A method for detecting seal cover mold wear based on machine vision

Abstract

The present invention belongs to the field of image processing technology, and specifically relates to a method for detecting wear of a sealing cap mold based on machine vision. The method comprises: capturing multiple images of a standard sealing cap mold during horizontal rotation; determining the grayscale significance of the mold position at different spatial positions based on the difference between the grayscale values of the same mold position at different spatial positions; determining the degree of grayscale influence of light at the spatial position on different mold positions based on the difference between the grayscale significance of different mold positions at the same spatial position; obtaining a corrected grayscale value for the mold position based on the degree of grayscale influence of light at different spatial positions on the same mold position, thereby reconstructing a standard image without illumination influence; and comparing the standard image with an image of the sealing cap mold to be detected without illumination influence, thereby detecting wear of the sealing cap mold to be detected. The present invention eliminates illumination interference and provides more accurate wear detection of the sealing cap mold.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and more particularly to a method for detecting wear of a sealing cover mold based on machine vision. Background Art

[0002] With the continuous development of modern manufacturing, molds play a vital role in product production. Especially for complex-shaped parts like sealing caps, mold accuracy directly impacts production efficiency and product quality. Over extended use, molds are susceptible to wear due to repeated high-intensity machining, impact, and friction. Wear not only reduces product dimensional accuracy but can also cause surface cracks and defects, ultimately impacting production stability and economic efficiency. Therefore, detecting mold wear is crucial.

[0003] With the improvement of industrial automation, machine vision-based detection technology has gradually become an important direction for mold wear monitoring. For example, the Chinese patent document with authorization publication number CN118196081B and the Chinese patent document with authorization publication number CN116912261B both use machine vision to detect defects on the mold surface.

[0004] Machine vision-based mold wear detection methods primarily rely on analyzing mold surface images, using image processing algorithms to extract features of worn areas and determine the extent of wear. Because sealing cap molds are metal molds, machine vision-based wear detection often results in reflections or shadows on the mold surface in the captured images, affecting the accuracy of wear detection.

[0005] Therefore, there is an urgent need for an efficient and accurate sealing cover mold wear detection method based on machine vision to improve the accuracy of sealing cover mold wear detection. Summary of the Invention

[0006] To solve the technical problem that the presence of reflections or shadows on the mold surface in the above-mentioned sealing cap mold image affects the accuracy of the detection of sealing cap mold wear, the present invention provides a sealing cap mold wear detection method based on machine vision, comprising:

[0007] The method comprises capturing multiple images of a standard sealing cap mold during horizontal rotation, and reconstructing a standard image free of illumination influence based on the multiple images of the standard sealing cap mold, including: the same mold position of the standard sealing cap mold is located at different spatial positions in different images, and determining the grayscale significance of the mold position at different spatial positions based on the difference between the grayscale values of the same mold position at different spatial positions; determining the degree of grayscale influence of light at the spatial position on different mold positions based on the difference between the grayscale significance of different mold positions at the same spatial position; determining the corrected grayscale value of the mold position based on the degree of grayscale influence of light at different spatial positions on the same mold position and the grayscale value of the mold position at different spatial positions; reconstructing an image based on the corrected grayscale values of all mold positions to obtain a standard image; capturing multiple images of the sealing cap mold to be inspected during horizontal rotation, and reconstructing an image to be inspected free of illumination influence based on the multiple images of the sealing cap mold to be inspected; and comparing the standard image with the image to be inspected to identify the wear condition of the sealing cap mold to be inspected.

[0008] The effects are as follows: the present invention eliminates the interference of illumination changes by reconstructing the standard image and the image to be detected, making image analysis more accurate, reducing the influence of environmental factors on the wear detection of the sealing cover, and improving the reliability of detection; the present invention performs analysis based on the grayscale significance of different mold positions at the same spatial position, and can accurately capture subtle differences in the mold surface, provide high-precision image data for subsequent wear detection, and ensure that even slight changes in wear can be detected; the present invention obtains the corrected grayscale value of the mold position according to the degree of influence of light at different spatial positions on the grayscale of the same mold position, and can remove the influence of illumination on the mold position, making the reconstructed standard image and the image to be detected more accurate. By analyzing the standard image and the image to be detected, the wear conditions of different positions of the sealing cover mold to be detected can be accurately reflected, ensuring the accuracy of wear detection, especially when dealing with complex mold structures, and can effectively identify early wear and minor defects.

[0009] Preferably, the grayscale significance satisfies the expression: ;in, Indicates the target mold position in The grayscale significance at a spatial position, the target mold position is any position on the standard sealing cover mold; Indicates the target mold position in The grayscale value of the pixel corresponding to the spatial position; The first grayscale sequence representing the target mold position Grayscale values; 、 Respectively represent the maximum grayscale value and the minimum grayscale value in the grayscale sequence of the target mold position; is the length of the grayscale sequence of the target mold position; is an absolute value symbol; the grayscale sequence is a sequence composed of grayscale values of the target mold position at different spatial positions.

[0010] The effect is that by calculating the grayscale significance of the target mold position at different spatial positions, the grayscale changes of the target mold position at different angles and positions can be effectively measured, which can provide more stable and reliable grayscale data for subsequent image reconstruction and wear detection, thereby improving detection accuracy and robustness.

[0011] Preferably, the grayscale influence degree satisfies the expression:

[0012] ;in, Indicates the The degree of influence of light at a spatial position on the grayscale of the target mold position; Indicates the target mold position in Grayscale saliency at a spatial position; Indicates the The first gray level saliency sequence of the spatial position Gray level significance; 、 Respectively represent The maximum gray-level significance and the minimum gray-level significance in the gray-level significance sequence of the spatial position; Indicates the The length of the gray significance sequence of spatial positions; the gray significance sequence is the length of the gray significance sequence of spatial positions; All mold positions at spatial positions are in The sequence of gray-level saliency of spatial positions.

[0013] The effect is that by calculating the degree of grayscale influence of light at different spatial locations on the target mold position, the effect of illumination on the grayscale value changes of the mold image is effectively considered. By comparing the grayscale significance of different mold positions at different spatial locations, the influence of illumination on the different mold structures is quantified, allowing for subsequent adjustment of the grayscale data at each mold position, ensuring that the final image remains consistent under varying illumination, thereby improving the accuracy of image reconstruction and the reliability of detection results, and providing a more stable and accurate detection foundation, especially in complex lighting environments.

[0014] Preferably, the corrected grayscale value satisfies the expression:

[0015] ;in, Represents the corrected grayscale value of the target mold position; Indicates the The degree of influence of light at a spatial position on the grayscale of the target mold position; Indicates the target mold position in The grayscale value of the pixel corresponding to the spatial position; The length of the grayscale sequence representing the target mold position, wherein the grayscale sequence is a sequence of grayscale values of the target mold position at different spatial positions; Expressed as a natural constant An exponential function with base .

[0016] The effect is that the present invention fully considers the degree of light influence, and weights the grayscale values of the target mold position at different spatial positions. The weight is determined by the degree of influence of light at different spatial positions on the grayscale of the target mold position, so that the final corrected grayscale value can better reflect the real image characteristics when there is no light influence, which helps to reduce the interference of light changes on image quality, improve the stability and accuracy of the image, and enhance the reliability of subsequent sealing cover mold wear detection.

[0017] Preferably, reconstructing the image according to the corrected grayscale values of all mold positions to obtain a standard image includes: arranging the corrected grayscale values of all mold positions according to the corresponding positions of all mold positions in the first image obtained by shooting, to form a new image as the standard image.

[0018] Preferably, the comparing of the standard image and the image to be detected and identifying the wear condition of the sealing cover mold to be detected includes: performing template matching on the standard image and the image to be detected; determining the defect possibility of each pixel point in the mold area of the image to be detected based on the difference between each pixel point in the mold area of the image to be detected and the corresponding matching pixel point in the standard image; and screening the wear area according to the size of the defect possibility.

[0019] Preferably, the defect probability satisfies the expression:

[0020] ;in, Indicates the defect possibility of a target pixel, where the target pixel is any pixel in the mold area of the image to be inspected; Indicates the grayscale value of the target pixel; Represents the grayscale value of the matching pixel of the target pixel in the standard image; Indicates the extreme gray value in the mold area of the standard image; Indicates the number of pixels in the neighborhood of the target pixel. Gray value of each pixel; Indicates the number of pixels in the neighborhood of the target pixel. The gray value of the matching pixel in the standard image; Indicates the size of the neighborhood of the target pixel; is a hyperparameter; The natural constant An exponential function with base .

[0021] Preferably, screening the wear area according to the size of the defect possibility includes: taking the area consisting of all pixels whose defect possibility is greater than a preset wear threshold as the wear area.

[0022] The beneficial effects of the present invention are as follows: the present invention eliminates the interference of illumination changes by reconstructing the standard image and the image to be detected, making image analysis more accurate, reducing the influence of environmental factors on the wear detection of the sealing cover, and improving the reliability of detection; the present invention is based on the grayscale significance analysis of different mold positions at the same spatial position, and can accurately capture subtle differences in the mold surface, provide high-precision image data for subsequent wear detection, and ensure that even slight changes in wear can be detected; the present invention obtains the corrected grayscale value of the mold position according to the degree of influence of light at different spatial positions on the grayscale of the same mold position, and can remove the influence of illumination on the mold position, making the reconstructed standard image and the image to be detected more accurate. By analyzing the standard image and the image to be detected, the wear conditions of different positions of the sealing cover mold to be detected can be accurately reflected, ensuring the accuracy of wear detection, especially when dealing with complex mold structures, and can effectively identify early wear and minor defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0024] Figure 1 is a flow chart schematically illustrating a method for detecting seal cover mold wear based on machine vision in the present invention;

[0025] Figure 2 is a first schematic diagram schematically showing an image of a standard sealing cap mold captured during a rotation process;

[0026] Figure 3 is a second schematic diagram schematically showing an image of a standard sealing cap mold taken during a rotation process;

[0027] Figure 4 is a third schematic diagram schematically showing an image of a standard sealing cap mold captured during a rotation process;

[0028] Figure 5FIG1 is a flow chart schematically illustrating step S2 of a method for detecting wear of a sealing cover mold based on machine vision in the present invention. DETAILED DESCRIPTION

[0029] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0030] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0031] The embodiment of the present invention discloses a method for detecting wear of a sealing cover mold based on machine vision, referring to Figure 1 , including steps S1 to S4:

[0032] S1. Take multiple images of a standard sealing cap mold while it is rotating horizontally.

[0033] Place the standard sealing cap mold without wear horizontally on the testing table, which can rotate horizontally. During the testing table's horizontal rotation, use the camera above the testing table to shoot the standard sealing cap mold on the testing table. The implementer can set the angular velocity of the testing table's rotation and the camera's shooting frequency according to the actual implementation situation. For example, the angular velocity of the testing table's rotation is , the shooting frequency is once every 0.02 seconds. Figure 2 、 Figure 3 as well as Figure 4 They are respectively a first schematic diagram, a second schematic diagram and a third schematic diagram of images captured during the rotation process.

[0034] Perform semantic segmentation on the captured image to obtain the mold area in the image.

[0035] S2. Reconstructing a standard image without illumination influence based on the multiple images of the standard sealing cap mold.

[0036] It should be noted that the same position on the standard sealing cap mold will pass through different spatial positions during the rotation process and correspond to different pixel points in different images, for example Figure 2 midpoint After rotation, it is located Figure 3 midpoint Location and Figure 4 midpoint Different positions on the mold may pass through the same spatial position during the rotation process, such as Figure 2 midpoint After a certain rotation, Figure 3 midpoint location, Figure 2 midpoint After a certain rotation, Figure 4 midpoint location, Figure 2 midpoint location, Figure 3 midpoint Location and Figure 4 midpoint The location is Figure 2 、 Figure 3 、 Figure 4 The same row and column of Figure 2 midpoint 、 Figure 3 midpoint as well as Figure 4 midpoint The pixel positions in the image are the same, so Figure 2 midpoint location, Figure 3 midpoint Location and Figure 4 midpoint The present invention eliminates the interference of light based on the difference in grayscale values of the same mold position at different spatial positions on the standard sealing cover mold, and reconstructs the image to obtain a standard image without the influence of light.

[0037] Specifically, the flowchart of step S2 refers to Figure 5 , including steps S201 to S204:

[0038] S201 : Determine the grayscale significance of the mold position at different spatial positions based on the difference between the grayscale values of the same mold position at different spatial positions.

[0039] For any position on the standard sealing cap mold, the grayscale value of the pixel point corresponding to the mold position in the different images obtained is obtained according to the angular velocity of the rotation of the detection platform and the shooting frequency, and the grayscale sequence of the mold position is constructed according to the time sequence of the shooting.

[0040] It should be noted that due to the complex shooting environment and different lighting conditions at different spatial positions, there will be reflections or shadows on the mold surface in the captured image, which makes the same position on the mold present different colors when passing through different spatial positions during the rotation process, that is, there are differences in the grayscale values of the same mold position in the grayscale sequence. When the light at a certain spatial position has a greater impact on the color presented by the mold position in the image, the greater the difference between the grayscale value of the pixel corresponding to the mold position at this spatial position and the grayscale value of the pixel corresponding to the mold position at other spatial positions, that is, the grayscale value of the pixel corresponding to the mold position at this spatial position is more significant in the grayscale sequence of the mold position. Therefore, for any mold position, the present invention obtains the grayscale significance of the mold position at different spatial positions based on the grayscale sequence of the mold position, so as to subsequently determine the degree of influence of light at different spatial positions on the grayscale of the target mold position based on the grayscale significance.

[0041] Specifically, the grayscale significance satisfies the expression:

[0042] ;

[0043] Among them, any position on the standard sealing cover mold is recorded as the target mold position, Indicates the target mold position in Grayscale saliency at a spatial position; Indicates the target mold position in The grayscale value of the pixel corresponding to the spatial position; The first grayscale sequence representing the target mold position Grayscale values; The maximum grayscale value in the grayscale sequence representing the target mold position; The minimum grayscale value in the grayscale sequence representing the target mold position; The length of the grayscale sequence representing the target mold position; is the absolute value symbol; Reflects the target mold position in the The average difference between the grayscale value at the target mold position and the grayscale value at other spatial positions, For the mean difference Normalization is performed. When the average difference is larger, the target mold position is closer to the The more significant the gray value of the pixel corresponding to the first spatial position is in the gray sequence of the target mold position, the The greater the influence of light at a certain spatial position on the color of the target mold position in the image.

[0044] S202 : Determine the degree of influence of the light at the spatial position on the grayscales of different mold positions based on the difference in grayscale significance between different mold positions at the same spatial position.

[0045] It should be noted that the mold surface has different structures, and light at the same spatial location has different effects on the colors presented in the image for different mold surface structures. Different locations on the mold may pass through the same spatial location during rotation. Therefore, the present invention analyzes the grayscale significance of all mold locations passing through the same spatial location to determine the degree of influence of light at that spatial location on the grayscale of the target mold location.

[0046] Specifically, for any spatial position, the grayscale significance of all mold positions passing through the spatial position during the rotation of the detection platform at the spatial position is sorted according to the time sequence of the mold positions passing through the spatial position during the rotation of the detection platform to form a grayscale significance sequence for the spatial position.

[0047] According to The gray level saliency sequence of spatial positions is obtained The degree of influence of light at a spatial position on the grayscale of the target mold position:

[0048] ;

[0049] in, Indicates the The degree of influence of light at a spatial position on the grayscale of the target mold position; Indicates the target mold position in Grayscale saliency at a spatial position; Indicates the The first gray level saliency sequence of the spatial position Gray level significance; Indicates the The maximum gray-level significance in the gray-level significance sequence of spatial positions; Indicates the The minimum gray significance in the gray significance sequence of spatial positions; Indicates the The length of the grayscale significance sequence of the spatial position. The greater the gray significance of the spatial position, the greater the target mold position is in the The gray significance of the spatial position is greater than that of the other mold positions in the When the gray level of a spatial position is significant, the The greater the influence of the light at a spatial position on the grayscale of the target mold position.

[0050] S203 , determining a corrected grayscale value of the mold position according to the degree of influence of light at different spatial positions on the grayscale of the same mold position and the grayscale value of the mold position at different spatial positions.

[0051] The grayscale value of the target mold position is corrected according to the degree of influence of the light at each spatial position on the grayscale of the target mold position to obtain the corrected grayscale value of the target mold position:

[0052] ;

[0053] in, Represents the corrected grayscale value of the target mold position; Indicates the The degree of influence of light at a spatial position on the grayscale of the target mold position; Indicates the target mold position in The grayscale value of the pixel corresponding to the spatial position; The length of the grayscale sequence representing the target mold position; Expressed as a natural constant The present invention will be an exponential function with As the target mold position in The weight of the gray value of the pixel corresponding to the spatial position, when the gray influence The larger the The greater the influence of light at each spatial position on the color presentation of the target mold position in the image, the greater the difference between the actual color of the target mold position and the target mold position in the first spatial position. The greater the difference in the grayscale value of the corresponding pixel point at the spatial position, the greater the weight The smaller the value, the less reference is made to the target mold position in the first The gray value of the corresponding pixel point when the spatial position is The smaller the hour, the The smaller the effect of light at a spatial position on the color presentation of the target mold position in the image, the greater the difference between the actual color of the target mold position and the color of the target mold position in the first spatial position. The closer the grayscale values of the corresponding pixels are, the greater the weight The larger the value, the more reference is made to the target mold position in the first The grayscale value of the pixel corresponding to the spatial position is adjusted so that the corrected grayscale value can remove the influence of light and approach the actual color of the target mold position.

[0054] Similarly, obtain the corrected grayscale values of all mold positions.

[0055] S204 , reconstructing an image according to the corrected grayscale values of all mold positions to obtain a standard image.

[0056] The corrected grayscale values of all mold positions are arranged according to the corresponding positions of all mold positions in the first captured image to form a new image as a standard image.

[0057] At this point, a standard image of the standard sealing cap mold without illumination influence is obtained.

[0058] S3. Capturing multiple images of the sealing cap mold to be inspected while it is rotating horizontally, and reconstructing an image to be inspected without illumination influence based on the multiple images of the sealing cap mold to be inspected.

[0059] For the sealing cap mold to be inspected, the method in step S1 and step S2 is used to generate an image as the image to be inspected.

[0060] S4. Compare the standard image with the image to be inspected to identify the wear condition of the sealing cover mold to be inspected.

[0061] Perform template matching on the standard image and the image to be tested, and determine the defect possibility of each pixel in the mold area of the image to be tested based on the difference between each pixel in the mold area of the image to be tested and the corresponding matching pixel in the standard image:

[0062] ;

[0063] Among them, any pixel point in the mold area of the image to be detected is recorded as the target pixel point. Indicates the defect possibility of the target pixel; Indicates the grayscale value of the target pixel; Represents the grayscale value of the matching pixel of the target pixel in the standard image; Indicates the extreme gray value in the mold area of the standard image; Indicates the number of pixels in the neighborhood of the target pixel. Gray value of each pixel; Indicates the number of pixels in the neighborhood of the target pixel. The gray value of the matching pixel in the standard image; Indicates the size of the neighborhood of the target pixel, which is eight neighborhoods in this embodiment, namely In other embodiments, the implementer can set the neighborhood range size according to the actual implementation situation; is a hyperparameter used to prevent Larger, resulting in Always close to 0, The experience value is 5, and the implementer can also set it according to the actual implementation situation; The natural constant The exponential function with base Perform negative correlation mapping.

[0064] When the gray value of the target pixel differs from the gray value of the matching pixel in the standard image When the value is larger, the target pixel is more likely to be a worn pixel or a noise pixel. Since the worn area has a certain area, multiple worn pixels appear adjacent to each other. The closer the difference between the neighboring pixel and the corresponding matching pixel, The smaller it is, the more likely the target pixel is located in the worn area, and the greater the possibility of defect of the target pixel.

[0065] Similarly, the defect probability of each pixel in the mold area of the image to be inspected is obtained, and the defect probability greater than the preset wear threshold is set. The area formed by all the pixels of is regarded as the wear area. It is set by the implementers according to the actual implementation situation and is not limited to specific ones. For example .

[0066] At this point, the wear detection of the sealing cover mold is realized.

[0067] In the description of this specification, "multiple" and "several" mean at least two, such as two, three or more, unless otherwise clearly defined.

[0068] While this specification has shown and described several embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, variations, and alternatives will occur to those skilled in the art without departing from the concept and spirit of the present invention. It should be understood that in practicing the present invention, alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A method for detecting seal cover mold wear based on machine vision, characterized in that: include: Capture multiple images of a standard sealing cap mold during horizontal rotation, and reconstruct a standard image without illumination influence based on the multiple images of the standard sealing cap mold, including: The same mold position of the standard sealing cap mold is located at different spatial positions in different images. Based on the difference between the grayscale values of the same mold position at different spatial positions, the grayscale significance of the mold position at different spatial positions is determined, satisfying the expression: , The target mold position is The gray significance at a spatial position, the target mold position is any position on the standard sealing cover mold, The target mold position is The grayscale value of the pixel corresponding to the spatial position is is the first grayscale sequence of the target mold position Gray values, 、 are the maximum grayscale value and the minimum grayscale value in the grayscale sequence of the target mold position, is the length of the grayscale sequence of the target mold position, is the absolute value symbol; the grayscale sequence is the sequence of grayscale values of the target mold position at different spatial positions; according to the difference in grayscale significance between different mold positions at the same spatial position, the degree of influence of the light at the spatial position on the grayscale of different mold positions is determined, satisfying the expression: , For the The degree of influence of light at a spatial position on the grayscale of the target mold position, 、 、 Respectively The first gray level saliency sequence of the spatial position Gray significance, maximum gray significance, minimum gray significance, For the The length of the gray significance sequence of spatial positions; the gray significance sequence is the length of the gray significance sequence of spatial positions. All mold positions at spatial positions are in A sequence of grayscale significance of each spatial position is constructed; based on the degree of influence of light at different spatial positions on the grayscale of the same mold position and the grayscale value of the mold position at different spatial positions, the corrected grayscale value of the mold position is determined; the image is reconstructed based on the corrected grayscale values of all mold positions to obtain a standard image; Taking multiple images of the sealing cap mold to be inspected when it is horizontally rotating, and reconstructing an image to be inspected without illumination influence based on the multiple images of the sealing cap mold to be inspected; Compare the standard image with the image to be inspected to identify the wear condition of the sealing cover mold to be inspected.

2. The method for detecting sealing cover mold wear based on machine vision according to claim 1, characterized in that: The corrected grayscale value satisfies the expression: ； in, Represents the corrected grayscale value of the target mold position; Indicates the The degree of influence of light at a spatial position on the grayscale of the target mold position; Indicates the target mold position in The grayscale value of the pixel corresponding to the spatial position; The length of the grayscale sequence representing the target mold position, wherein the grayscale sequence is a sequence of grayscale values of the target mold position at different spatial positions; Expressed as a natural constant An exponential function with base .

3. The method for detecting sealing cover mold wear based on machine vision according to claim 1, characterized in that: The reconstructing of the image according to the corrected grayscale values of all mold positions to obtain a standard image includes: The corrected grayscale values of all mold positions are arranged according to the corresponding positions of all mold positions in the first captured image to form a new image as a standard image.

4. The method for detecting sealing cover mold wear based on machine vision according to claim 1, characterized in that: The comparing the standard image with the image to be inspected and identifying the wear condition of the sealing cover mold to be inspected includes: Perform template matching between the standard image and the image to be tested; determine the defect possibility of each pixel point in the mold area of the image to be tested based on the difference between each pixel point in the mold area of the image to be tested and the corresponding matching pixel point in the standard image; and screen the worn area based on the size of the defect possibility.

5. The method for detecting sealing cover mold wear based on machine vision according to claim 4, characterized in that: The defect probability satisfies the expression: ； in, Indicates the defect possibility of a target pixel, where the target pixel is any pixel in the mold area of the image to be inspected; Indicates the grayscale value of the target pixel; Represents the grayscale value of the matching pixel of the target pixel in the standard image; Indicates the extreme gray value in the mold area of the standard image; Indicates the number of pixels in the neighborhood of the target pixel. Gray value of each pixel; Indicates the number of pixels in the neighborhood of the target pixel. The gray value of the matching pixel in the standard image; Indicates the size of the neighborhood of the target pixel; is a hyperparameter; The natural constant An exponential function with base .

6. The method for detecting sealing cover mold wear based on machine vision according to claim 4, characterized in that: The method of screening the wear area according to the possibility of defects includes: The area formed by all pixels whose defect probability is greater than a preset wear threshold is regarded as the wear area.

Images