CN118115499B - Visual detection method for production quality of electric power copper bar - Google Patents
Visual detection method for production quality of electric power copper bar Download PDFInfo
- Publication number
- CN118115499B CN118115499B CN202410524134.7A CN202410524134A CN118115499B CN 118115499 B CN118115499 B CN 118115499B CN 202410524134 A CN202410524134 A CN 202410524134A CN 118115499 B CN118115499 B CN 118115499B
- Authority
- CN
- China
- Prior art keywords
- region
- area
- corrosion
- copper bar
- cluster
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 title claims abstract description 143
- 229910052802 copper Inorganic materials 0.000 title claims abstract description 143
- 239000010949 copper Substances 0.000 title claims abstract description 143
- 238000001514 detection method Methods 0.000 title claims abstract description 24
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 21
- 230000000007 visual effect Effects 0.000 title claims abstract description 10
- 238000005260 corrosion Methods 0.000 claims abstract description 181
- 230000007797 corrosion Effects 0.000 claims abstract description 181
- 238000000034 method Methods 0.000 claims description 47
- 239000011159 matrix material Substances 0.000 claims description 20
- 238000011179 visual inspection Methods 0.000 claims description 10
- 238000007689 inspection Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 238000005530 etching Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 4
- 239000006185 dispersion Substances 0.000 description 4
- 238000003064 k means clustering Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000000758 substrate Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000003518 caustics Substances 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 239000002904 solvent Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
Abstract
The invention relates to the technical field of image data processing, in particular to a visual detection method for the production quality of an electric copper bar, which comprises the following steps: acquiring an electric power copper bar image; obtaining a plurality of areas of each class cluster according to the gray value of each pixel point in the electric power copper bar image; obtaining an etched region cluster according to the gray level and gradient of each pixel point in each region and the form of each region; and obtaining the corrosion degree of the electric power copper bar according to the number of the pixel points contained in each area in the corrosion area cluster, the gray value of each pixel point and the number of the pixel points in the electric power copper bar image, and performing quality detection. When the corrosion degree of the electric power copper bar is calculated, dividing the image into a plurality of areas through the gray value of each pixel point in the electric power copper bar image; the difference of the gray level and the gradient of different pixel points in the corrosion area is larger than that of different pixel points in the non-corrosion area, so that a more accurate corrosion area is obtained, and the detection result is more accurate.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to a visual detection method for production quality of an electric copper bar.
Background
A power copper bar is a conductive device used in power transmission and distribution systems. It is usually made of pure copper and has excellent electrical conductivity. Are commonly used to connect electrical equipment, electrical power distribution cabinets, switchgear, etc. to transmit electrical current and ensure reliable operation of the system. They can be manufactured in different shapes, sizes and cross-sectional areas to accommodate the needs of various electrical systems. If a chemical solvent containing corrosive substances is used in the production process or the environment is not clean, corrosion may occur to partial areas of the surface of the electric copper bar, so that quality detection on the electric copper bar is required in time.
According to the existing method, when the corrosion area is segmented according to the gray level difference between the corrosion area and the normal copper surface through a K-means clustering algorithm, the electric power copper bar surface possibly has a hole area, so that the segmented hole clusters possibly comprise the hole clusters, the corrosion area cannot be accurately extracted, and the detection result is inaccurate.
Disclosure of Invention
The invention provides a visual detection method for the production quality of an electric power copper bar, which aims to solve the existing problems.
The visual detection method for the production quality of the electric power copper bar adopts the following technical scheme:
The invention provides a visual detection method for the production quality of an electric power copper bar, which comprises the following steps:
Acquiring an electric power copper bar image;
According to the gray value of each pixel point in the electric power copper bar image, the pixel points in the electric power copper bar image are gathered into a plurality of class clusters, and a plurality of areas of each class cluster are obtained;
Obtaining the possibility that each region is a corrosion region according to the gray level and gradient of each pixel point in each region and the morphology of each region;
Obtaining corrosion area clusters according to the possibility that each area in each type of cluster is a corrosion area;
obtaining the corrosion degree of each area in the corrosion area cluster according to the number of the pixel points contained in each area in the corrosion area cluster and the gray value of each pixel point;
obtaining the corrosion degree of the electric power copper bar according to the corrosion degree of each area in the corrosion area cluster, the number of pixel points contained in each area in the corrosion area cluster and the number of pixel points in the electric power copper bar image;
And carrying out quality detection according to the corrosion degree of the electric power copper bar.
Further, the step of acquiring the electric power copper bar image comprises the following specific steps:
graying is carried out on the electric power copper bar image to be detected, so that the electric power copper bar gray level image to be detected is obtained and is recorded as the electric power copper bar image.
Further, according to the gray value of each pixel point in the electric power copper bar image, the pixel points in the electric power copper bar image are clustered into a plurality of class clusters to obtain a plurality of areas of each class cluster, and the method comprises the following specific steps:
According to the absolute value of the difference between the gray values of the pixel points in the electric power copper bar image, the pixel points in the electric power copper bar image are clustered into a plurality of clusters;
and carrying out connected domain detection on the pixel points in each class cluster to obtain a plurality of areas of each class cluster.
Further, the step of obtaining the possibility that each region is a corrosion region according to the gray level and the gradient of each pixel point in each region and the morphology of each region comprises the following specific steps:
the prior gray value of pixel points in normal area in normal power copper bar image is preset ；
Acquiring a gradient value and a gradient direction of each pixel point in each region through a sobel operator;
Selecting one pixel point in each edge of each region as a chain code starting pixel point, and acquiring a chain code of each edge in each region;
And obtaining the possibility that each region is a corrosion region according to the gray value of each pixel point in each region, the gradient direction, the priori gray value of the pixel point in the normal region in the normal power copper bar image and the chain code of each edge.
Further, the specific formula is as follows, according to the gray value of each pixel point in each area, the gradient direction, the prior gray value of the pixel point in the normal area in the normal power copper bar image and the chain code of each edge, to obtain the possibility that each area is a corrosion area:
in the method, in the process of the invention, Represent the firstThe likelihood that the individual areas are areas of corrosion,Is the prior gray value of the pixel point in the normal area in the normal power copper bar image,Is the firstThe average gray value of all pixels in a region,Represent the firstThe number of edges contained in each region,Is the firstFirst of the areasEdge chain code of each edgeThe direction of the individual chain codeThe minimum included angle of the directions of the individual chain codes,Represent the firstFirst of the areasThe number of chain code directions contained in the edge chain codes of the edges,Is the firstIn the first regionThe gradient direction of the individual pixel points,Is the firstIn the first region8 Th in the neighborhood of each pixel pointThe gradient direction of the individual pixel points,Represent the firstIn the first regionThe pixel point and the 8 th pixel point in the neighborhoodThe minimum included angle of the gradient direction of each pixel point,Is the firstThe number of pixels contained in the individual regions,The function of sigomid is represented as such,As a function of the absolute value of the function,Representing a cosine function.
Further, according to the likelihood that each area in each cluster is an etching area, an etching area cluster is obtained, and the specific formula is as follows:
in the method, in the process of the invention, Represent the firstThe individual clusters are the likelihood of a cluster of eroded regions,Represent the firstThe number of regions contained in the individual clusters,Represent the firstThe first group of the personal groupThe likelihood that individual areas are corrosion areas;
and acquiring the possibility that each type of cluster in the power copper bar image is an corroded area cluster, and marking the type of cluster with the highest possibility of being the corroded area cluster as the corroded area cluster.
Further, the method for obtaining the corrosion degree of each area in the corrosion area cluster according to the number of the pixel points contained in each area in the corrosion area cluster and the gray value of each pixel point comprises the following specific steps:
According to the gray value of each pixel point in each area in the corrosion area cluster, a gray level co-occurrence matrix of each area in the corrosion area cluster is obtained;
According to the gray level co-occurrence matrix of each region in the corroded region cluster, obtaining entropy of the gray level co-occurrence matrix of each region in the corroded region cluster;
And obtaining the corrosion degree of each region in the corrosion region cluster according to the entropy of the gray level co-occurrence matrix of each region in the corrosion region cluster, the number of the pixel points in each region and the gray level value of each pixel point in each region.
Further, the specific formula for obtaining the corrosion degree of each area in the corrosion area cluster according to the entropy of the gray level co-occurrence matrix of each area in the corrosion area cluster, the number of the pixel points in each area and the gray level value of each pixel point in each area is as follows:
in the method, in the process of the invention, Indicating the first in the etched region clusterThe degree of corrosion of the individual areas is,Indicating the first in the etched region clusterThe number of pixels contained in each region,Represents the maximum value of the number of pixel points contained in all areas in the corroded area cluster,Indicating the first in the etched region clusterThe value of the entropy of the gray co-occurrence matrix of each region,Indicating the first in the etched region clusterStandard deviation of pixel gray values in each region,Indicating the first in the etched region clusterThe maximum gray value of the pixel points contained in the individual areas,Indicating the first in the etched region clusterThe minimum gray value of the pixel points contained in the individual areas,Indicating the first in the etched region clusterThe average value of the gray values of all pixels in each area,The sigomid functions are represented.
Further, the corrosion degree of the electric copper bar is obtained according to the corrosion degree of each area in the corrosion area cluster, the number of pixel points contained in each area in the corrosion area cluster and the number of pixel points in the electric copper bar image, and the specific formula comprises the following steps:
in the method, in the process of the invention, Indicating the degree of corrosion of the power copper bar,The number of pixel points contained in the power copper bar image is represented,Indicating the first in the etched region clusterThe degree of corrosion of the individual areas is,Indicating the first in the etched region clusterThe number of pixels contained in each region,The number of the regions included in the etched region cluster is represented.
Further, the quality detection is performed according to the corrosion degree of the electric power copper bar, and the method comprises the following specific steps:
Presetting a corrosion degree threshold When the corrosion degree of the electric power copper barGreater than or equal to the corrosion level thresholdThe quality of the electric power copper bar to be detected is unqualified;
when the corrosion degree of the electric power copper bar Less than the corrosion degree thresholdAnd the quality of the electric power copper bar to be detected is qualified.
The technical scheme of the invention has the beneficial effects that: according to the gray level and the gradient of each pixel point in each region and the shape of each region, the possibility that each region is a corrosion region is obtained, because the difference between the gray level values of each pixel point in the corrosion region is larger than the difference between the gray level values of each pixel point in the non-corrosion region, the difference between the gradient values of each pixel point in the corrosion region is larger than the difference between the gray level values of each pixel point in the non-corrosion region, so that the possibility that each region is a corrosion region is closer to the actual situation, and the accuracy of the corrosion region cluster is higher; according to the number of the pixel points contained in each area in the corrosion area cluster and the gray value of each pixel point, the corrosion degree of each area in the corrosion area cluster is obtained, and the number of the pixel points contained in the corrosion area and the dispersion degree of the gray value of the pixel points are related to the corrosion degree of each area, so that the corrosion degree of each area in the corrosion area cluster can be combined with the form and gray characteristics of the corrosion area; and further, the corrosion degree of the electric power copper bar is more accurate, and the accuracy of the detection result is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart showing the steps of a visual inspection method for the production quality of an electric power copper bar;
fig. 2 is a gray scale image of an electrical copper bar to be inspected.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of a production quality visual detection method of the electric copper bar according to the invention, which is provided by combining the accompanying drawings and the preferred embodiment, and the detailed description of the specific implementation, the structure, the characteristics and the effects thereof is as follows. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
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.
The invention provides a specific scheme of a visual detection method for the production quality of an electric power copper bar, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a step flow chart of a visual inspection method for production quality of an electric copper bar according to an embodiment of the invention is shown, and the method includes the following steps:
Step S001: and acquiring an electric power copper bar image.
The main purpose of this embodiment is to perform quality inspection on the produced power copper bar, so that it is necessary to acquire a power copper bar image.
Specifically, under the condition of avoiding shadows and light reflection, acquiring an electric power copper bar image to be detected through a high-resolution camera; by graying, an electric power copper bar gray level image to be detected is obtained, and is marked as an electric power copper bar image as shown in fig. 2.
Step S002: and according to the gray value of each pixel point in the electric power copper bar image, the pixel points in the electric power copper bar image are gathered into a plurality of class clusters, and a plurality of areas of each class cluster are obtained.
It should be noted that, because areas such as holes may exist on the surface of the electric power copper bar, when the pixel points in the electric power copper bar image are clustered by the K-means clustering algorithm, a plurality of clusters may be obtained. And carrying out post-processing on the clustering result of the pixel points in the electric power copper bar image to obtain a corrosion area cluster in the electric power copper bar image, and carrying out quality detection on the electric power copper bar through the corrosion area cluster in the electric power copper bar image.
In this embodiment, the clustering result is analyzed, and the corrosion area cluster is obtained from the clustering result according to the characteristics of the corrosion area. Therefore, the pixel points in the power copper bar image are clustered into a plurality of clusters through a clustering algorithm. Because the power copper bar image mainly consists of a normal area, a hole area and a corrosion area, the number of final clusters is set to be 3.
Specifically, in the electric power copper bar image, according to the absolute value of the difference between the gray values of the pixel points, the k=3 is used for describing the embodiment through the K-means clustering algorithm, and the pixel points in the electric power copper bar image are clustered into 3 clusters. And carrying out connected domain detection on the pixel points in each class cluster to obtain a plurality of areas of each class cluster. The connected domain detection algorithm is a known technology, and this embodiment is not described in detail.
Step S003: obtaining the possibility that each region is a corrosion region according to the gray level and gradient of each pixel point in each region and the morphology of each region; and obtaining the corroded area cluster according to the possibility that each area in each type of cluster is a corroded area.
It should be noted that, because the corroded area in the RGB image is brown, dark green, and other colors, and the normal area and the hole area are bright orange red, the gray values of the corroded area pixels and the non-corroded area pixels are different; when the copper plate is corroded, the corrosion degrees of different areas may be different, so that the gray values of all the pixel points in the corrosion areas are greatly different, the gray values of all the pixel points in the normal area and the hole area are similar, and the gray and gradient directions of the pixel points in the corrosion areas are more discrete relative to the gray and gradient directions of the pixel points in the normal area and the hole area; because the corrosion area of the copper bar surface is generated by unexpected factors, the edges of the hole area and the normal area are mostly formed intentionally, so that the edges of the corrosion area are smoother relative to the edges of the hole area and the edges of the normal area. Therefore, according to the gray scale, the gradient direction and the edge shape of each pixel point in each region, the possibility that each region is a corrosion region is obtained.
Specifically, the gradient value and the gradient direction of each pixel point in each region are obtained through a sobel operator. The sobel operator is a known technique, and this embodiment is not described in detail. And selecting one pixel point in each edge of each region as a chain code starting pixel point, and acquiring the chain code of each edge in each region. The method for obtaining the chain code of each edge in each region is known in the art, and the description of this embodiment is omitted. According to the gray value, gradient direction and chain code of each pixel point in each region, the possibility that each region is a corrosion region is obtained, and the specific calculation formula is as follows:
in the method, in the process of the invention, Represent the firstThe likelihood that the individual areas are areas of corrosion,The prior gray value of the pixel point in the normal area in the normal power copper bar image is a preset value, and the prior gray value of the pixel point in the normal area in the normal power copper bar image preset in the embodimentThis embodiment is described by way of example; Is the first The average gray value of all pixels in a region,Represent the firstThe number of edges contained in each region,Is the firstFirst of the areasEdge chain code of each edgeThe direction of the individual chain codeThe minimum included angle of the directions of the individual chain codes,Represent the firstFirst of the areasThe number of chain code directions contained in the edge chain codes of the edges,Is the firstIn the first regionThe gradient direction of the individual pixel points,Is the firstIn the first region8 Th in the neighborhood of each pixel pointThe gradient direction of the individual pixel points,Represent the firstIn the first regionThe pixel point and the 8 th pixel point in the neighborhoodThe minimum included angle of the gradient direction of each pixel point,Is the firstThe number of pixels contained in the individual regions,The function of sigomid is represented as such,As a function of the absolute value of the function,Representing a cosine function.
It should be noted that becauseRepresent the firstThe absolute value of the difference between the average gray value of all the pixel points in each area and the gray value of the pixel point in the normal area in the normal power copper bar is larger, which indicates the firstThe larger the difference between the average gray level of each area and the gray level of the surface of the normal power copper bar is, the firstThe greater the likelihood of the individual areas being eroded; Represent the first The degree of edge smoothness of the individual regions, which will beThe minimum included angle between each chain code direction and the next chain code direction in the edge chain codes of each area passes throughMapping the function and taking average value to obtain the product, whereinAs input of function, ifThe less smooth the edges of the regions belong to the corrosion region, so that more chain code direction changes exist, thenWill be smaller and thereforeThe smaller the value of (2) is, the description of the (1)The greater the likelihood that the individual regions are corrosion regions; Represent the first The gradient directions of all the pixel points in each area are messy, and the gradient directions of the pixel points in the normal area and the pixel points in the hole area in the power copper bar image are similar to the gradient directions of the pixel points in the corrosion area, so that the power copper bar image passes through the first stepComparing the gradient direction of each pixel point in each region with the gradient directions of all pixels in 8 adjacent regions to obtain the first pixel pointThe gradient direction of all pixels in each region is disordered, soThe smaller the value, the firstThe greater the likelihood that the individual areas are corrosion areas.
So far, the possibility that each area in the power copper bar image is a corrosion area is obtained through the steps.
It should be noted that, in the above steps, each area in the power copper bar image is analyzed, but when the power copper bar image is acquired, noise may be generated, so that the gray value of a part of pixel points in the power copper bar image is changed, and the possibility that a part of non-corroded areas in the power copper card image are corroded areas is high, and the possibility that a part of corroded areas are corroded areas is low. Therefore, all areas in each type of cluster need to be subjected to overall analysis to obtain the corrosion area clusters in the power copper bar image. And obtaining the corrosion degree of the electric power copper bar through the corrosion area cluster in the electric power copper bar image.
It should be further noted that, because noise is randomly generated, the average value of the probability that all the areas in the corroded area cluster are corroded areas is larger than the average value of the probability that all the areas in the other area clusters are corroded areas. Therefore, according to the possibility that each area in each type of cluster in the electric power copper bar image is an etching area, the etching area cluster is obtained.
Specifically, according to the possibility that each area in each type of cluster is a corrosion area, the possibility that each type of cluster is a corrosion area cluster is obtained, and a specific calculation formula is as follows:
in the method, in the process of the invention, Represent the firstThe individual clusters are the likelihood of a cluster of eroded regions,Represent the firstThe number of regions contained in the individual clusters,Represent the firstThe first group of the personal groupThe individual areas are the potential for corrosion areas.
Further, through the steps, the possibility that each type of cluster in the power copper bar image is an etching area cluster is obtained, and the type cluster with the highest possibility of being the etching area cluster is marked as the etching area cluster.
Step S004: obtaining the corrosion degree of each area in the corrosion area cluster according to the number of the pixel points contained in each area in the corrosion area cluster and the gray value of each pixel point; obtaining the corrosion degree of the electric power copper bar according to the corrosion degree of each area in the corrosion area cluster, the number of pixel points contained in each area in the corrosion area cluster and the number of pixel points in the electric power copper bar image; and carrying out quality detection according to the corrosion degree of the electric power copper bar.
It should be noted that, because the corrosion area in the electric copper bar is generated by unexpected factors, and the copper surface is corroded to generate a copper green, the gray value of the pixel point in the corrosion area is lower than the gray value of the pixel point in the normal area, and the degree of dispersion of the gray value of the pixel point in the corrosion area is greater than the degree of dispersion of the gray value of the pixel point in the normal area. The number of pixel points in the corrosion area is also related to the corrosion degree of the corrosion area. Therefore, according to the number of the pixel points contained in each area in the corrosion area cluster, the gray value of the pixel points in each area in the corrosion area cluster is obtained, and the corrosion degree of each area in the corrosion area cluster is obtained.
Specifically, a gray level co-occurrence matrix of each region in the corroded region cluster is obtained, and entropy of the gray level co-occurrence matrix of each region in the corroded region cluster is obtained according to the gray level co-occurrence matrix of each region. The method for obtaining the gray level co-occurrence matrix of each region and the entropy of the gray level co-occurrence matrix of each region are known techniques, and are not described in detail in this embodiment. And obtaining the corrosion degree of each region in the corrosion region cluster according to the entropy of the gray level co-occurrence matrix of each region in the corrosion region cluster, the number of the pixel points in each region and the gray level value of each pixel point in each region. The specific calculation formula is as follows:
in the method, in the process of the invention, Indicating the first in the etched region clusterThe degree of corrosion of the individual areas is,Indicating the first in the etched region clusterThe number of pixels contained in each region,Represents the maximum value of the number of pixel points contained in all areas in the corroded area cluster,Indicating the first in the etched region clusterThe value of the entropy of the gray co-occurrence matrix of each region,Indicating the first in the etched region clusterStandard deviation of pixel gray values in each region,Indicating the first in the etched region clusterThe maximum gray value of the pixel points contained in the individual areas,Indicating the first in the etched region clusterThe minimum gray value of the pixel points contained in the individual areas,Indicating the first in the etched region clusterThe average value of the gray values of all pixels in each area,The sigomid functions are represented.
It should be noted that the number of the substrates,Represents the first of the etched area clustersThe maximum area ratio of each region to the other regions in the etched region cluster indicates the first region in the etched region cluster if the ratio is closer to 1The area of each region is larger than the area of other regions in the etched region cluster, then the first region in the etched region clusterThe greater the degree of corrosion in the individual zones; Indicating the first in the etched region cluster The gray level discrete coefficient of each region comprises the first of the corroded region clusterThe maximum gray level difference of each region, the entropy of gray level co-occurrence matrix and the gray level standard deviation are used for measuring the degree of the dispersion of the gray level of pixel points in the region, and the larger the value is, the description of the first pixel point in the corroded region clusterThe more discrete the gray value of the pixel point in each region is, the corrosion region cluster is the firstThe greater the degree of corrosion in the individual zones; represents the first of the etched area clusters The overall gray level of each region is lower due to the low gray value of the pixel points in the corroded regionThe larger the value of (C) is, the more the number of the etching area clusters isThe lower the gray value of the pixel point in each region, so the first region in the corroded region clusterThe greater the extent of corrosion in the individual zones.
Further, according to the corrosion degree of each area in the corrosion area cluster, the number of pixel points contained in each area in the corrosion area cluster, and the number of pixel points in the power copper bar image, the corrosion degree of the power copper bar is obtained, and a specific calculation formula is shown as follows:
in the method, in the process of the invention, Indicating the degree of corrosion of the power copper bar,The number of pixel points contained in the power copper bar image is represented,Indicating the first in the etched region clusterThe degree of corrosion of the individual areas is,Indicating the first in the etched region clusterThe number of pixels contained in each region,The number of the regions included in the etched region cluster is represented.
It should be noted that the number of the substrates,The ratio of the area of all areas in the corrosion area cluster to the area of the power copper bar image is shown, and the larger the value is, the larger the area of the corrosion area is, and the greater the corrosion degree of the power copper bar is; The average value of the corrosion degrees of all areas in the corrosion area cluster is represented, wherein the average corrosion degree of all areas in the corrosion area cluster is represented, and the larger the average value is, the stronger the corrosion degree of all areas in the corrosion area cluster is represented, and the greater the corrosion degree of the electric power copper bar is.
Further, a corrosion degree threshold is presetWhen the corrosion degree of the electric power copper barGreater than or equal to the corrosion level thresholdThe quality of the electric power copper bar to be detected is unqualified; when the corrosion degree of the electric power copper barLess than the corrosion degree thresholdAnd the quality of the electric power copper bar to be detected is qualified. Wherein the preset corrosion degree threshold valueThis embodiment will be described by way of example.
This embodiment is completed.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (9)
1. The visual detection method for the production quality of the electric power copper bar is characterized by comprising the following steps of:
Acquiring an electric power copper bar image;
According to the gray value of each pixel point in the electric power copper bar image, the pixel points in the electric power copper bar image are gathered into a plurality of class clusters, and a plurality of areas of each class cluster are obtained;
Obtaining the possibility that each region is a corrosion region according to the gray level and gradient of each pixel point in each region and the morphology of each region;
Obtaining corrosion area clusters according to the possibility that each area in each type of cluster is a corrosion area;
obtaining the corrosion degree of each area in the corrosion area cluster according to the number of the pixel points contained in each area in the corrosion area cluster and the gray value of each pixel point;
obtaining the corrosion degree of the electric power copper bar according to the corrosion degree of each area in the corrosion area cluster, the number of pixel points contained in each area in the corrosion area cluster and the number of pixel points in the electric power copper bar image;
Performing quality detection according to the corrosion degree of the electric power copper bar;
According to the gray level and gradient of each pixel point in each region and the morphology of each region, the possibility that each region is a corrosion region is obtained, and the method comprises the following specific steps:
the prior gray value of pixel points in normal area in normal power copper bar image is preset ；
Acquiring a gradient value and a gradient direction of each pixel point in each region through a sobel operator;
Selecting one pixel point in each edge of each region as a chain code starting pixel point, and acquiring a chain code of each edge in each region;
And obtaining the possibility that each region is a corrosion region according to the gray value of each pixel point in each region, the gradient direction, the priori gray value of the pixel point in the normal region in the normal power copper bar image and the chain code of each edge.
2. The visual inspection method for the production quality of the electric power copper bar according to claim 1, wherein the step of obtaining the electric power copper bar image comprises the following specific steps:
graying is carried out on the electric power copper bar image to be detected, so that the electric power copper bar gray level image to be detected is obtained and is recorded as the electric power copper bar image.
3. The visual inspection method for the production quality of the electric power copper bar according to claim 1, wherein the step of gathering the pixel points in the electric power copper bar image into a plurality of clusters according to the gray value of each pixel point in the electric power copper bar image to obtain a plurality of areas of each cluster comprises the following specific steps:
According to the absolute value of the difference between the gray values of the pixel points in the electric power copper bar image, the pixel points in the electric power copper bar image are clustered into a plurality of clusters;
and carrying out connected domain detection on the pixel points in each class cluster to obtain a plurality of areas of each class cluster.
4. The visual inspection method for the production quality of the electric power copper bar according to claim 1, wherein the obtaining the possibility that each area is a corrosion area according to the gray value of each pixel point in each area, the gradient direction, the prior gray value of the pixel point in the normal area in the normal electric power copper bar image and the chain code of each edge comprises the following specific formulas:
in the method, in the process of the invention, Represent the firstThe likelihood that the individual areas are areas of corrosion,Is the prior gray value of the pixel point in the normal area in the normal power copper bar image,Is the firstThe average gray value of all pixels in a region,Represent the firstThe number of edges contained in each region,Is the firstFirst of the areasEdge chain code of each edgeThe direction of the individual chain codeThe minimum included angle of the directions of the individual chain codes,Represent the firstFirst of the areasThe number of chain code directions contained in the edge chain codes of the edges,Is the firstIn the first regionThe gradient direction of the individual pixel points,Is the firstIn the first region8 Th in the neighborhood of each pixel pointThe gradient direction of the individual pixel points,Represent the firstIn the first regionThe pixel point and the 8 th pixel point in the neighborhoodThe minimum included angle of the gradient direction of each pixel point,Is the firstThe number of pixels contained in the individual regions,The function of sigomid is represented as such,As a function of the absolute value of the function,Representing a cosine function.
5. The visual inspection method for the production quality of the electric power copper bar according to claim 1, wherein the method is characterized in that the corrosion area cluster is obtained according to the possibility that each area in each type of cluster is a corrosion area, and comprises the following specific formulas:
in the method, in the process of the invention, Represent the firstThe individual clusters are the likelihood of a cluster of eroded regions,Represent the firstThe number of regions contained in the individual clusters,Represent the firstThe first group of the personal groupThe likelihood that individual areas are corrosion areas;
and acquiring the possibility that each type of cluster in the power copper bar image is an corroded area cluster, and marking the type of cluster with the highest possibility of being the corroded area cluster as the corroded area cluster.
6. The visual inspection method for the production quality of the electric power copper bar according to claim 1, wherein the method for obtaining the corrosion degree of each area in the corrosion area cluster according to the number of the pixel points contained in each area in the corrosion area cluster and the gray value of each pixel point comprises the following specific steps:
According to the gray value of each pixel point in each area in the corrosion area cluster, a gray level co-occurrence matrix of each area in the corrosion area cluster is obtained;
According to the gray level co-occurrence matrix of each region in the corroded region cluster, obtaining entropy of the gray level co-occurrence matrix of each region in the corroded region cluster;
And obtaining the corrosion degree of each region in the corrosion region cluster according to the entropy of the gray level co-occurrence matrix of each region in the corrosion region cluster, the number of the pixel points in each region and the gray level value of each pixel point in each region.
7. The visual inspection method for the production quality of the electric power copper bar according to claim 6, wherein the specific formula is as follows, according to the entropy of the gray level co-occurrence matrix of each area in the corrosion area cluster, the number of pixel points contained in each area and the gray level value of each pixel point in each area, the corrosion degree of each area in the corrosion area cluster is obtained:
in the method, in the process of the invention, Indicating the first in the etched region clusterThe degree of corrosion of the individual areas is,Indicating the first in the etched region clusterThe number of pixels contained in each region,Represents the maximum value of the number of pixel points contained in all areas in the corroded area cluster,Indicating the first in the etched region clusterThe value of the entropy of the gray co-occurrence matrix of each region,Indicating the first in the etched region clusterStandard deviation of pixel gray values in each region,Indicating the first in the etched region clusterThe maximum gray value of the pixel points contained in the individual areas,Indicating the first in the etched region clusterThe minimum gray value of the pixel points contained in the individual areas,Indicating the first in the etched region clusterThe average value of the gray values of all pixels in each area,The sigomid functions are represented.
8. The visual inspection method for the production quality of the electric power copper bar according to claim 1, wherein the method is characterized in that the corrosion degree of the electric power copper bar is obtained according to the corrosion degree of each area in the corrosion area cluster, the number of pixel points contained in each area in the corrosion area cluster and the number of pixel points in an electric power copper bar image, and comprises the following specific formulas:
in the method, in the process of the invention, Indicating the degree of corrosion of the power copper bar,The number of pixel points contained in the power copper bar image is represented,Indicating the first in the etched region clusterThe degree of corrosion of the individual areas is,Indicating the first in the etched region clusterThe number of pixels contained in each region,The number of the regions included in the etched region cluster is represented.
9. The visual inspection method for the production quality of the electric power copper bar according to claim 1, wherein the quality inspection is performed according to the corrosion degree of the electric power copper bar, and the method comprises the following specific steps:
Presetting a corrosion degree threshold When the corrosion degree of the electric power copper barGreater than or equal to the corrosion level thresholdThe quality of the electric power copper bar to be detected is unqualified;
when the corrosion degree of the electric power copper bar Less than the corrosion degree thresholdAnd the quality of the electric power copper bar to be detected is qualified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410524134.7A CN118115499B (en) | 2024-04-29 | 2024-04-29 | Visual detection method for production quality of electric power copper bar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410524134.7A CN118115499B (en) | 2024-04-29 | 2024-04-29 | Visual detection method for production quality of electric power copper bar |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118115499A CN118115499A (en) | 2024-05-31 |
| CN118115499B true CN118115499B (en) | 2024-07-12 |
Family
ID=91219519
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410524134.7A Active CN118115499B (en) | 2024-04-29 | 2024-04-29 | Visual detection method for production quality of electric power copper bar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118115499B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115861320A (en) * | 2023-02-28 | 2023-03-28 | 天津中德应用技术大学 | Intelligent detection method for automobile part machining information |
| CN117218124A (en) * | 2023-11-09 | 2023-12-12 | 江苏森力威冶金设备有限公司 | Copper-aluminum switching surface processing quality detection method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102256181B1 (en) * | 2019-12-30 | 2021-05-27 | 한국과학기술원 | Method of inspecting and evaluating coating state of steel structure and system for the same |
| CN114742788A (en) * | 2022-04-01 | 2022-07-12 | 南通高精数科机械有限公司 | Copper bar defect detection method and system based on machine vision |
| CN117152137B (en) * | 2023-10-30 | 2024-01-26 | 江苏高特高金属科技有限公司 | Welded pipe corrosion state detection method based on image processing |
| CN117392469B (en) * | 2023-12-11 | 2024-02-20 | 深圳市丰源升科技有限公司 | Perovskite battery surface coating detection method and system based on machine vision |
| CN117522873B (en) * | 2024-01-05 | 2024-03-29 | 惠汕绿创(江苏)科技有限公司 | Solar photovoltaic module production quality detection system |
-
2024
- 2024-04-29 CN CN202410524134.7A patent/CN118115499B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115861320A (en) * | 2023-02-28 | 2023-03-28 | 天津中德应用技术大学 | Intelligent detection method for automobile part machining information |
| CN117218124A (en) * | 2023-11-09 | 2023-12-12 | 江苏森力威冶金设备有限公司 | Copper-aluminum switching surface processing quality detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118115499A (en) | 2024-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114842009B (en) | Cable defect detection optimization method based on gray level run matrix | |
| CN107507194B (en) | Insulator string fault detection method based on infrared image temperature distribution rule and BP neural network | |
| CN113808138B (en) | Artificial intelligence-based wire and cable surface defect detection method | |
| CN116309537B (en) | Defect detection method for oil stain on surface of tab die | |
| CN115345885A (en) | Method for detecting appearance quality of metal fitness equipment | |
| CN116721107B (en) | Intelligent monitoring system for cable production quality | |
| CN116977342B (en) | PCB circuit detection method based on image segmentation | |
| CN112508913B (en) | Cable section edge detection method based on image detection | |
| CN116452589B (en) | Intelligent detection method for surface defects of artificial board based on image processing | |
| CN114511718B (en) | Intelligent management method and system for materials for building construction | |
| CN116168037B (en) | Method and system for calculating bending degree of wire crimping based on image processing | |
| CN117692649B (en) | Ship remote monitoring video efficient transmission method based on image feature matching | |
| CN109584232A (en) | Equipment use state on-line monitoring method, system and terminal based on image recognition | |
| CN112561875A (en) | Photovoltaic cell panel coarse grid detection method based on artificial intelligence | |
| CN115984255A (en) | Defect identification method of online energy-taking movable intelligent vibration damper | |
| CN117576100A (en) | Surface defect grading detection and evaluation method for FPC connector | |
| CN118115499B (en) | Visual detection method for production quality of electric power copper bar | |
| CN113033099B (en) | Neural network modeling method of antenna shape based on computer vision | |
| CN109903258B (en) | Power cable category detection method and system based on gray level matching | |
| CN116758056A (en) | Electrical terminal production defect detection method | |
| CN109544614B (en) | Method for identifying matched image pair based on image low-frequency information similarity | |
| CN115456113A (en) | Modulation format identification method based on constellation diagram multi-feature extraction algorithm | |
| CN109059790B (en) | Spring pitch measurement method based on Fourier transform | |
| CN112037193A (en) | Power line feature marking method and device | |
| CN117455870B (en) | Connecting wire and connector quality visual detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |