A visual positioning method for laser stripping of multiple soft copper extrusions

Abstract

The present invention relates to the field of image processing technology, and in particular to a visual positioning method for laser stripping of multiple soft copper extrusions, comprising: obtaining a number of clusters under each clustering, and obtaining the stripping volatility of each pixel point according to the distance between each pixel point under each clustering and the cluster center point of the cluster to which all other pixels in the corresponding preset local window belong, and the distance between the cluster center points of the cluster to which the same pixel point belongs under two adjacent clusterings; obtaining the stripping possibility of each pixel point according to the stripping volatility of each pixel point and the grayscale value of the pixel point in the preset local window of each pixel point, and performing visual positioning of laser stripping of multiple soft copper extrusions. The present invention reduces the influence of small grayscale differences, improves the accuracy of visual positioning of laser stripping of multiple soft copper extrusions, and improves the generation efficiency of multiple soft copper extrusions.

Description

Technical Field

[0001] The invention relates to the technical field of image processing, and in particular to a visual positioning method for laser stripping of multiple soft copper extrusion sheets. Background Art

[0002] The principle of the multi-piece soft copper extrusion laser stripping process is to first form an insulating layer on the surface of the soft copper through the extrusion equipment, and then use the laser stripping technology to remove the unnecessary glue part to achieve the purpose of processing and treatment. The different areas of the multi-piece soft copper extrusion laser stripping process are positioned by visual positioning technology, so as to ensure the accuracy and efficiency of the laser stripping process through precise visual positioning.

[0003] When positioning the laser stripping process of multiple soft copper extrusions, the grayscale differences of the multiple soft coppers in different processing areas are small, and the different processing areas are also affected by light, making it impossible to accurately determine each area, resulting in low accuracy of visual positioning results, thereby hindering production and reducing production efficiency. Summary of the invention

[0004] The invention provides a visual positioning method for laser stripping of multiple soft copper extrusion sheets to solve the existing problems.

[0005] The present invention adopts the following technical scheme for a visual positioning method for laser stripping of multiple soft copper extrusion sheets:

[0006] One embodiment of the present invention provides a visual positioning method for laser stripping of multiple soft copper extrusions, the method comprising the following steps:

[0007] Get the image of soft copper extrusion laser stripping;

[0008] The pixels in the soft copper extrusion laser stripping image are clustered several times to obtain several clusters in each clustering process; all clustering parameters are different for different clustering processes; in each clustering process, the stripping volatility of each pixel is obtained based on the distance between the center point of the cluster to which each pixel belongs and other pixels in the preset local window, and the distance between the center points of the clusters to which the same pixel belongs in two adjacent clusterings;

[0009] According to the peeling volatility of each pixel point and the gray value of the pixel point in the preset local window of each pixel point, the peeling possibility of each pixel point is obtained;

[0010] Visual positioning of laser stripping of multiple soft copper extrusions is performed based on the stripping possibility of each pixel.

[0011] Furthermore, the pixel points in the soft copper extrusion laser stripping image are clustered several times to obtain several clusters under each clustering, including the following specific steps:

[0012] pass The clustering algorithm clusters the soft copper extrusion laser stripping images with different K values ​​to obtain K clusters of the soft copper extrusion laser stripping images under each K value; wherein the clusters under each K value are the clusters under each clustering;

[0013] Among them, the maximum value of the K value is the preset first parameter A, and the minimum value of the K value is 2.

[0014] Furthermore, in each clustering, according to the distance between each pixel and the center point of the cluster to which it belongs and the distance between the center points of the clusters to which the same pixel belongs in two adjacent clusterings, the peeling volatility of each pixel is obtained, and the specific steps include the following:

[0015] According to the distance between each pixel point at each K value and the center point of the corresponding cluster of other pixels in the preset local window, the first fluctuation degree of each pixel point at each K value is obtained;

[0016] According to the distance between the cluster center points of the cluster to which the same pixel belongs under two adjacent K values, the second fluctuation degree of each pixel is obtained;

[0017] According to the first fluctuation degree of each pixel point and the second fluctuation degree of each pixel point under each K value, the peeling volatility of each pixel point is obtained.

[0018] Furthermore, the first fluctuation degree of each pixel point at each K value is obtained according to the distance between each pixel point at each K value and the center point of the corresponding cluster of other pixels in the preset local window, and the specific steps include the following:

[0019] The average of the distances between each pixel point at each K value and the center point of its corresponding cluster of all other pixels in the preset local window is taken as the first fluctuation degree of each pixel point at each K value.

[0020] Furthermore, the second fluctuation degree of each pixel point is obtained according to the distance between the cluster center points of the cluster to which the same pixel point belongs under two adjacent K values, and the specific steps include the following:

[0021] The average of the distances between the cluster center points of the cluster to which each pixel belongs under all two adjacent K values ​​is taken as the second fluctuation degree of each pixel.

[0022] Furthermore, the stripping volatility of each pixel is obtained according to the first fluctuation degree of each pixel and the second fluctuation degree of each pixel under each K value, and the specific steps include the following:

[0023] The average of the first fluctuation degree of each pixel point under all K values ​​is recorded as the first value of each pixel point, the first values ​​of all pixel points are linearly normalized, and the peeling volatility of each pixel point is obtained according to the first value of each pixel point after normalization and the second fluctuation degree of each pixel point;

[0024] Among them, after normalization, the first value of each pixel point and the volatility of glue peeling of each pixel point are positively correlated, and the second fluctuation degree of each pixel point and the volatility of glue peeling of each pixel point are positively correlated.

[0025] Furthermore, the stripping possibility of each pixel is obtained according to the stripping volatility of each pixel and the gray value of the pixel in the preset local window of each pixel, and the specific steps include the following:

[0026] According to the peeling volatility of each pixel and the mean of the grayscale values ​​of all pixels in the local window of each pixel, the peeling possibility of each pixel is obtained;

[0027] Among them, the peeling volatility of each pixel point and the peeling possibility of each pixel point are positively correlated, and the mean of the grayscale values ​​of all pixels in the local window of each pixel point and the peeling possibility of each pixel point are positively correlated.

[0028] Furthermore, the visual positioning of multiple soft copper extrusion laser stripping is performed according to the stripping possibility of each pixel point, and the specific steps include the following:

[0029] pass The clustering algorithm clusters the pixels in the soft copper extrusion laser stripping image with K=3, and obtains three clusters;

[0030] Calculate the mean value of the peeling probability of all pixels in each cluster, take the area corresponding to the cluster with the largest mean value of peeling probability as the area to be processed by laser peeling, take the area corresponding to the cluster with the second largest mean value of peeling probability as the unprocessed area, and take the area corresponding to the cluster with the smallest mean value of peeling probability as the processed area;

[0031] The area being processed by laser stripping, the unprocessed area and the processed area are taken as the visual positioning results of laser stripping of multiple pieces of soft copper extrusion.

[0032] Furthermore, the specific steps of obtaining the preset local window are as follows:

[0033] Take any pixel point in the soft copper extrusion laser stripping image as the local window center point, is the size of the local window, then the local window of any pixel point in the soft copper extrusion laser stripping image is obtained;

[0034] in, The second parameter is preset.

[0035] Furthermore, the acquisition of the soft copper extrusion laser stripping image includes the following specific steps:

[0036] An industrial camera is used to collect RGB images of multiple pieces of soft copper extrusion laser stripping during the production process, and histogram equalization is performed on each channel value in the RGB images of multiple pieces of soft copper extrusion laser stripping to obtain the processed RGB images of soft copper extrusion laser stripping. The RGB images of soft copper extrusion laser stripping are then preprocessed with grayscale to obtain the grayscale images of soft copper extrusion laser stripping.

[0037] The beneficial effects of the technical solution of the present invention are as follows: the present invention obtains the stripping volatility of each pixel point according to the change of the cluster center point of the cluster to which each pixel point belongs under different clustering, and reduces the influence of small grayscale differences in various regions through the stripping volatility of each pixel point; according to the stripping volatility of each pixel point and the grayscale value of the pixel point in a preset local window of each pixel point, the stripping possibility of each pixel point is obtained, and visual positioning of laser stripping of multiple soft copper extrusions is performed, which reduces the influence of lighting in different regions, improves the accuracy of visual positioning of laser stripping of multiple soft copper extrusions, and improves the generation efficiency of multiple soft copper extrusions. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 A flowchart of the steps of a method for visual positioning of laser stripping of multiple soft copper extrusions of the present invention;

[0040] Figure 2 Flow chart for visual positioning of laser stripping of multiple soft copper extrusions. DETAILED DESCRIPTION

[0041] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a visual positioning method for laser stripping of multiple soft copper extrusions proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0042] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0043] The following is a detailed description of a specific scheme of a visual positioning method for laser stripping of multiple soft copper extrusion sheets provided by the present invention in conjunction with the accompanying drawings.

[0044] See also Figure 1 , which shows a flowchart of a method for visual positioning of laser stripping of multiple soft copper extrusions provided by an embodiment of the present invention, the method comprising the following steps:

[0045] Step S001: Collecting soft copper extrusion laser stripping images.

[0046] It should be noted that in order to distinguish various areas in the soft copper extrusion laser stripping process, it is necessary to collect soft copper extrusion laser stripping images and analyze various areas through soft copper extrusion laser stripping image detection.

[0047] Specifically, an industrial camera is used to collect RGB images of multiple pieces of soft copper extrusion laser stripping during the production process, and histogram equalization is performed on each channel value in the RGB images of multiple pieces of soft copper extrusion laser stripping to obtain the processed RGB images of soft copper extrusion laser stripping. The RGB images of soft copper extrusion laser stripping are then preprocessed with grayscale to obtain the grayscale image of soft copper extrusion laser stripping.

[0048] Among them, the process of performing histogram equalization on each channel value in the RGB image of multiple pieces of soft copper extrusion laser stripping and grayscale preprocessing on the RGB image of soft copper extrusion laser stripping are both well-known technologies and will not be described in detail here.

[0049] At this point, the soft copper extrusion laser stripping image is obtained.

[0050] Step S002: cluster the pixels in the soft copper extrusion laser stripping image several times to obtain several clusters under each clustering, and obtain the first fluctuation degree of each pixel and the second fluctuation degree of each pixel under each K value based on the distance between the center point of the cluster to which each pixel belongs and other pixels in its preset local window under each K value, and the distance between the center points of the clusters to which the same pixel belongs under two adjacent clusterings.

[0051] It should be noted that since there are three processing states in the process of laser stripping of soft copper extrusion, namely, processed, unprocessed and in-process, and since the grayscale differences between the areas in the soft copper extrusion laser stripping images corresponding to the three states are small, the effect of visual positioning of multiple pieces of soft copper extrusion laser stripping is poor. Therefore, it is necessary to cluster the soft copper extrusion laser stripping images under different K values, and analyze each pixel in the image through the clustering results under different K values.

[0052] It should be further explained that, during the laser stripping process of soft copper extrusion, the existing light will affect the division of the area. During the laser stripping process, the light corresponding to the three states of processed, unprocessed and processed is different. Therefore, the fluctuation of each pixel is analyzed by changing the cluster to which each pixel belongs in the clustering results under different K values, so as to determine the three processing stages corresponding to each area.

[0053] Specifically, a first parameter A is preset, wherein in this embodiment, This example is used for description, and this embodiment is not specifically limited, wherein A can be determined according to the specific implementation situation. A second parameter is preset , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. It may depend on the specific implementation situation.

[0054] pass The clustering algorithm clusters all the pixels in the soft copper extrusion laser stripping image with different K values, and obtains K clusters of the soft copper extrusion laser stripping image under each K value. The maximum value of K value is the preset first parameter A, and the minimum value of K value is 2; The clustering algorithm is a well-known technology and will not be described in detail here. The clustering result of each clustering is the clustering result under each K value.

[0055] Take any pixel point in the soft copper extrusion laser stripping image as the local window center point, is the size of the local window, and the local window of any pixel point in the soft copper extrusion laser stripping image is obtained.

[0056] It should be noted that when the pixels in the local range of each pixel in the soft copper extrusion laser stripping image belong to the same cluster, it means that the volatility of the pixel is small; when the pixels in the local range of each pixel in the soft copper extrusion laser stripping image do not belong to the same cluster, it means that the volatility of the pixel is large. Therefore, the distance between the cluster center points of the clusters to which the pixels around each pixel belong can be used to analyze whether each pixel is in a different processing stage.

[0057] Specifically, according to the distance between each pixel point at each K value and the center point of the cluster to which it belongs in the preset local window, the first fluctuation degree of each pixel point at each K value is obtained. As an embodiment, the specific calculation method is: the average of the distance between each pixel point at each K value and the center point of the cluster to which it belongs in all other pixel points in the preset local window is used as the first fluctuation degree of each pixel point at each K value. It can be expressed as:

[0058] In the formula, Indicates indivual The value of The pixel and all other pixels in the corresponding local window The distance between the cluster center points of the clusters to which the pixel points belong, Indicates The number of all pixels in a local window of pixels, Indicated in Value is The next The first fluctuation degree of each pixel.

[0059] Among them, the larger the distance between each pixel point under each K value and the center point of the cluster to which it belongs in other pixel points in its preset local window, the smaller the possibility that each pixel point belongs to the same area as the pixel point in the corresponding local window, that is, the smaller the possibility of belonging to the same processing stage, the larger the first fluctuation degree of each pixel point; the smaller the distance between each pixel point under each K value and the center point of the cluster to which it belongs in other pixel points in its preset local window, the larger the possibility that each pixel point belongs to the same area as the pixel point in the corresponding local window, that is, the larger the possibility of belonging to the same processing stage, the smaller the first fluctuation degree of each pixel point.

[0060] At this point, the first fluctuation degree of each pixel is obtained.

[0061] It should be noted that, when the distance between the cluster center points of the cluster to which the same pixel belongs under two adjacent K values ​​is smaller, the fluctuation of each pixel is smaller, that is, the influence of illumination and different processing stages is smaller; when the distance between the cluster center points of the cluster to which the same pixel belongs under two adjacent K values ​​is larger, the fluctuation of each pixel is larger, that is, the influence of illumination and different processing stages is greater.

[0062] Specifically, the second fluctuation degree of each pixel is obtained according to the distance between the cluster center points of the cluster to which the same pixel belongs under two adjacent K values. As an embodiment, the specific calculation method is: the average of the distances between the cluster center points of the cluster to which each pixel belongs under all two adjacent K values ​​is taken as the second fluctuation degree of each pixel. The formula is expressed as:

[0063] In the formula, Indicates indivual The value of The cluster center point of the cluster to which the pixel belongs is indivual The value of The distance between the cluster center points of the clusters to which the pixel points belong, Indicates all The number of values, Indicates The second fluctuation degree of each pixel.

[0064] Among them, the larger the distance between the cluster center points of the cluster to which the same pixel belongs under two adjacent K values, the greater the impact of the pixel on the illumination and different processing stages; the smaller the distance between the cluster center points of the cluster to which the same pixel belongs under two adjacent K values, the smaller the impact of the pixel on the illumination and different processing stages.

[0065] At this point, the second fluctuation degree of each pixel is obtained.

[0066] Step S003: Obtain the glue peeling volatility of each pixel point according to the first fluctuation degree of each pixel point and the second fluctuation degree of each pixel point under each K value, and obtain the glue peeling possibility of each pixel point according to the glue peeling volatility of each pixel point and the grayscale value of the pixel point in the preset local window of each pixel point.

[0067] It should be noted that the change of each pixel is analyzed by the change of the center point of the cluster to which each pixel belongs under different K values, and the area being laser stripped is determined by the change of each pixel, so as to accurately perform visual positioning of laser stripping of multiple pieces of soft copper extrusion.

[0068] Specifically, according to the first fluctuation degree of each pixel point under each K value and the second fluctuation degree of each pixel point, the volatility of glue peeling of each pixel point is obtained. The average of the first fluctuation degree of each pixel point under all K values ​​is recorded as the first numerical value of each pixel point, and the first numerical values ​​of all pixels points are linearly normalized. According to the first numerical value of each pixel point and the second fluctuation degree of each pixel point after normalization, the volatility of glue peeling of each pixel point is obtained; wherein, after normalization, the first numerical value of each pixel point and the volatility of glue peeling of each pixel point are positively correlated, and the second fluctuation degree of each pixel point and the volatility of glue peeling of each pixel point are positively correlated. As an embodiment, the specific calculation formula is:

[0069] In the formula, Indicates indivual The value of The first fluctuation degree of pixels, Indicates The second fluctuation degree of pixels, Indicates all The number of values, represents the linear normalization function, Indicates The peeling volatility of pixels. For the The first value of the pixel.

[0070] Among them, when the first fluctuation degree of each pixel point and the second fluctuation degree of each pixel point under each K value are greater, the corresponding peeling volatility of each pixel point is greater, that is, the possibility that the pixel point is in the peeling area is greater; when the first fluctuation degree of each pixel point and the second fluctuation degree of each pixel point under each K value are smaller, the corresponding peeling volatility of each pixel point is smaller, that is, the possibility that the pixel point is in the peeling area is smaller.

[0071] At this point, the peeling volatility of each pixel is obtained.

[0072] It should be noted that when laser stripping is performed on multiple pieces of soft copper extrusion, there are three areas corresponding to the processing stages, namely the processing area, the unprocessed area, and the processed area. Generally speaking, the pixels in the processing area are usually greatly affected by light, and this area will generate heat or reflect more light during the laser stripping process, which will cause the pixels in the processing area to show a higher grayscale value in the image; the pixels in the unprocessed area will reflect light in its original state under lighting conditions because they have not undergone any processing, and their grayscale values ​​may be between the processing area and the processed area. The surface texture of the processed area has changed due to stripping, cutting, etc., resulting in the reflection mode of light in this area being different from the original state. The grayscale value of the pixels in this area may be less affected by light, and the grayscale value of the pixels in this area is also smaller.

[0073] It should be further explained that the order of the degree to which the three areas are affected by light is that the area being treated is greater than the untreated area, which is greater than the treated area. Therefore, when multiple pieces of soft copper extrusions are laser stripped and exposed to light, there will be differences in grayscale values. Therefore, further analysis is conducted through the changes in grayscale values ​​of the three areas affected by light.

[0074] Specifically, the peeling possibility of each pixel is obtained according to the peeling volatility of each pixel and the grayscale value of the pixel in the local window of each pixel. As an embodiment, the specific calculation method is: according to the peeling volatility of each pixel and the mean of the grayscale values ​​of all pixels in the local window of each pixel, the peeling possibility of each pixel is obtained; wherein, the peeling volatility of each pixel and the peeling possibility of each pixel are positively correlated, and the mean of the grayscale values ​​of all pixels in the local window of each pixel and the peeling possibility of each pixel are positively correlated. The formula is expressed as:

[0075] In the formula, Indicates The volatility of pixels, Indicates The local window of pixels The gray value of a pixel, Indicates The number of all pixels in a local window of pixels, Indicates The possibility of peeling glue at each pixel.

[0076] in, It represents the mean of the grayscale values ​​of all pixels in the local window of each pixel. The larger the mean of the grayscale value, the more likely the pixel is to be in the laser stripping area, the second most likely to be in the unprocessed area, and the least likely to be in the processed area. The greater the volatility of the stripping of each pixel, the more likely the pixel is to be in the laser stripping area; the smaller the volatility of the stripping of each pixel, the less likely the pixel is to be in the laser stripping area.

[0077] At this point, the possibility of glue stripping at each pixel is obtained.

[0078] Step S004: Visual positioning of laser stripping of multiple soft copper extrusion sheets is performed according to the stripping possibility of each pixel point.

[0079] The stripping possibility of each pixel point is used to determine the various areas of multiple soft copper extrusions for laser stripping, so The clustering algorithm clusters the pixels in the soft copper extrusion laser stripping image, where the number of clusters is 3; thus, three clusters are obtained. The clustering algorithm is a well-known technology and will not be described in detail here.

[0080] Calculate the mean value of the peeling probability of all pixels in each cluster, and use the area corresponding to the cluster with the largest mean value of peeling probability as the area to be laser peeled, the area corresponding to the cluster with the second largest mean value of peeling probability as the unprocessed area, and the area corresponding to the cluster with the smallest mean value of peeling probability as the processed area.

[0081] Then the area in laser stripping treatment, the untreated area and the treated area are obtained; the area in laser stripping treatment, the untreated area and the treated area are used as the visual positioning result of laser stripping of multiple soft copper extrusions. Among them, the flowchart of visual positioning of laser stripping of multiple soft copper extrusions is as follows Figure 2 shown.

[0082] At this point, the laser stripping and visual positioning of multiple pieces of soft copper extrusion is completed.

[0083] At this point, this embodiment is completed.

[0084] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A visual positioning method for laser stripping of multiple soft copper extrusions, characterized in that: The method comprises the following steps: Get the image of soft copper extrusion laser stripping; The pixels in the soft copper extrusion laser stripping image are clustered several times to obtain several clusters in each clustering process; all clustering parameters are different for different clustering processes; in each clustering process, the stripping volatility of each pixel is obtained based on the distance between the center point of the cluster to which each pixel belongs and other pixels in the preset local window, and the distance between the center points of the clusters to which the same pixel belongs in two adjacent clusterings; According to the peeling volatility of each pixel point and the gray value of the pixel point in the preset local window of each pixel point, the peeling possibility of each pixel point is obtained; Visual positioning of laser stripping of multiple soft copper extrusions is performed based on the stripping possibility of each pixel point; The pixel points in the soft copper extrusion laser stripping image are clustered several times to obtain several clusters under each clustering, including the following specific steps: The soft copper extrusion laser stripping images are clustered with different K values ​​by using the K-means clustering algorithm to obtain K clusters of the soft copper extrusion laser stripping images under each K value; wherein the clusters under each K value are the clusters under each clustering; The maximum value of K is the preset first parameter A, and the minimum value of K is 2; In each clustering, according to the distance between each pixel and the center point of the cluster to which it belongs and the distance between the center points of the clusters to which the same pixel belongs in two adjacent clusterings, the peeling volatility of each pixel is obtained, and the specific steps are as follows: According to the distance between each pixel point at each K value and the center point of the cluster to which it belongs and other pixel points in the preset local window, the first fluctuation degree of each pixel point at each K value is obtained; According to the distance between the cluster center points of the cluster to which the same pixel belongs under two adjacent K values, the second fluctuation degree of each pixel is obtained; According to the first fluctuation degree of each pixel point and the second fluctuation degree of each pixel point under each K value, the peeling volatility of each pixel point is obtained.

2. According to claim 1, a method for visual positioning of laser stripping of multiple soft copper extrusions, characterized in that: The method of obtaining the first fluctuation degree of each pixel point at each K value according to the distance between each pixel point at each K value and other pixel points in the preset local window and the center point of the corresponding cluster to which it belongs comprises the following specific steps: The average of the distances between each pixel point at each K value and the center point of its corresponding cluster of all other pixels in the preset local window is taken as the first fluctuation degree of each pixel point at each K value.

3. According to claim 1, a method for visual positioning of laser stripping of multiple soft copper extrusions, characterized in that: The method of obtaining the second fluctuation degree of each pixel point according to the distance between the cluster center points of the cluster to which the same pixel point belongs under two adjacent K values ​​includes the following specific steps: The average of the distances between the cluster center points of the cluster to which each pixel belongs under all two adjacent K values ​​is taken as the second fluctuation degree of each pixel.

4. According to claim 1, a method for visual positioning of laser stripping of multiple soft copper extrusions, characterized in that: The step of obtaining the volatility of glue stripping of each pixel point according to the first fluctuation degree of each pixel point and the second fluctuation degree of each pixel point under each K value includes the following specific steps: The average of the first fluctuation degree of each pixel point under all K values ​​is recorded as the first value of each pixel point, the first values ​​of all pixel points are linearly normalized, and the peeling volatility of each pixel point is obtained according to the first value of each pixel point after normalization and the second fluctuation degree of each pixel point; Among them, after normalization, the first value of each pixel point and the volatility of glue peeling of each pixel point are positively correlated, and the second fluctuation degree of each pixel point and the volatility of glue peeling of each pixel point are positively correlated.

5. According to claim 1, a method for visual positioning of laser stripping of multiple soft copper extrusions, characterized in that: The method of obtaining the possibility of glue stripping of each pixel point according to the glue stripping volatility of each pixel point and the grayscale value of the pixel point in the preset local window of each pixel point includes the following specific steps: According to the peeling volatility of each pixel and the mean of the grayscale values ​​of all pixels in the local window of each pixel, the peeling possibility of each pixel is obtained; Among them, the peeling volatility of each pixel point and the peeling possibility of each pixel point are positively correlated, and the mean of the grayscale values ​​of all pixels in the local window of each pixel point and the peeling possibility of each pixel point are positively correlated.

6. According to claim 1, a method for visual positioning of laser stripping of multiple soft copper extrusions, characterized in that: The visual positioning of multiple soft copper extrusion laser stripping according to the stripping possibility of each pixel point includes the following specific steps: The pixels in the soft copper extrusion laser stripping image were clustered with K=3 by using K-means clustering algorithm, and three clusters were obtained. Calculate the mean value of the peeling probability of all pixels in each cluster, take the area corresponding to the cluster with the largest mean value of peeling probability as the area to be processed by laser peeling, take the area corresponding to the cluster with the second largest mean value of peeling probability as the unprocessed area, and take the area corresponding to the cluster with the smallest mean value of peeling probability as the processed area; The area being processed by laser stripping, the unprocessed area and the processed area are taken as the visual positioning results of laser stripping of multiple pieces of soft copper extrusion.

7. According to claim 1, a method for visual positioning of laser stripping of multiple soft copper extrusions, characterized in that: The specific steps of obtaining the preset local window are as follows: Take any pixel point in the soft copper extrusion laser stripping image as the local window center point, is the size of the local window, then the local window of any pixel point in the soft copper extrusion laser stripping image is obtained; in, The second parameter is preset.

8. According to claim 1, a method for visual positioning of laser stripping of multiple soft copper extrusions, characterized in that: The specific steps of obtaining the soft copper extrusion laser stripping image are as follows: An industrial camera is used to collect RGB images of multiple pieces of soft copper extrusion laser stripping during the production process, and histogram equalization is performed on each channel value in the RGB images of multiple pieces of soft copper extrusion laser stripping to obtain the processed RGB images of soft copper extrusion laser stripping. The RGB images of soft copper extrusion laser stripping are then preprocessed with grayscale to obtain the grayscale images of soft copper extrusion laser stripping.

Images