance, conductivity, etc. These differences may cause the copper foil to exhibit different reflectivity, transmittance or scattering characteristics during image acquisition, thereby affecting the clarity and contrast of image acquisition. Copper foils of high quality grades usually have a smoother surface, reducing image distortion or noise caused by surface unevenness. Conversely, copper foils of low quality grades may cause blur or deformation during image acquisition due to surface unevenness.

[0072] The microtexture change rate is an indicator that describes how fast the microtexture of the copper foil surface changes. The surface texture of copper foil with a high microtexture change rate is more complex and changeable, which may make it difficult to accurately capture and identify these texture features during image acquisition. Copper foil with a high microtexture change rate may generate more noise during image acquisition, such as surface defects, scratches, pollution, etc. These noises will reduce the clarity and contrast of the image, making it difficult for the image to accurately reflect the actual state of the copper foil.

[0073] Therefore, different types of copper foils have different quality grades and micro-texture change rates, which will have a significant impact on the quality of image acquisition. Therefore, when acquiring images of the upper and lower surfaces of the copper foil, it is necessary to adjust the real-time acquisition speeds of the first group of linear array CCD cameras and the second group of linear array CCD cameras simultaneously according to the moving speed ratio, quality grade, micro-texture change rate and preset reference acquisition speed.

[0074] In an optional implementation, the real-time acquisition speed may be calculated using the following formula:

[0075] Vcai = Vbase × R × P × (1 + γ·M);

[0076] Among them, V is the real-time acquisition speed of the linear array CCD camera, V is the preset benchmark acquisition speed, R is the mobile speed ratio, P is the quality level, M is the micro-texture change rate, and γ is the influence coefficient of the micro-texture change rate, which is determined based on experience. The influence coefficient reflects the sensitivity of the micro-texture change rate to the adjustment of the acquisition speed.

[0077] After calculating the real-time acquisition speed of the camera (the first group of linear array CCD cameras and the second group of linear array CCD cameras), the real-time acquisition speed can be changed by adjusting the internal parameters of the camera (such as shutter speed, frame rate, etc.). After adjusting the real-time acquisition speed of the camera, you can first collect images for a period of time and determine whether the images are clear, stable, and without missing any key information. If you find that the image quality is poor or information is missing, you need to adjust the real-time acquisition speed again.

[0078] The above optional implementation method can ensure that the camera's acquisition speed matches the copper foil's movement speed by monitoring the moving speed ratio between the real-time moving speed and the reference moving speed, and adjusting the real-time acquisition speed according to this ratio, thereby improving acquisition efficiency and avoiding image overlap or loss. Adjusting the camera's acquisition speed according to the copper foil's quality grade and micro-texture change rate can ensure that high-quality images can be obtained on copper foils of different quality grades and texture complexity. For copper foils of high quality grades, clearer images can be acquired; for copper foils with high micro-texture change rates, it can ensure that the image can capture more details. This optional implementation method enhances the adaptability of the image acquisition system to copper foils of different models, different quality grades, and different micro-texture change rates. By dynamically adjusting the acquisition speed, the system can automatically adapt to different copper foil characteristics without manual intervention, thereby improving the automation level of the entire image acquisition process, helping to reduce production costs, improve production efficiency, and reduce the possibility of human errors.

[0079] S12, acquiring an upper surface image of the copper foil to be tested acquired by the first group of linear array CCD cameras at the real-time acquisition speed, and acquiring a lower surface image acquired by the second group of linear array CCD cameras at the real-time acquisition speed.

[0080] In large-scale, high-efficiency production line inspection scenarios, a linear array CCD (Charge-Coupled Device) camera can be used to quickly capture images of continuously moving objects. In the embodiment of the present application, a first group of linear array CCD cameras are used to capture the upper surface of the copper foil to be tested to obtain an upper surface image. At the same time, a second group of linear array CCD cameras are used to capture the lower surface of the copper foil to be tested to obtain a lower surface image.

[0081] S13, obtaining corresponding feature point pairs in the upper surface image and the lower surface image.

[0082] From the physical properties of copper foil, its upper and lower surfaces are not completely independent. As a whole, the internal stress and microstructure of copper foil may affect the morphology of the upper and lower surfaces. For example, copper foil may be subjected to forces such as tension, compression or bending during the production process, which may cause a certain correlation between the upper and lower surfaces in morphology. In addition, the microstructure of copper foil (such as grain size, arrangement, etc.) may also affect the image features of the upper and lower surfaces. Therefore, it is necessary to obtain the corresponding feature point pairs in the upper surface image and the lower surface image.

[0083] Feature points are points with unique properties in an image, such as corner points, edge points, or areas with rich textures. A feature point detection algorithm can be used to detect feature points in the upper surface image and feature points in the lower surface image to obtain feature point pairs.

[0084] Among them, the feature point detection algorithm may include: Harris corner point detection, SIFT (Scale-Invariant Feature Transform), SURF (Speeded Up Robust Features), etc.

[0085] In an optional implementation, the acquiring corresponding feature point pairs in the upper surface image and the lower surface image includes:

[0086] Performing feature point detection on the upper surface image to obtain a first key feature point;

[0087] Performing feature point detection on the lower surface image to obtain second key feature points;

[0088] Feature matching is performed on the first key feature point and the second key feature point to obtain corresponding feature point pairs.

[0089] A feature point detection algorithm is used to detect feature points in the upper surface image, such as edges, corners, texture features, etc., to obtain a plurality of first key feature points. The same feature point detection algorithm is used to detect feature points corresponding to the upper surface image in the lower surface image to obtain a plurality of second key feature points.

[0090] The first key feature points are matched with the second key feature points by a feature matching algorithm. The matching process is to calculate the similarity between the feature descriptors (such as Euclidean distance, Hamming distance, etc.), and select the point pair with the highest similarity as the matching pair. The result is a set of corresponding feature point pairs, which correspond to the same physical position or feature in the upper surface image and the lower surface image.

[0091] S14, identifying potential defect areas in the upper surface image and the lower surface image according to the corresponding feature point pairs.

[0092] In an optional implementation, the identifying potential defect areas in the upper surface image and the lower surface image according to the corresponding feature point pairs includes:

[0093] Calculating a displacement vector between the corresponding feature point pairs;

[0094] Determining whether there is a displacement between the upper surface image and the lower surface image according to the displacement vector;

[0095] When it is determined that there is displacement, the area corresponding to the displacement vector in the upper surface image and the lower surface image is identified as a potential defect area.

[0096] For each pair of matched feature points, their displacement vectors between the upper surface image and the lower surface image are calculated. The displacement vector represents the position change from the feature point in the upper surface image to the corresponding feature point in the lower surface image. The calculated displacement vectors are statistically analyzed, including the calculation of the mean, variance, maximum and minimum values, and the directional distribution of the vectors. These statistical information helps to reveal the overall deformation or local defects that may exist between the upper and lower surfaces of the copper foil. Based on the statistical characteristics of the displacement vectors, one or more thresholds are set to determine whether a certain feature point pair indicates a potential defect area. For example, a maximum allowable value of a displacement vector can be set, and feature point pairs exceeding this value may indicate a defect. This is because if the copper foil does not deform or move abnormally during transmission, the corresponding feature points on its upper and lower surfaces should theoretically maintain a relatively fixed positional relationship. The abnormal increase in the displacement vector may mean that the copper foil has defects such as bending, twisting, or internal stress, which may not be obvious when observing the upper or lower surface alone, but can be revealed by analyzing the correlation between the upper and lower surfaces.

[0097] For feature point pairs indicating potential defects, their positions in the upper and lower surface images are marked. These positions may form one or more continuous regions, which are preliminarily considered as potential defect regions. Specifically, for feature points with displacement, an area is marked as a potential defect region in the upper and lower surface images respectively based on the size and direction of the displacement vector, with the feature point as the center. The potential defect region refers to the actual area that should theoretically appear in the lower surface image after the feature point in the upper surface image is displaced, but the position is offset.

[0098] S15, performing surface defect detection on the potential defect area to obtain a hidden defect detection result.

[0099] Since the marked potential defect areas are determined based on the displacement of feature points, the potential defect areas may not completely correspond to the actual defect location or shape. Therefore, more sophisticated defect detection algorithms are needed to verify these potential defect areas and determine whether there are real defects and the specific type and severity of the defects.

[0100] A hidden defect detection model can be pre-trained based on machine learning, and the potential defect area can be used as the input of the hidden defect detection model. The hidden defect detection model is used to perform detection and output the hidden defect detection result.

[0101] S16, performing surface defect detection on the upper surface image to obtain an upper surface defect detection result, and performing surface defect detection on the lower surface image to obtain a lower surface defect detection result.

[0102] Hidden defect inspection results provide information about potential defect areas, but may not capture defects in non-potential defect areas. Complete surface defect inspection of both the top and bottom surfaces ensures that all possible defects are detected, providing a more comprehensive quality assessment.

[0103] In an optional embodiment, performing surface defect detection on the upper surface image to obtain an upper surface defect detection result, and performing surface defect detection on the lower surface image to obtain a lower surface defect detection result includes:

[0104] Performing differential processing on the upper surface image and a reference upper surface image to obtain a first differential image;

[0105] Performing surface defect detection based on the upper surface image to obtain a first upper surface defect detection result;

[0106] Performing surface defect detection based on the first differential image to obtain a second upper surface defect detection result;

[0107] Correcting the first upper surface defect detection result according to the second upper surface defect detection result to obtain the upper surface defect detection result;

[0108] performing a difference process on the lower surface image and a reference lower surface image to obtain a second difference image;

[0109] Performing surface defect detection based on the lower surface image to obtain a first lower surface defect detection result;

[0110] Performing surface defect detection based on the second differential image to obtain a second lower surface defect detection result;

[0111] The first lower surface defect detection result is corrected according to the second lower surface defect detection result to obtain the lower surface defect detection result.

[0112] The reference upper surface image and the reference lower surface image are images of a known copper foil surface without defects or with a standard appearance. The reference upper surface image and the reference lower surface image are used as a reference for comparison to identify any deviations or defects on the upper and lower surfaces of the copper foil to be tested. Copper foil surface defects refer to any physical features on the upper and lower surfaces of the copper foil that do not meet the expected standards or specifications, such as scratches, dents, cracks, stains, oxidation, etc. These defects may affect the performance, reliability and service life of the copper foil.

[0113] By comparing the top / bottom surface images of the copper foil to be tested with known reference top / bottom surface images, any deviations from the standard or expectations, which often indicate potential defects, can be more easily identified. Using the reference top / bottom surface images as a reference can reduce false positives and negatives caused by factors such as lighting changes, texture differences, or imaging equipment errors. The reference top / bottom surface images provide a stable comparison basis to help distinguish true defects from false defects.

[0114] Since differential processing can highlight the difference between the two images, it helps to identify defects on the surface of the copper foil. In addition, differential processing has a certain robustness to interference factors such as lighting changes and shadows. In this embodiment, a new image is obtained by calculating the pixel difference between the upper / lower surface image and the reference upper / lower surface image, namely the differential image. The grayscale value or color value of the corresponding pixel in the upper / lower surface image and the reference upper / lower surface image can be subtracted to obtain a differential image. The value of each pixel in the differential image represents the degree of difference between the two images at that position. The differential image can highlight the change area between the two images, which may correspond to defects, movement or changes on the surface of the object.

[0115] The difference image may contain a lot of noise and small changes that may not correspond to actual defects. In order to filter out these noises, threshold processing can be applied to the difference image. That is, the pixel values ​​in the difference image are divided into two categories: pixels above the threshold are regarded as defective areas, while pixels below the threshold are regarded as background or noise.

[0116] Since the upper / lower surface image and the reference upper / lower surface image may have differences in position or angle when they are taken, it is necessary to align the upper / lower surface image and the reference upper / lower surface image to ensure that the two are consistent in space. The alignment of the upper surface image and the reference upper surface image can be achieved by feature matching, affine transformation or other image registration algorithms.

[0117] In order to improve the effect of image alignment, the upper / lower surface image may be first denoised, and then the denoised upper / lower surface image and the reference upper / lower surface image may be registered.

[0118] Defect-related features, such as texture features, shape features, color features, etc., can be first extracted from the upper / lower surface images and the reference upper / lower surface images. Surface defect detection is performed based on the extracted features using a defect detection model. Surface defect detection can also be performed based on the upper / lower surface images and the reference upper / lower surface images using a defect detection model. The defect detection model is a pre-trained machine learning model that can identify and locate defects on the surface of the copper foil. The defect-related features extracted from the upper / lower surface images and the reference upper / lower surface images, or the upper / lower surface images and the reference upper / lower surface images are directly used as inputs to the defect detection model, and the defect detection results (first upper surface defect detection results / second upper surface defect detection results) are output through the defect detection model. The surface defect detection results include all detected defect information, such as information such as the location, size, shape, type, and one or more images or visual marks representing the defects. The defect information can be presented using numbers, images, or a combination of both.

[0119] After obtaining the first upper surface defect detection result and the second upper surface defect detection result, the second upper surface defect detection result can be used to correct the error or uncertainty in the first upper surface defect detection result. For example, the defect position, size and type in the first upper surface defect detection result and the second upper surface defect detection result are matched, merged or screened to generate the final upper surface defect detection result.

[0120] Similarly, after obtaining the first lower surface defect detection result and the second lower surface defect detection result, the second lower surface defect detection result can be used to correct the errors or uncertainties in the first lower surface defect detection result. For example, the defect positions, sizes and types in the first lower surface defect detection result and the second lower surface defect detection result are matched, merged or screened to generate the final lower surface defect detection result.

[0121] It is understandable that before the differential image is input into the defect detection model, denoising, contrast enhancement, etc. may be performed to enhance the quality of the differential image and improve the accuracy of the detection result.

[0122] It is understandable that in order to further improve the accuracy of the detection results, the output of the defect detection model can be post-processed, such as removing isolated points, filling holes, etc.

[0123] It is understandable that the defect detection model used for defect detection on the lower surface image and the defect detection model used for defect detection based on the lower surface image can be the same model or different models, and the present application does not impose any limitation thereto.

[0124] In the above optional implementation, direct defect detection on the upper / lower surface image may be affected by various factors, such as illumination changes, image noise, surface texture differences, etc., resulting in false alarms (misjudging non-defective areas as defects) or missed alarms (failure to detect real defects). The reference upper / lower surface image represents a defect-free or standard state of the upper / lower surface of the copper foil. Through differential processing, the influence of the above factors on the upper / lower surface detection results can be eliminated or reduced, because the differential image mainly reflects the difference between the upper / lower surface image and the reference upper / lower surface image. Using the detection results of the first differential image to correct the detection results of the upper surface image, and using the detection results of the second differential image to correct the detection results of the lower surface image, can further reduce false alarms and missed alarms and improve the accuracy of detection. In addition, differential processing can highlight the inconsistent areas between the upper / lower surface image and the reference upper / lower surface image, which are more likely to be defects. By focusing on these inconsistent areas, attention to non-critical areas in the image can be reduced, thereby reducing the interference of external factors on the detection results and enhancing the robustness of detection.

[0125] S17, generating a copper foil surface defect detection result according to the hidden defect detection result, the upper surface defect detection result and the lower surface defect detection result.

[0126] It can be considered that the defects in the hidden defect detection results, the upper surface defect detection results, and the lower surface defect detection results are all real. The information on the defect characteristics (such as position, size, shape, etc.) in the hidden defect detection results, the upper surface defect detection results, and the lower surface defect detection results are merged to generate a more comprehensive defect description, which helps to more accurately determine the nature and severity of the defects. The result of the fusion of the three defect detection results is used as the final copper foil surface defect detection result.

[0127] In an optional embodiment, the method further comprises:

[0128] Determine the defect location according to the copper foil surface defect detection result;

[0129] The defect position is sent to a labeling machine, so that the labeling machine labels the area corresponding to the defect position on the copper foil to be tested.

[0130] After the system detects a defect, it will record the location of the defect in the image and send the defect location to the labeling machine.

[0131] After receiving the defect location, the labeling machine labels the area corresponding to the defect location on the copper foil according to the defect location. The labeling machine usually has a high-precision positioning system and a reliable actuator to ensure that the label can be accurately attached to the defect location.

[0132] In some optional embodiments, before labeling, the system can select the appropriate label type (such as color, shape, size, etc.) according to the type and severity of the defect, and print or prepare it, thereby helping to quickly identify and handle different types of defects during the production process.

[0133] After labeling is completed, production personnel can quickly locate the defective copper foil area based on the label information and take corresponding treatment measures (such as rework, scrapping, etc.).

[0134] The above optional implementation method, by introducing precise marking of defect positions during the copper foil surface defect detection process, not only improves the automation level of the detection process, but also helps to quickly identify and process defective copper foil in actual production.

[0135] In an optional implementation, the copper foil surface defect detection results can be classified and counted. The classification and statistics results can be obtained by Figure 2 The defect detection display interface shown is visually displayed. The defect detection display interface may include basic information of the copper foil, detection means, detection time, detected defect type, characteristics, location, priority and other information.

[0136] The number of defects on the upper surface, the number of defects on the lower surface, and the total number of defects can be counted. The average size of defects can be calculated, and the changing trend of defects can be analyzed. The defect distribution map can also be displayed to help understand the distribution of various defects on the copper foil surface and their impact on the quality of the copper foil.

[0137] A set of standardized report templates can be designed in advance, and copper foil quality inspection reports can be generated based on the standardized report templates. The template includes basic report information (such as report number, inspection date, inspection personnel, etc.), inspection results (such as the number and distribution of various defects, etc.), data analysis results (such as the average size of defects, change trends, etc.) and recommended quality control measures.

[0138] The above optional implementation method, by classifying and counting the copper foil surface defect detection results and generating a copper foil quality inspection report, makes the inspection results clearer and more intuitive, so that enterprise managers and production personnel can have a more comprehensive understanding of the quality status of the copper foil and thus take more effective quality control measures.

[0139] The copper foil surface defect detection method provided by the embodiment of the present application can dynamically adjust the real-time acquisition speed of the first group and the second group of linear array CCD cameras according to the real-time moving speed of the copper foil to be tested and the preset reference acquisition speed. This dynamic adjustment mechanism ensures that the camera can always capture images at the optimal frame rate, avoids image blur or frame loss, thereby improving the acquisition quality of the copper foil surface image, and can avoid unnecessary image acquisition and storage, reducing the waste of computing resources and storage space. Two groups of linear array CCD cameras are used to respectively collect the upper surface and lower surface images of the copper foil to ensure that the two are synchronized in time, so that the detection process can cover the entire surface of the copper foil, thereby improving the comprehensiveness of the detection. The corresponding feature point pairs in the upper surface image and the lower surface image are obtained by the image processing algorithm. The feature point pairs can accurately capture the slight changes in the upper and lower surfaces of the copper foil, thereby more accurately identifying the potential defect area. Surface defect detection is performed on the potential defect area, the upper surface image and the lower surface image respectively, and the hidden defect detection results, the upper surface defect detection results and the lower surface defect detection results are obtained. This multi-dimensional detection can more comprehensively discover various defect types on the copper foil surface, and improve the accuracy and reliability of the detection. Finally, based on the hidden defect detection results, upper surface defect detection results and lower surface defect detection results, the copper foil surface defect detection results are comprehensively generated. The comprehensive detection results can fully reflect the quality status of the copper foil surface.

[0140] Figure 3 It is a functional module diagram of the copper foil surface defect detection device provided in an embodiment of the present application.

[0141] In some embodiments, the copper foil surface defect detection device 30 may include a plurality of functional modules composed of program code segments. The program code of each program segment in the copper foil surface defect detection device 30 may be stored in a memory of a computer device and executed by at least one processor to execute (see Figure 1 Description) The function of copper foil surface defect detection.

[0142] In this embodiment, the copper foil surface defect detection device 30 can be divided into multiple functional modules according to the functions it performs. The functional modules may include: a camera adjustment module 301, an image acquisition module 302, a feature acquisition module 303, a region recognition module 304, a first detection module 305, a second detection module 306, a result generation module 307 and a copper foil labeling module 308. The module referred to in this application refers to a series of computer-readable instruction segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0143] The camera adjustment module 301 is used to adjust the real-time acquisition speed of the first group of linear array CCD cameras and the second group of linear array CCD cameras according to the real-time moving speed of the copper foil to be tested and the preset reference acquisition speed;

[0144] The image acquisition module 302 is used to acquire the upper surface image of the copper foil to be tested acquired by the first group of linear array CCD cameras at the real-time acquisition speed, and to acquire the lower surface image acquired by the second group of linear array CCD cameras at the real-time acquisition speed;

[0145] The feature acquisition module 303 is used to acquire corresponding feature point pairs in the upper surface image and the lower surface image;

[0146] The region identification module 304 is used to identify potential defect regions in the upper surface image and the lower surface image according to the corresponding feature point pairs;

[0147] The first detection module 305 is used to perform surface defect detection on the potential defect area to obtain a hidden defect detection result;

[0148] The second detection module 306 is used to perform surface defect detection on the upper surface image to obtain an upper surface defect detection result, and to perform surface defect detection on the lower surface image to obtain a lower surface defect detection result;

[0149] The result generating module 307 is used to generate a copper foil surface defect detection result according to the hidden defect detection result, the upper surface defect detection result and the lower surface defect detection result.

[0150] The copper foil labeling module 308 is used to determine the defect position according to the copper foil surface defect detection result; send the defect position to the labeling machine, so that the labeling machine labels the area corresponding to the defect position on the copper foil to be tested.

[0151] The copper foil surface defect detection device provided by the embodiment of the present application can dynamically adjust the real-time acquisition speed of the first group and the second group of linear array CCD cameras according to the real-time moving speed of the copper foil to be tested and the preset reference acquisition speed. This dynamic adjustment mechanism ensures that the camera can always capture images at the optimal frame rate, avoids image blur or frame loss, thereby improving the acquisition quality of the copper foil surface image, and can avoid unnecessary image acquisition and storage, reducing the waste of computing resources and storage space. Two groups of linear array CCD cameras are used to respectively collect the upper surface and lower surface images of the copper foil to ensure that the two are synchronized in time, so that the detection process can cover the entire surface of the copper foil, thereby improving the comprehensiveness of the detection. The corresponding feature point pairs in the upper surface image and the lower surface image are obtained by the image processing algorithm. The feature point pairs can accurately capture the slight changes in the upper and lower surfaces of the copper foil, thereby more accurately identifying the potential defect area. The potential defect area, the upper surface image and the lower surface image are respectively subjected to surface defect detection to obtain hidden defect detection results, upper surface defect detection results and lower surface defect detection results. This multi-dimensional detection can more comprehensively discover various defect types on the copper foil surface, thereby improving the accuracy and reliability of the detection. Finally, based on the hidden defect detection results, upper surface defect detection results and lower surface defect detection results, the copper foil surface defect detection results are comprehensively generated. The comprehensive detection results can fully reflect the quality status of the copper foil surface.

[0152] It should be understood that the various variations and specific embodiments of the copper foil surface defect detection method provided in the above embodiment are also applicable to the copper foil surface defect detection device in this embodiment. Through the detailed description of the aforementioned copper foil surface defect detection method, those skilled in the art can clearly understand the implementation process of the copper foil surface defect detection device in this embodiment. For the sake of brevity of the specification, it will not be described in detail here.

[0153] The embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, all or part of the steps of the copper foil surface defect detection method are implemented.

[0154] See also Figure 4 FIG. 4 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. In a preferred embodiment of the present application, the computer device 4 includes a memory 401 , at least one processor 402 , and at least one communication bus 403 .

[0155] Those skilled in the art should understand that Figure 4 The structure of the computer device shown does not constitute a limitation of the embodiments of the present application. The computer device 4 may also include more or less other hardware or software than shown in the figure, or a different arrangement of components.

[0156] In some embodiments, the computer device 4 is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits, programmable gate arrays, digital processors, and embedded devices. The computer device 4 may also include client devices, which include but are not limited to any electronic product that can interact with the client through a keyboard, mouse, remote control, touchpad, or voice control device, such as a personal computer, tablet computer, smart phone, digital camera, etc.

[0157] It should be noted that the computer device 4 is only an example, and other existing or future electronic products that are suitable for the present application should also be included in the protection scope of the present application and included here by reference.

[0158] In some embodiments, a computer program is stored in the memory 401, and when the computer program is executed by the at least one processor 402, all or part of the steps in the copper foil surface defect detection method as described above are implemented. The memory 401 includes a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc memory, magnetic disk memory, magnetic tape memory, or any other computer-readable medium that can be used to carry or store data. Further, the computer-readable storage medium may mainly 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, and the like.

[0159] In some embodiments, the at least one processor 402 is the control core (CrolUnit) of the computer device 4, and uses various interfaces and lines to connect the various components of the entire computer device 4, and executes various functions and processes data of the computer device 4 by running or executing the program or module stored in the memory 401, and calling the data stored in the memory 401. For example, when the at least one processor 402 executes the computer program stored in the memory, it implements all or part of the steps of the copper foil surface defect detection method described in the embodiment of the present application; or implements all or part of the functions of the copper foil surface defect detection device. The at least one processor 402 can be composed of an integrated circuit, for example, it can be composed of a single packaged integrated circuit, or it can be composed of multiple integrated circuits with the same function or different functions, including one or more central processing units (CPU), microprocessors, digital processing chips, graphics processors, and various control chips.

[0160] In some embodiments, the at least one communication bus 403 is configured to realize connection and communication between the memory 401 and the at least one processor 402, etc. Although not shown, the computer device 4 may also include a power supply (such as a battery) for powering each component. Preferably, the power supply may be logically connected to the at least one processor 402 through a power management device, so as to realize functions such as management of charging, discharging, and power consumption management through the power management device. The power supply may also include any components such as one or more DC or AC power supplies, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The computer device 4 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0161] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor to execute part of the method described in each embodiment of the present application.

[0162] In the several embodiments provided in this 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 illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0163] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Claims

1. A method for detecting surface defects of copper foil, characterized in that: The method comprises: The real-time acquisition speed of the first group of linear array CCD cameras and the second group of linear array CCD cameras is adjusted according to the real-time moving speed of the copper foil to be tested and the preset reference acquisition speed; Acquire an upper surface image of the copper foil to be tested acquired by the first group of linear array CCD cameras at the real-time acquisition speed, and acquire a lower surface image acquired by the second group of linear array CCD cameras at the real-time acquisition speed; Acquire corresponding feature point pairs in the upper surface image and the lower surface image; Identify potential defect areas in the upper surface image and the lower surface image according to the corresponding feature point pairs; Performing surface defect detection on the potential defect area to obtain hidden defect detection results; Performing surface defect detection on the upper surface image to obtain an upper surface defect detection result, and performing surface defect detection on the lower surface image to obtain a lower surface defect detection result; A copper foil surface defect detection result is generated according to the hidden defect detection result, the upper surface defect detection result and the lower surface defect detection result.

2. The copper foil surface defect detection method according to claim 1, characterized in that: The method of adjusting the real-time acquisition speed of the first group of linear array CCD cameras and the second group of linear array CCD cameras according to the real-time moving speed of the copper foil to be tested and the preset reference acquisition speed includes: The moving speed ratio is calculated according to the real-time moving speed of the copper foil to be tested and the preset reference moving speed; Determining the quality grade according to the model parameters of the copper foil to be tested; Obtaining the micro texture change rate of the copper foil to be tested; The real-time acquisition speeds of the first group of linear array CCD cameras and the second group of linear array CCD cameras are adjusted according to the moving speed ratio, the quality level, the micro texture change rate and the preset reference acquisition speed.

3. The copper foil surface defect detection method according to claim 2, characterized in that: The acquiring corresponding feature point pairs in the upper surface image and the lower surface image comprises: Performing feature point detection on the upper surface image to obtain a first key feature point; Performing feature point detection on the lower surface image to obtain second key feature points; Feature matching is performed on the first key feature point and the second key feature point to obtain corresponding feature point pairs.

4. The copper foil surface defect detection method according to claim 3, characterized in that: The identifying the potential defect areas in the upper surface image and the lower surface image according to the corresponding feature point pairs comprises: Calculating a displacement vector between the corresponding feature point pairs; Determining whether there is a displacement between the upper surface image and the lower surface image according to the displacement vector; When it is determined that there is displacement, the area corresponding to the displacement vector in the upper surface image and the lower surface image is identified as a potential defect area.

5. The copper foil surface defect detection method according to claim 1, characterized in that: The performing surface defect detection on the upper surface image to obtain an upper surface defect detection result, and performing surface defect detection on the lower surface image to obtain a lower surface defect detection result comprises: Performing differential processing on the upper surface image and a reference upper surface image to obtain a first differential image; Performing surface defect detection based on the upper surface image to obtain a first upper surface defect detection result; Performing surface defect detection based on the first differential image to obtain a second upper surface defect detection result; Correcting the first upper surface defect detection result according to the second upper surface defect detection result to obtain the upper surface defect detection result; performing a difference process on the lower surface image and a reference lower surface image to obtain a second difference image; Performing surface defect detection based on the lower surface image to obtain a first lower surface defect detection result; Performing surface defect detection based on the second differential image to obtain a second lower surface defect detection result; The first lower surface defect detection result is corrected according to the second lower surface defect detection result to obtain the lower surface defect detection result.

6. The copper foil surface defect detection method according to claim 1, characterized in that: The method further comprises: Determine the defect location according to the copper foil surface defect detection result; The defect position is sent to a labeling machine, so that the labeling machine labels the area corresponding to the defect position on the copper foil to be tested.

7. The copper foil surface defect detection method according to claim 1, characterized in that: The first group of linear array CCD cameras is used to capture the upper surface of the copper foil to be tested to obtain the upper surface image under the lighting environment provided by the upper surface detection light source and the high-brightness backlight source; the second group of linear array CCD cameras is used to capture the lower surface of the copper foil to be tested to obtain the lower surface image under the lighting environment provided by the lower surface detection light source.

8. A copper foil surface defect detection device, characterized in that: The device comprises: A camera adjustment module, used for adjusting the real-time acquisition speed of the first group of linear array CCD cameras and the second group of linear array CCD cameras according to the real-time moving speed of the copper foil to be tested and a preset reference acquisition speed; An image acquisition module, used to acquire an upper surface image of the copper foil to be tested acquired by the first group of linear array CCD cameras at the real-time acquisition speed, and to acquire a lower surface image acquired by the second group of linear array CCD cameras at the real-time acquisition speed; A feature acquisition module, used to acquire corresponding feature point pairs in the upper surface image and the lower surface image; A region recognition module, used for identifying potential defect regions in the upper surface image and the lower surface image according to the corresponding feature point pairs; A first detection module is used to perform surface defect detection on the potential defect area to obtain a hidden defect detection result; A second detection module is used to perform surface defect detection on the upper surface image to obtain an upper surface defect detection result, and to perform surface defect detection on the lower surface image to obtain a lower surface defect detection result; The result generating module is used to generate the copper foil surface defect detection result according to the hidden defect detection result, the upper surface defect detection result and the lower surface defect detection result.

9. A computer device, characterized in that: The computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the copper foil surface defect detection method as claimed in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the copper foil surface defect detection method as claimed in any one of claims 1 to 7 are implemented.

Images