Automatic detection and area estimation method and system for grinding burn area

Abstract

The present application belongs to the technical field of image processing, and particularly relates to a grinding burn area automatic detection and area estimation method and system, comprising: acquiring a workpiece image after grinding processing; performing image segmentation on the acquired workpiece image to find a grinding burn range, and obtaining a workpiece binary image; performing morphological processing on the obtained workpiece binary image to obtain a workpiece morphological processing binary image; performing adaptive threshold processing on the acquired workpiece image to obtain a workpiece adaptive threshold binary image; merging the obtained workpiece morphological processing binary image and workpiece adaptive threshold binary image to obtain a workpiece merged binary image; according to the obtained workpiece merged binary image, tracking a grinding burn boundary of the workpiece, determining a grinding burn area of the workpiece, and calculating a grinding burn area of the workpiece. The present application combines K-means algorithm and morphological operation in technology, and realizes accurate and efficient automatic detection and area estimation of the grinding burn area.

Description

Technical Field

[0001] This invention belongs to the field of image processing technology, specifically relating to an automatic detection and area estimation method and system for grinding burn areas. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] In mechanical products, many important components such as bearings, gears, crankshafts, camshafts, piston pins, and universal joints require grinding after heat treatment. The power consumption per unit cutting area during grinding far exceeds that of other machining methods, and most of the converted heat enters the workpiece surface, easily causing changes in the metallographic structure of the machined surface. If the process parameters, cooling methods, and abrasive conditions are not properly selected, the workpiece is highly susceptible to developing a deep metallographic alteration layer (i.e., a tempered layer) during grinding, accompanied by significant residual surface stress, and even leading to cracks—a problem known as grinding burn.

[0004] Grinding burns reduce the wear resistance, corrosion resistance, and fatigue strength of materials; severe burns can even lead to cracks. Surface burns on parts can affect the surface integrity and processing quality of the workpiece, significantly reducing product performance and lifespan, and may even render the workpiece unusable, resulting in substantial economic losses.

[0005] Traditional methods for detecting grinding burns rely heavily on worker experience and subjective judgment, which is not only time-consuming but also susceptible to human error, making it difficult to guarantee accuracy and consistency. With the development of modern industrial automation technology, the industry has increasingly higher demands for automation, intelligence, and accuracy in grinding burn detection. Image processing and machine learning have demonstrated great potential in many industrial applications; in particular, the K-means clustering algorithm, which can quickly classify large amounts of data, has been widely used in image processing, especially in image segmentation and object detection tasks. Morphological operations, on the other hand, are widely used due to their excellent performance in image preprocessing, noise removal, and feature extraction.

[0006] However, using the K-means algorithm or morphological operations alone often fails to meet the high accuracy and real-time requirements of grinding burn detection. While the K-means algorithm can quickly classify images, it may be sensitive to noise and small non-burned areas; and while morphological operations can effectively remove noise, they may inadvertently delete burned areas or result in incomplete burned areas. Summary of the Invention

[0007] To address the aforementioned issues, this invention proposes an automatic detection and area estimation method and system for grinding burn areas. This method combines the K-means algorithm with morphological operations to achieve accurate and efficient automatic detection and area estimation of grinding burn areas.

[0008] According to some embodiments, the first solution of the present invention provides an automatic detection and area estimation method for grinding burn areas, which adopts the following technical solution:

[0009] An automatic detection and area estimation method for grinding burn areas includes:

[0010] Obtain images of the workpiece after grinding;

[0011] The acquired workpiece image is segmented to locate the grinding burn area, resulting in a binary image of the workpiece.

[0012] Morphological processing is performed on the obtained binary image of the workpiece to obtain a morphologically processed binary image of the workpiece.

[0013] The acquired workpiece image is subjected to adaptive thresholding to obtain an adaptive thresholded binary image of the workpiece.

[0014] The obtained workpiece morphology-processed binary image and the workpiece adaptive thresholded binary image are merged to obtain the merged binary image of the workpiece;

[0015] Based on the obtained merged binary image of the workpiece, the grinding burn boundary of the workpiece is traced, the grinding burn area of ​​the workpiece is determined, and the grinding burn area of ​​the workpiece is calculated.

[0016] As a further technical limitation, during the morphological processing, an area opening operation is performed on the obtained binary image of the workpiece and a preset image pixel number threshold. When the number of pixels of a connected component in the image is less than the preset image pixel number threshold, the connected component is deleted to obtain a binary image of the workpiece morphological processing.

[0017] As a further technical limitation, the workpiece morphology-processed binary image and the workpiece adaptive thresholding binary image are merged to obtain a merged binary image of the workpiece if and only if both the workpiece morphology-processed binary image and the workpiece adaptive thresholding binary image are within the grinding burn range.

[0018] As a further technical limitation, the workpiece is obtained by superimposing the combined binary image of the workpiece, the workpiece image, and the grinding burn boundary of the workpiece to obtain the boundary of the grinding burn area and determine the grinding burn area of ​​the workpiece; the number of image pixels of the determined grinding burn area of ​​the workpiece is calculated, and the grinding burn area of ​​the workpiece is obtained by calculating the number of image pixels of the grinding burn area of ​​the workpiece and the total number of image pixels of the workpiece image.

[0019] As a further technical limitation, in the process of adaptive thresholding, the grayscale mean of the acquired workpiece image is calculated, the adaptive threshold is determined, and an adaptive thresholded binary image of the workpiece is obtained based on the obtained adaptive threshold and the workpiece image.

[0020] As a further technical limitation, after acquiring the workpiece image, the workpiece image is converted to grayscale; that is, based on the rgb2gray function, the hue and saturation of the workpiece image are eliminated, while the brightness of the workpiece image is preserved, thus converting the colored workpiece image into a grayscale image.

[0021] As a further technical limitation, the K-means algorithm is used to segment the workpiece image during the image segmentation process. Specifically, K image pixel values ​​are randomly selected as initial cluster centers; the distance between each pixel in the workpiece image and the selected K cluster centers is calculated, and the cluster center with the smallest distance is taken as the cluster center, and the workpiece image pixels are assigned to the cluster centers; the cluster centers are updated until the cluster centers no longer change or the maximum number of iterations is reached, at which point the image segmentation is completed, and a binary image of the workpiece is obtained.

[0022] After image segmentation, K clustered images with cluster centers are obtained. The clustered image region with the smallest gray value is the range of the grinding burn area.

[0023] According to some embodiments, the second aspect of the present invention provides an automatic detection and area estimation system for grinding burn areas, employing the following technical solution:

[0024] An automatic detection and area estimation system for grinding burn areas includes:

[0025] The acquisition module is configured to acquire images of the workpiece after grinding.

[0026] The clustering module is configured to perform image segmentation on the acquired workpiece image, find the grinding burn area, and obtain a binary image of the workpiece.

[0027] The processing module is configured to perform morphological processing on the obtained workpiece binary image to obtain a workpiece morphologically processed binary image; perform adaptive thresholding on the acquired workpiece image to obtain a workpiece adaptively thresholded binary image; and merge the obtained workpiece morphologically processed binary image and the workpiece adaptively thresholded binary image to obtain a merged workpiece binary image.

[0028] The detection and calculation module is configured to trace the grinding burn boundary of the workpiece based on the obtained merged binary image of the workpiece, determine the grinding burn area of ​​the workpiece, and calculate the grinding burn area of ​​the workpiece.

[0029] According to some embodiments, a third aspect of the present invention provides a computer-readable storage medium, employing the following technical solution:

[0030] A computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps of an automatic detection and area estimation method for grinding burn areas as described in the first aspect of the present invention.

[0031] According to some embodiments, the fourth aspect of the present invention provides an electronic device, which adopts the following technical solution:

[0032] An electronic device includes a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the automatic detection and area estimation method for grinding burn areas as described in the first aspect of the present invention.

[0033] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0034] This invention effectively improves the accuracy of automatic detection and area estimation of workpiece grinding burn areas, and effectively analyzes and processes different burn images to achieve automated detection and identification of workpiece grinding burns. Attached Figure Description

[0035] The accompanying drawings, which form part of this embodiment, are used to provide a further understanding of this embodiment. The illustrative embodiments and their descriptions are used to explain this embodiment and do not constitute an improper limitation of this embodiment.

[0036] Figure 1 This is a flowchart of the automatic detection and area estimation method for grinding burn areas in Embodiment 1 of the present invention;

[0037] Figure 2 The diagram shows the detailed steps of the automatic detection and area estimation method for grinding burn areas in Embodiment 1 of the present invention.

[0038] Figure 3 This is a schematic diagram of the K-means image segmentation process in Embodiment 1 of the present invention;

[0039] Figure 4 This is a schematic diagram of a burned titanium alloy workpiece after grinding, as shown in Embodiment 1 of the present invention.

[0040] Figure 5 This is a schematic diagram of the burn detection results of a ground titanium alloy workpiece in Embodiment 1 of the present invention;

[0041] Figure 6 This is a structural block diagram of the automatic detection and area estimation system for grinding burn areas in Embodiment 2 of the present invention. Detailed Implementation

[0042] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0043] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of this application. Unless otherwise specified, 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 application pertains.

[0044] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0045] In this invention, terms such as "upper," "lower," "left," "right," "front," "back," "vertical," "horizontal," "side," and "bottom" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used only to facilitate the description of the structural relationships of the various components or elements of this invention and do not specifically refer to any component or element in this invention. They should not be construed as limiting the invention.

[0046] In this invention, terms such as "fixed connection," "connected," and "linked" should be interpreted broadly, indicating a fixed connection, an integral connection, or a detachable connection; a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can determine the specific meaning of these terms in this invention based on the specific circumstances, and they should not be construed as limitations on the invention.

[0047] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0048] Example 1

[0049] Embodiment 1 of the present invention introduces an automatic detection and area estimation method for grinding burn areas.

[0050] like Figure 1 and Figure 2 The method for automatic detection and area estimation of grinding burn areas, as shown, includes:

[0051] Obtain images of the workpiece after grinding;

[0052] The acquired workpiece image is segmented to locate the grinding burn area, resulting in a binary image of the workpiece.

[0053] Morphological processing is performed on the obtained binary image of the workpiece to obtain a morphologically processed binary image of the workpiece.

[0054] The acquired workpiece image is subjected to adaptive thresholding to obtain an adaptive thresholded binary image of the workpiece.

[0055] The obtained workpiece morphology-processed binary image and the workpiece adaptive thresholded binary image are merged to obtain the merged binary image of the workpiece;

[0056] Based on the obtained merged binary image of the workpiece, the grinding burn boundary of the workpiece is traced, the grinding burn area of ​​the workpiece is determined, and the grinding burn area of ​​the workpiece is calculated.

[0057] Taking titanium alloy as an example, the method proposed in this embodiment will be described in detail.

[0058] As one or more implementation methods, obtaining such Figure 4 The image shows the burned workpiece images of four workpieces after grinding. After acquiring the workpiece images, grayscale processing is performed. That is, based on the rgb2gray function, the hue and saturation of the workpiece image are eliminated, while the brightness of the workpiece image is preserved, converting the colored workpiece image into a grayscale image. The color image includes red, green, and blue images. Based on the weighted average formula, the grayscale value T can be obtained as: T = 0.299R + 0.587G + 0.114B; R is the value of the red channel, G is the value of the green channel, and B is the value of the blue channel.

[0059] As one or more implementation methods, the K-means algorithm is used to segment the workpiece image during the image segmentation process; the specific process is as follows: Figure 3 As shown:

[0060] (1) Initialization

[0061] Three pixel values ​​are randomly selected as the initial cluster centers. These pixel values ​​are in the grayscale range (0-255); K=3 is chosen to segment the image into three main brightness levels: dark, medium, and bright. Thus, it can be expected that darker clusters may represent burned areas, while brighter clusters may represent normal areas; by comparing the average brightness of the clusters, the clusters representing burned areas can be determined.

[0062] (2) Allocation

[0063] For each pixel in the image, calculate its distance to three centers, and then assign it to the nearest center. The distance used here is the Euclidean distance, calculated using the following formula:

[0064]

[0065] Where x and y are the grayscale values ​​of two pixels.

[0066] (3) Update

[0067] For each cluster, the center of the cluster is recalculated, which is to calculate the average value of all pixel values ​​in the cluster.

[0068]

[0069] Among them, S j It is assigned to center c j The pixel set, x i It is set S j The pixel values ​​in the image.

[0070] (4) Iteration

[0071] Repeat the assignment and update steps until any of the following conditions are met:

[0072] 1) The cluster center no longer changes significantly;

[0073] 2) Reach the predetermined maximum number of iterations, i.e., 500 times.

[0074] (5) Results

[0075] After K-means clustering, each pixel is assigned to a cluster. In this way, the image is segmented into three brightness levels, each corresponding to a cluster; the original workpiece image G(x,y) is clustered by K-means to form a binary image Q(x,y) of the workpiece, in which the pixel values ​​of the burned areas are set to 1, and the pixel values ​​of the remaining areas are set to 0.

[0076] As one or more implementations, in the process of identifying the extent of grinding burn areas, the cluster with the smallest gray value among three clusters is found; assuming that the area with the smallest gray value represents the burn, because the burn area is usually darker than the surrounding area, a vector C is given, where C... i Find the minimum value in the vector representing the center (mean gray level) of the i-th cluster; that is, burned Cluster = argmin. i C i .

[0077] As one or more implementation methods, during morphological processing, an area opening operation is performed on the obtained binary image Q(x, y) of the workpiece and a preset image pixel count threshold T. When the number of pixels of the connected component CC in the image is less than the preset image pixel count threshold, the connected component is deleted, resulting in the morphologically processed binary image Q of the workpiece. new (x,y); that is, Wherein, CC(x,y) is a connected component containing position (x,y). In this embodiment, the preset image pixel number threshold T is defined as 100.

[0078] As one or more implementation methods, during the adaptive thresholding process, the average grayscale value of the acquired workpiece image is calculated, an adaptive threshold is determined, and an adaptively thresholded binary image of the workpiece is obtained based on the obtained adaptive threshold and the workpiece image; specifically,

[0079] (1) Calculate the local neighborhood mean

[0080] For each pixel location (x, y), a neighborhood N(x, y) is defined. Within this neighborhood, the gray values ​​of all pixels in N(x, y) are summed, and then divided by the total number of pixels in N(x, y) to obtain the average gray value M(x, y), i.e.: Where G(x,y) is the gray value of the image at position (x,y); N(x,y) is the local neighborhood of pixel position (x,y); and M(x,y) is the average gray value within the neighborhood N(x,y).

[0081] (2) Calculate the adaptive threshold

[0082] For each pixel position (x,y), a constant multiplier m is used, the value of which affects the sensitivity of the threshold; that is, the adaptive threshold T(x,y) for position (x,y) is T(x,y) = m × M(x,y); in this embodiment, m is taken as 0.3.

[0083] (3) Binarization

[0084] Based on the adaptive threshold T(x,y) and the original image G(x,y), the adaptive thresholded binary image B(x,y) of the workpiece is obtained, i.e.

[0085] As one or more implementations, the workpiece morphology-processed binary image and the workpiece adaptive thresholding binary image are merged to obtain a merged workpiece binary image if and only if both the workpiece morphology-processed binary image and the workpiece adaptive thresholding binary image are within the grinding burn range; that is, the merged workpiece binary image B'(x,y) is B'(x,y) = B(x,y)·Q. new (x,y); if and only if B(x,y) and Q new When both (x,y) are 1, then B'(x,y) is 1; otherwise, B'(x,y) is 0, meaning only Q is 1. new Only when both (x,y) and B(x,y) are marked as pixel positions of the burn area will it be marked as a burn area.

[0086] As one or more implementation methods, based on the obtained merged binary image of the workpiece, the workpiece image, and the grinding burn boundary of the workpiece, boundary superposition is performed to obtain the boundary of the grinding burn area, thus determining the grinding burn area of ​​the workpiece; the number of image pixels of the determined grinding burn area of ​​the workpiece is calculated, and the grinding burn area of ​​the workpiece is obtained by calculating the number of image pixels of the grinding burn area of ​​the workpiece and the total number of image pixels of the workpiece image; specifically:

[0087] In the merged binary image B'(x,y) of the workpiece, a pixel value of 1 represents white and a pixel value of 0 represents black; the goal of boundary tracing is to find the boundary of the burned area (usually a white area).

[0088] Consider a pixel position (x,y) on the boundary if and only if B'(x,y) = 1, and it has at least one neighboring pixel B'(i,j) = 0; (i,j) is a pixel position in the eight-neighborhood of (x,y); that is...

[0089]

[0090] It should be noted that for a specific pixel location (x, y), its eight neighborhood includes the eight pixels surrounding it. This takes into account the pixel's horizontal, vertical, and diagonal neighbors, hence the name "eight neighborhood". Compared to the commonly used four-neighbor and six-neighbor neighborhoods, choosing "eight neighborhood" here allows for the detection of finer boundary changes and details in burn detection.

[0091] Considering the original image G(x,y) and the merged binary image B'(x,y) of the workpiece, the boundary is superimposed onto the original image, highlighting the boundary of the burn area in the original image, thus obtaining the following: Figure 5 The boundary O(x,y) of the grinding burn area shown is O(x,y) = G(x,y) + α × B′(x,y); where α is a constant used to emphasize the boundary. In this embodiment, α is 255, corresponding to an 8-bit image.

[0092] As one or more implementations, the size function is used to obtain the size of the boundary image of the grinding burn area; [M,N]=size(B'); thus, the boundary P of the grinding burn area can be obtained. b for Total number of image pixels P of the workpiece image t For P t =M×N; where M is the number of rows in binary image B and N is the number of columns in binary image B'.

[0093] The percentage R of the grinding burn area of ​​the workpiece is the ratio of the number of image pixels in the grinding burn area to the total number of image pixels in the workpiece image, i.e.

[0094] Example 2

[0095] Embodiment 2 of the present invention introduces an automatic detection and area estimation system for grinding burn areas.

[0096] like Figure 6 The system shown is an automatic detection and area estimation system for grinding burn areas, comprising:

[0097] The acquisition module is configured to acquire images of the workpiece after grinding.

[0098] The clustering module is configured to perform image segmentation on the acquired workpiece image, find the grinding burn area, and obtain a binary image of the workpiece.

[0099] The processing module is configured to perform morphological processing on the obtained workpiece binary image to obtain a workpiece morphologically processed binary image; perform adaptive thresholding on the acquired workpiece image to obtain a workpiece adaptively thresholded binary image; and merge the obtained workpiece morphologically processed binary image and the workpiece adaptively thresholded binary image to obtain a merged workpiece binary image.

[0100] The detection and calculation module is configured to trace the grinding burn boundary of the workpiece based on the obtained merged binary image of the workpiece, determine the grinding burn area of ​​the workpiece, and calculate the grinding burn area of ​​the workpiece.

[0101] The detailed steps are the same as those of the automatic detection and area estimation method for grinding burn areas provided in Example 1, and will not be repeated here.

[0102] Example 3

[0103] Embodiment 3 of the present invention provides a computer-readable storage medium.

[0104] A computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the automatic detection and area estimation method for grinding burn areas as described in Embodiment 1 of the present invention.

[0105] The detailed steps are the same as those of the automatic detection and area estimation method for grinding burn areas provided in Example 1, and will not be repeated here.

[0106] Example 4

[0107] Embodiment 4 of the present invention provides an electronic device.

[0108] An electronic device includes a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the automatic detection and area estimation method for grinding burn areas as described in Embodiment 1 of the present invention.

[0109] The detailed steps are the same as those of the automatic detection and area estimation method for grinding burn areas provided in Example 1, and will not be repeated here.

[0110] The above description is merely a preferred embodiment of this practice and is not intended to limit the scope of this practice. Various modifications and variations can be made to this practice by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this practice should be included within the protection scope of this practice.

Claims

1. A method for automatic detection and area estimation of grinding burn areas, characterized in that, include: Obtain images of the workpiece after grinding; The acquired workpiece image is segmented to locate the grinding burn area, resulting in a binary image of the workpiece. Morphological processing is performed on the obtained binary image of the workpiece to obtain a morphologically processed binary image of the workpiece. The acquired workpiece image is subjected to adaptive thresholding to obtain an adaptive thresholded binary image of the workpiece. The obtained workpiece morphology-processed binary image and the workpiece adaptive thresholded binary image are merged to obtain the merged workpiece binary image; Based on the obtained merged binary image of the workpiece, the grinding burn boundary of the workpiece is traced, the grinding burn area of ​​the workpiece is determined, and the grinding burn area of ​​the workpiece is calculated. During the morphological processing, an area opening operation is performed on the obtained binary image of the workpiece and a preset image pixel number threshold. When the number of pixels of a connected component in the image is less than the preset image pixel number threshold, the connected component is deleted to obtain the morphologically processed binary image of the workpiece. The workpiece morphology-processed binary image and the workpiece adaptive thresholding binary image are merged to obtain a merged binary image of the workpiece if and only if both the workpiece morphology-processed binary image and the workpiece adaptive thresholding binary image are within the grinding burn range. Based on the obtained combined binary image of the workpiece, the workpiece image, and the grinding burn boundary of the workpiece, the boundary is superimposed to obtain the boundary of the grinding burn area and determine the grinding burn area of ​​the workpiece; the number of image pixels of the determined grinding burn area of ​​the workpiece is calculated, and the grinding burn area of ​​the workpiece is obtained by calculating the number of image pixels of the grinding burn area of ​​the workpiece and the total number of image pixels of the workpiece image.

2. The method for automatic detection and area estimation of grinding burn areas as described in claim 1, characterized in that, In the adaptive thresholding process, the grayscale mean of the acquired workpiece image is calculated, the adaptive threshold is determined, and the adaptive thresholded binary image of the workpiece is obtained based on the obtained adaptive threshold and the workpiece image.

3. The method for automatic detection and area estimation of grinding burn areas as described in claim 1, characterized in that, After acquiring the workpiece image, the workpiece image is converted to grayscale; that is, based on the rgb2gray function, the hue and saturation of the workpiece image are eliminated, while the brightness of the workpiece image is preserved, thus converting the colored workpiece image into a grayscale image.

4. The method for automatic detection and area estimation of grinding burn areas as described in claim 1, characterized in that, In the image segmentation process, the K-means algorithm is used to segment the workpiece image. Specifically, K image pixel values ​​are randomly selected as initial cluster centers. The distance between each pixel in the workpiece image and the selected K cluster centers is calculated, and the cluster center with the smallest distance is used as the cluster center. Workpiece image pixels are then assigned to the cluster centers. The cluster centers are updated until the cluster centers no longer change or the maximum number of iterations is reached, at which point the image segmentation is completed, and a binary image of the workpiece is obtained. After image segmentation, K clustered images with cluster centers are obtained. The clustered image region with the smallest gray value is the range of the grinding burn area.

5. An automatic detection and area estimation system for grinding burn areas, employing the automatic detection and area estimation method for grinding burn areas as described in any one of claims 1-4, characterized in that, include: The acquisition module is configured to acquire images of the workpiece after grinding. The clustering module is configured to perform image segmentation on the acquired workpiece image, find the grinding burn area, and obtain a binary image of the workpiece. The processing module is configured to perform morphological processing on the obtained workpiece binary image to obtain a workpiece morphologically processed binary image; perform adaptive thresholding on the acquired workpiece image to obtain a workpiece adaptively thresholded binary image; and merge the obtained workpiece morphologically processed binary image and the workpiece adaptively thresholded binary image to obtain a merged workpiece binary image. The detection and calculation module is configured to trace the grinding burn boundary of the workpiece based on the obtained merged binary image of the workpiece, determine the grinding burn area of ​​the workpiece, and calculate the grinding burn area of ​​the workpiece.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the steps of the automatic detection and area estimation method for grinding burn areas as described in any one of claims 1-4.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the automatic detection and area estimation method for grinding burn areas as described in any one of claims 1-4.

Images