Electrode foil corrosion condition determination method and system
By constructing a composite gradient structure tensor and a corrosion saliency map, combined with automatic threshold segmentation and database matching, the problems of low efficiency and unstable results in electrode foil corrosion detection are solved, enabling a comprehensive evaluation and reliable judgment of electrode foil corrosion.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HUBEI FUYIDA ELECTRONIC TECH CO LTD
- Filing Date
- 2025-10-16
- Publication Date
- 2026-06-26
AI Technical Summary
Existing methods for detecting electrode foil corrosion are inefficient and produce unstable results. Automated detection is subject to imaging interference and has limited evaluation parameters, making it difficult to meet quality control requirements.
By constructing a composite gradient structure tensor that reflects the local brightness and texture information of pixels, anisotropic diffusion filtering is performed. Combined with corrosion saliency maps and mapping functions, an automatic threshold segmentation method is used to calculate morphological feature parameters and perform multidimensional matching with a standard corrosion level database to achieve a comprehensive judgment of corrosion status.
This improves the automation level of electrode foil corrosion detection, resulting in more reliable results and enhancing the accuracy and efficiency of product quality testing.
Smart Images
Figure CN121329920B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of situation assessment technology, specifically relating to a method and system for assessing the corrosion status of electrode foil. Background Technology
[0002] Electrode foil is the fundamental material for manufacturing aluminum electrolytic capacitors. Its performance determines the capacitor's capacitance, loss, leakage current, and lifespan. During electrode foil production, an electrochemical etching process creates a complex porous structure on the aluminum foil surface, increasing the surface area and improving the capacitor's capacitance per unit volume. The uniformity, depth, and morphology of the etching are crucial to the quality of the electrode foil; excessive or insufficient etching can lead to performance degradation or even product failure. Therefore, detecting and assessing the etching condition of the electrode foil is a core aspect of quality control in the production process. The industry primarily relies on manual visual inspection or sampling observation using microscopes. This method is inefficient, and the results are easily affected by factors such as operator experience, fatigue, and external environmental conditions.
[0003] Existing automated detection methods typically include image acquisition, preprocessing, segmentation, and feature analysis. In practical applications, the complex texture of the electrode foil surface makes it susceptible to interference from uneven lighting and noise during imaging, resulting in low contrast and blurred edges between the corroded area and the background substrate. Traditional image preprocessing methods, such as Gaussian filtering and median filtering, while smoothing background noise, also blur the contour edges of the corroded area, affecting subsequent image segmentation. Furthermore, existing evaluation methods often rely on single feature parameters, failing to provide a comprehensive assessment of the corrosion level. Summary of the Invention
[0004] This invention provides a method and system for judging the corrosion of electrode foil, in order to solve the technical problems of low efficiency and unstable results of manual detection of electrode foil corrosion in the prior art, and the existing automated detection is subject to imaging interference, blurred contours in preprocessing, and single evaluation parameters, which are difficult to meet the quality control requirements.
[0005] In a first aspect, the present invention provides a method for judging the corrosion status of electrode foil, comprising the following steps:
[0006] S1. Obtain the grayscale image of the electrode foil to be analyzed; construct a structure tensor based on the composite gradient reflecting the local brightness and texture information of the pixel, determine the anisotropic diffusion coefficient according to the structure tensor, and use the anisotropic diffusion coefficient to perform iterative anisotropic diffusion filtering on the grayscale image to obtain the filtered image.
[0007] S2, the anisotropic diffusion coefficient determined for each pixel is fused with the pixel intensity of the filtered image to obtain a high-contrast erosion saliency map; a mapping function is constructed based on the gray-level distribution of the erosion saliency map, and each pixel of the saliency map is input into the mapping function to obtain a segmentation threshold map of the same size as the filtered image.
[0008] S3. The filtered image is segmented using an automatic thresholding method to separate all corrosion areas; the area, perimeter, and shape compactness of each corrosion area are calculated as morphological feature parameters; the statistical distribution of the morphological feature parameters of all corrosion areas is matched with the standard corrosion level database in a multidimensional manner to output the corrosion status judgment result of the electrode foil.
[0009] Furthermore, a structure tensor is constructed based on the composite gradient reflecting the local brightness and texture information of pixels, and an anisotropic diffusion coefficient is determined according to the structure tensor. The anisotropic diffusion coefficient is then used to perform iterative anisotropic diffusion filtering on the grayscale image to obtain the filtered image, including:
[0010] Calculate the composite gradient of each pixel in the grayscale image. The composite gradient is a weighted sum of the brightness gradient and the texture gradient, with a weight coefficient of 0.5 for each.
[0011] A 3x3 structure tensor is constructed based on the composite gradient, and the eigenvalues of the structure tensor are calculated. The anisotropic diffusion coefficient is then determined based on the eigenvalues.
[0012] Perform anisotropic diffusion filtering once and calculate the bimodal separation index of the gray-level histogram of the current gray-level image;
[0013] Repeat the anisotropic diffusion filtering until the change in the bimodal separation index calculated in three consecutive iterations is less than 0.001, then terminate the iteration.
[0014] Furthermore, in S3, the global gray-level variance of the corrosion saliency map is calculated. When the global gray-level variance is less than a preset low fluctuation threshold, an automatic thresholding segmentation method is used on the filtered image to segment all corrosion regions, including:
[0015] The Otsu method is used to calculate the global segmentation threshold, which maximizes the inter-class variance between the pixel classes in the eroded region and the pixel classes in the background region. Pixels with gray values greater than the segmentation threshold in the filtered image are classified as eroded regions, and pixels with gray values less than or equal to the segmentation threshold are classified as background regions.
[0016] Furthermore, the area, perimeter, and shape compactness of each corroded region are calculated as morphological characteristic parameters, including:
[0017] The total number of pixels contained in each segmented eroded region is counted, and this count is taken as the area A of the eroded region.
[0018] An edge tracking algorithm is used to determine the boundary of each eroded region, and the total number of pixels on the boundary is counted as the perimeter P of the eroded region.
[0019] According to the formula Calculate the shape compactness C of each eroded region.
[0020] Furthermore, the statistical distribution of morphological characteristic parameters of all corroded areas is matched in a multidimensional manner with a standard corrosion level database to output the corrosion status assessment results of the electrode foil, including:
[0021] The mean and standard deviation of the area, perimeter, and shape compactness of all corrosion regions of the electrode foil to be analyzed are calculated to form a 6-dimensional feature vector.
[0022] Retrieve the standard 6-dimensional feature vector corresponding to each corrosion level from the standard corrosion level database;
[0023] Calculate the weighted Euclidean distance between the 6-dimensional eigenvector of the electrode foil to be analyzed and the standard eigenvector of each level in the database;
[0024] The standard level with the smallest weighted Euclidean distance is output as the result of judging the corrosion status of the electrode foil.
[0025] Furthermore, in S1, the Sobel operator is used to calculate the brightness gradient component of the grayscale image, a set of multi-directional Gabor filters are used to extract the texture features of the grayscale image and calculate its gradient component, and the two are weighted and fused to obtain the composite gradient.
[0026] Furthermore, in S2, a mapping function is constructed based on the gray-level distribution of the erosion saliency map. The expression of the mapping function is as follows: T(x,y)=μ(x,y)×[1-k×(1-S(x,y))], where T(x,y) is the threshold, μ(x,y) is the local mean, k is the preset modulation coefficient, and S(x,y) is the pixel saliency.
[0027] Furthermore, in S3, the standard corrosion level database pre-stores several standard levels, each of which corresponds to a standard three-dimensional feature distribution.
[0028] Further, in S1, a color image is captured of the electrode foil sample to be analyzed, and the color image is converted into an 8-bit grayscale image.
[0029] Secondly, the present invention provides an electrode foil corrosion condition judgment system, including a memory and a processor. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned electrode foil corrosion condition judgment method is implemented.
[0030] The beneficial effects are as follows: By constructing a composite gradient structure tensor reflecting the local brightness and texture information of pixels and performing anisotropic diffusion filtering, it is possible to smooth the complex texture and noise in the background area of the electrode foil image while preserving the contour edge information of the etched area, thus resolving the contradiction between noise reduction and edge preservation in traditional filtering methods. This invention performs multidimensional matching of statistical distribution with a standard corrosion level database, achieving a comprehensive evaluation of the corrosion condition. This makes the corrosion results more reliable and improves the automation level of electrode foil product quality inspection. Attached Figure Description
[0031] Figure 1 This is a flowchart of a method for judging the corrosion status of electrode foil. Detailed Implementation
[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0033] An embodiment of the electrode foil corrosion determination method provided by the present invention:
[0034] like Figure 1 As shown, the method for judging the corrosion condition of electrode foil includes the following steps:
[0035] S1. Obtain the grayscale image of the electrode foil to be analyzed; construct a structure tensor based on the composite gradient reflecting the local brightness and texture information of the pixel, determine the anisotropic diffusion coefficient according to the structure tensor, and use the anisotropic diffusion coefficient to perform iterative anisotropic diffusion filtering on the grayscale image to obtain the filtered image.
[0036] Under uniform illumination, the electrode foil sample to be analyzed was vertically photographed, and the color image was converted into an 8-bit grayscale image. The Sobel operator was used to calculate the brightness gradient components Ix and Iy of the grayscale image. Simultaneously, a set of multi-directional Gabor filters was used to extract the texture features of the grayscale image and calculate their gradient components Tx and Ty. These two gradients were then weighted and fused to obtain composite gradients Gx and Gy. A structure tensor J for each pixel was constructed based on the composite gradient. Then, eigenvalue decomposition was performed on the structure tensor J to obtain eigenvalues λ1 and λ2. The diffusion coefficient matrix D was determined based on the magnitude and difference of the eigenvalues. When λ1 is much larger than λ2, it indicates a strong edge, so the diffusion coefficient perpendicular to the edge direction is set to close to zero, while the diffusion coefficient along the edge direction is set to 1. When λ1 and λ2 are both small and close, it indicates a smooth region, so the diffusion coefficients in both directions are set to 1. The grayscale image was iteratively updated based on this diffusion coefficient. After each iteration, the inter-class variance of the grayscale histogram of the current grayscale image is calculated as a bimodal separation index. When the change in the inter-class variance value calculated in three consecutive iterations is less than a preset small threshold, such as 0.001, the filtering is determined to have converged and the iteration is terminated.
[0037] In an optional embodiment, a structure tensor is constructed based on a composite gradient reflecting the local brightness and texture information of a pixel, and an anisotropic diffusion coefficient is determined according to the structure tensor. The grayscale image is then subjected to iterative anisotropic diffusion filtering using the anisotropic diffusion coefficient to obtain a filtered image, including:
[0038] Calculate the composite gradient of each pixel in the grayscale image. The composite gradient is a weighted sum of the brightness gradient and the texture gradient, with a weight coefficient of 0.5 for each.
[0039] A 3x3 structure tensor is constructed based on the composite gradient, and the eigenvalues of the structure tensor are calculated. The anisotropic diffusion coefficient is then determined based on the eigenvalues.
[0040] Perform anisotropic diffusion filtering once and calculate the bimodal separation index of the gray-level histogram of the current gray-level image;
[0041] Repeat the anisotropic diffusion filtering until the change in the bimodal separation index calculated in three consecutive iterations is less than 0.001, then terminate the iteration.
[0042] The filtering process aims to smooth noise and irrelevant textures in the background regions of a grayscale image, while sharpening and preserving the true edges of eroded areas. For example, for a pixel at coordinates (100, 120) in a grayscale image, its brightness gradient is calculated to be 30 using the Sobel operator, and its texture gradient is calculated to be 18 using a set of Gaussian filters, resulting in a composite gradient of 24. A 3x3 structure tensor is constructed using the composite gradient values in the pixel's neighborhood. The calculated eigenvalues might be λ1=400 and λ2=60. Since the two eigenvalues differ significantly, it indicates the presence of strong edges, resulting in a smaller diffusion coefficient to suppress smoothing across edges. For example, the bimodal separation index calculated after the 8th iteration is 0.962, after the 9th iteration it is 0.965, and after the 10th iteration it is 0.967. Continuing the iteration, the indices calculated after the 11th, 12th, and 13th iterations are 0.9675, 0.9679, and 0.9682, respectively. The change between the 11th and 10th iterations is 0.0005, the change between the 12th and 11th iterations is 0.0004, and the change between the 13th and 12th iterations is 0.0003. Since the changes of 0.0005, 0.0004, and 0.0003 in the three consecutive iterations are all less than the preset threshold of 0.001, it indicates that the grayscale image quality has stabilized and the separation between the eroded and background areas has reached its optimal level. At this point, the iteration terminates to prevent excessive smoothing from causing the loss of subtle erosion features.
[0043] S2, the anisotropic diffusion coefficient determined for each pixel is fused with the pixel intensity of the filtered image to obtain a high-contrast erosion saliency map; a mapping function is constructed based on the gray-level distribution of the erosion saliency map, and each pixel of the saliency map is input into the mapping function to obtain a segmentation threshold map of the same size as the filtered image.
[0044] Specifically, the eigenvalue difference (λ1-λ2) of the anisotropic diffusion coefficient matrix is used as the edge intensity response. After normalization, it is summed at the pixel level with the normalized inverted gray value (255-I) of the filtered image to generate an erosion saliency map S. The local mean μ(x,y) and standard deviation σ(x,y) of the filtered image in the N×N neighborhood are calculated. A mapping function T(x,y)=μ(x,y)×[1-k×(1-S(x,y))] is constructed, where k is a preset modulation coefficient. The mapping function adjusts the threshold based on the local mean using the value of the erosion saliency map S. When the saliency S(x,y) of a pixel is high, its corresponding threshold T(x,y) is higher, thus generating a segmentation threshold map.
[0045] S3. The filtered image is segmented using an automatic thresholding method to separate all corrosion areas; the area, perimeter, and shape compactness of each corrosion area are calculated as morphological feature parameters; the statistical distribution of the morphological feature parameters of all corrosion areas is matched with the standard corrosion level database in a multidimensional manner to output the corrosion status judgment result of the electrode foil.
[0046] Specifically, each pixel (x, y) in the filtered image is traversed, and its pixel intensity value I(x, y) is obtained and compared with the threshold T(x, y) at the corresponding position in the segmentation thresholding image. If the pixel intensity value I(x, y) is less than the threshold T(x, y), the pixel is identified as an erosion point and assigned a value of 1; otherwise, it is identified as a background point and assigned a value of 0. After the traversal is completed, a binary mask image is obtained, where the regions with a logical value of 1 are the segmented erosion regions.
[0047] Calculate the global grayscale variance of the corrosion saliency map. If this variance is less than a preset low fluctuation threshold, instead of using a segmentation threshold map to segment the filtered image, an automatic threshold segmentation method is directly applied to the filtered image to segment all corrosion regions, including:
[0048] The Otsu method is used to calculate the global segmentation threshold, which maximizes the inter-class variance between the pixel classes in the eroded region and the pixel classes in the background region. Pixels with gray values greater than the segmentation threshold in the filtered image are classified as eroded regions, and pixels with gray values less than or equal to the segmentation threshold are classified as background regions.
[0049] Otsu's method automatically finds an optimal segmentation point on the gray-level histogram of a filtered image. Assuming the gray-level values of a filtered image range from 0 to 255, Otsu's method iterates through all possible thresholds from 1 to 254. For each candidate threshold, such as T=135, the algorithm divides all pixels into two groups: a background group with gray-level values less than or equal to 135 and an eroded group with gray-level values greater than 135. Then, it calculates the product of the square of the difference in gray-level means between these two groups and the proportion of pixels in each group, i.e., the inter-class variance.
[0050] The above process continues until a threshold, such as T=168, is found that maximizes the calculated inter-class variance. This threshold (T=168) is the global segmentation threshold. The grayscale value of each pixel in the filtered image is compared to 168. Pixels with a grayscale value of 190 are identified as eroded region pixels and assigned a value of 255 (i.e., white). Pixels with a grayscale value of 110 are marked as background pixels and assigned a value of 0 (i.e., black). A binary image containing only black and white is generated, where the white areas represent the segmented eroded regions.
[0051] In the filtered image, all pixels with grayscale values less than the global segmentation threshold are marked as eroded regions, and the remaining pixels are marked as background regions, thus generating a binary image. Connectivity analysis is performed on the segmented binary image to identify each independent eroded region. For each eroded region, its area is calculated by counting the total number of pixels it contains. The perimeter is calculated by tracing the contour of the region using an edge detection algorithm and accumulating the number or length of pixels on the contour. Shape compactness is preferably calculated using the formula 4 × π × area / perimeter squared; the closer to 1, the closer the shape is to a circle. Statistical histograms are generated from the area, perimeter, and shape compactness data of all eroded regions in the current filtered image, forming a three-dimensional feature distribution representing the current erosion state. A standard erosion level database pre-stores several standard levels, such as level one, level two, and level three, each corresponding to a standard three-dimensional feature distribution. The matching process calculates the distance between the three-dimensional feature distribution of the test sample and the three-dimensional feature distribution of each standard level in the database. The test sample is determined to be the standard level with the smallest distance, and this level is output as the erosion status judgment result.
[0052] In an optional embodiment, the area, perimeter, and shape compactness of each etched region are calculated as morphological characteristic parameters, including:
[0053] The total number of pixels contained in each segmented eroded region is counted, and this count is taken as the area A of the eroded region.
[0054] An edge tracking algorithm is used to determine the boundary of each eroded region, and the total number of pixels on the boundary is counted as the perimeter P of the eroded region.
[0055] According to the formula Calculate the shape compactness of each eroded region.
[0056] After obtaining the binary image, all independent white regions in the image are first identified using a connected component labeling algorithm, with each region representing an erosion point. For an erosion region labeled as '1', the region is traversed, and all white pixels belonging to it are counted. If there are a total of 620 pixels, the area A of the erosion region is 620. An edge tracking algorithm, such as Moore's neighborhood tracing, is applied to erosion region 1. Starting from a boundary pixel of the erosion region, the algorithm moves pixel by pixel along its outer boundary until it returns to the starting point. Assuming that this traversal covers a total of 110 boundary pixels, the perimeter P of the region is 110. Using the obtained area A=620 and perimeter P=110, its shape compactness C is calculated, yielding a result of approximately 0.64. The circular compactness is 1; a smaller value indicates a more irregular or elongated shape.
[0057] In an optional embodiment, the statistical distribution of morphological characteristic parameters of all corroded areas is matched in a multidimensional manner with a standard corrosion level database to output the corrosion status judgment result of the electrode foil, including:
[0058] The mean and standard deviation of the area, perimeter, and shape compactness of all corrosion regions of the electrode foil to be analyzed are calculated to form a 6-dimensional feature vector.
[0059] Retrieve the standard 6-dimensional feature vector corresponding to each corrosion level from the standard corrosion level database;
[0060] Calculate the weighted Euclidean distance between the 6-dimensional eigenvector of the electrode foil to be analyzed and the standard eigenvector of each level in the database;
[0061] The standard level with the smallest weighted Euclidean distance is output as the result of judging the corrosion status of the electrode foil.
[0062] Suppose that 80 eroded regions are detected on a filtered image to be tested. Calculate the area, perimeter, and compactness of these 80 regions and perform statistical analysis. The statistical results are as follows: average area 95, area standard deviation 30; average perimeter 60, perimeter standard deviation 15; average compactness 0.7, compactness standard deviation 0.1. This constitutes a 6-dimensional feature vector of the sample to be tested. .
[0063] Extract feature vectors of standard levels from the database; for example, the vector of level one slight erosion. Vector of Level 2 moderate corrosion The weighted Euclidean distance between the test vector and the two standard vectors is calculated, with the weighting coefficients pre-set according to the importance of each feature parameter. The calculated distance between the test sample and level one is 45.8, and the distance to level two is 12.3. Since 12.3 is the minimum distance, the features of the test sample are closest to the standard for level two moderate corrosion. Therefore, the output judgment is moderate corrosion.
[0064] An embodiment of the electrode foil corrosion assessment system provided by the present invention:
[0065] An electrode foil corrosion assessment system includes a processor and a memory. The memory stores computer program instructions, which, when executed by the processor, implement the aforementioned electrode foil corrosion assessment method.
[0066] An electrode foil corrosion assessment system also includes other components well known to those skilled in the art, such as a communication interface. The setup and functions of these components are known in the art and will not be described in detail here.
[0067] In this invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device. Any application or module described in this invention can be implemented using computer-readable / executable instructions stored or otherwise maintained by such a computer-readable medium.
[0068] The above are all preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Therefore, all equivalent changes made in accordance with the structure, shape and principle of the present invention should be covered within the scope of protection of the present invention.
Claims
1. A method for judging the corrosion condition of electrode foil, characterized in that, Includes the following steps: S1. Obtain the grayscale image of the electrode foil to be analyzed; construct a structure tensor based on the composite gradient reflecting the local brightness and texture information of the pixel, determine the anisotropic diffusion coefficient according to the structure tensor, and use the anisotropic diffusion coefficient to perform iterative anisotropic diffusion filtering on the grayscale image to obtain the filtered image. S2, the anisotropic diffusion coefficient determined for each pixel is fused with the pixel intensity of the filtered image to obtain a high-contrast erosion saliency map; a mapping function is constructed based on the gray-level distribution of the erosion saliency map, and each pixel of the saliency map is input into the mapping function to obtain a segmentation threshold map of the same size as the filtered image; wherein, the fusion of the anisotropic diffusion coefficient determined for each pixel with the pixel intensity of the filtered image to obtain a high-contrast erosion saliency map is specifically as follows: the eigenvalue difference of the anisotropic diffusion coefficient matrix is used as the edge intensity response, and after normalization, it is weighted and summed at the pixel level with the normalized inverted gray value of the filtered image to generate the erosion saliency map; S3. The filtered image is segmented using an automatic thresholding method to separate all corrosion areas; the area, perimeter, and shape compactness of each corrosion area are calculated as morphological feature parameters; the statistical distribution of the morphological feature parameters of all corrosion areas is matched with the standard corrosion level database in a multidimensional manner to output the corrosion status judgment result of the electrode foil.
2. The method for judging the corrosion status of electrode foil according to claim 1, characterized in that, A structure tensor is constructed based on a composite gradient reflecting the local brightness and texture information of pixels. An anisotropic diffusion coefficient is then determined based on the structure tensor. The grayscale image is then subjected to iterative anisotropic diffusion filtering using this coefficient to obtain the filtered image, including: Calculate the composite gradient of each pixel in the grayscale image. The composite gradient is a weighted sum of the brightness gradient and the texture gradient, with a weight coefficient of 0.5 for each. A 3x3 structure tensor is constructed based on the composite gradient, and the eigenvalues of the structure tensor are calculated. The anisotropic diffusion coefficient is then determined based on the eigenvalues. Perform anisotropic diffusion filtering once and calculate the bimodal separation index of the gray-level histogram of the current gray-level image; Repeat the anisotropic diffusion filtering until the change in the bimodal separation index calculated in three consecutive iterations is less than 0.001, then terminate the iteration.
3. The method for judging the corrosion status of electrode foil according to claim 1, characterized in that, In S3, the global gray-level variance of the corrosion saliency map is calculated. When the global gray-level variance is less than a preset low-fluctuation threshold, an automatic thresholding segmentation method is used on the filtered image to segment all corrosion regions, including: The Otsu method is used to calculate the global segmentation threshold, which maximizes the inter-class variance between the pixel classes in the eroded region and the pixel classes in the background region. Pixels with gray values less than the segmentation threshold in the filtered image are classified as eroded regions, and pixels with gray values less than or equal to the segmentation threshold are classified as background regions.
4. The method for judging the corrosion status of electrode foil according to claim 1, characterized in that, The area, perimeter, and shape compactness of each corroded region are calculated as morphological characteristic parameters, including: The total number of pixels contained in each segmented eroded region is counted, and this count is taken as the area A of the eroded region. An edge tracking algorithm is used to determine the boundary of each eroded region, and the total number of pixels on the boundary is counted as the perimeter P of the eroded region. According to the formula Calculate the shape compactness C of each eroded region.
5. The method for judging the corrosion status of electrode foil according to claim 1, characterized in that, The statistical distribution of morphological characteristic parameters of all corroded areas is matched in a multidimensional manner with a standard corrosion level database to output the corrosion status assessment results of the electrode foil, including: The mean and standard deviation of the area, perimeter, and shape compactness of all corrosion regions of the electrode foil to be analyzed are calculated to form a 6-dimensional feature vector. Retrieve the standard 6-dimensional feature vector corresponding to each corrosion level from the standard corrosion level database; Calculate the weighted Euclidean distance between the 6-dimensional eigenvector of the electrode foil to be analyzed and the standard eigenvector of each level in the database; The standard level with the smallest weighted Euclidean distance is output as the result of judging the corrosion status of the electrode foil.
6. The method for judging the corrosion status of electrode foil according to claim 1, characterized in that, In S1, the Sobel operator is used to calculate the brightness gradient component of the grayscale image, a set of multi-directional Gabor filters are used to extract the texture features of the grayscale image and calculate its gradient component, and the two are weighted and fused to obtain the composite gradient.
7. The method for judging the corrosion status of electrode foil according to claim 1, characterized in that, In S2, a mapping function is constructed based on the gray-level distribution of the erosion saliency map. The expression of the mapping function is as follows: T(x,y)=μ(x,y)×[1-k×(1-S(x,y))], where T(x,y) is the threshold, μ(x,y) is the local mean, k is the preset modulation coefficient, and S(x,y) is the pixel saliency.
8. The method for judging the corrosion status of electrode foil according to claim 1, characterized in that, In S3, the standard corrosion level database pre-stores several standard levels, each level corresponding to a standard three-dimensional feature distribution.
9. The method for judging the corrosion status of electrode foil according to claim 1, characterized in that, In S1, a color image is captured of the electrode foil sample to be analyzed, and the color image is converted into an 8-bit grayscale image.
10. A system for judging the corrosion status of electrode foil, characterized in that, It includes a memory and a processor, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the electrode foil corrosion determination method according to any one of claims 1-9 is implemented.