CN114723701A - Gear defect detection method and system based on computer vision - Google Patents

Gear defect detection method and system based on computer vision Download PDF

Info

Publication number
CN114723701A
CN114723701A CN202210346775.9A CN202210346775A CN114723701A CN 114723701 A CN114723701 A CN 114723701A CN 202210346775 A CN202210346775 A CN 202210346775A CN 114723701 A CN114723701 A CN 114723701A
Authority
CN
China
Prior art keywords
pixel points
gray
area
shadow
shadow area
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.)
Granted
Application number
CN202210346775.9A
Other languages
Chinese (zh)
Other versions
CN114723701B (en
Inventor
伏跃文
谢璐璐
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xiamen Lixing Automation Co ltd
Original Assignee
Nantong Boying Machinery Casting Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nantong Boying Machinery Casting Co ltd filed Critical Nantong Boying Machinery Casting Co ltd
Priority to CN202210346775.9A priority Critical patent/CN114723701B/en
Publication of CN114723701A publication Critical patent/CN114723701A/en
Application granted granted Critical
Publication of CN114723701B publication Critical patent/CN114723701B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Geometry (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The invention relates to the technical field of defect detection and image processing, in particular to a gear defect detection method and system based on computer vision. The method comprises the following steps: obtaining a light source angle adjusting objective function according to the area of the tooth space region, the area of each highlight region, and the average width and variance of the shadow region; adjusting the light source according to the light source angle adjusting target function, and obtaining an optimal tooth space gray image when the target function obtains a minimum value; obtaining suspected crack pixel points in the optimal tooth space gray level image and screening; classifying the pixel points of the shadow area by using suspected crack pixel points and different gray gradient thresholds; and enhancing various pixel points and other pixel points in the shadow area to different degrees, obtaining the contrast between various pixel points in the shadow area and other pixel points in the shadow area after enhancement, and judging whether the pixel points are crack pixel points or not. The method improves the detection efficiency and accuracy of the shadow area cracks in the tooth socket image.

Description

Gear defect detection method and system based on computer vision
Technical Field
The invention relates to the technical field of defect detection and image processing, in particular to a gear defect detection method and system based on computer vision.
Background
Due to the work of the gear or as the service time increases, certain defects, such as cracks, appear on the surface of the gear, and the defects can cause certain damage to the service of the machine. In the traditional gear defect detection process, nondestructive detection methods such as magnetic powder detection or liquid permeation detection are used for detecting the surface cracks of the gear, however, the accuracy of the detection result of the traditional mode depends on the capability of an operator, so the detection accuracy is uncontrollable. With the development of computer vision technology, in the prior art, a CCD camera is used for acquiring a gear surface image, an edge detection algorithm is used for acquiring whether defects exist in the gear surface, and the area, length, angle and number in an image target feature are compared with a preset tolerance to determine whether the gear has defects.
However, the problems in the prior art are that: most methods aim at the surface crack defect detection of the gear, the detection steps are complex, and almost no algorithm is used for detecting the cracks of the tooth space regions between teeth. However, the crack detection of the tooth space area is also an essential link in the gear defect detection process, and severe tooth space cracks may cause tooth breakage. When cracks exist between teeth, the existing detection algorithm cannot have good detection precision.
Disclosure of Invention
In order to solve the above technical problems, an object of the present invention is to provide a method and a system for detecting gear defects based on computer vision, wherein the adopted technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a gear defect detection method based on computer vision, including: obtaining a tooth space gray level image of a tooth space area, wherein the tooth space gray level image comprises a gear and a shadow area at a tooth root; dividing pixel points of the tooth socket gray image into highlight pixel points and shadow pixel points according to a preset gray threshold; clustering the highlight pixel points to obtain a plurality of highlight areas and areas thereof;
performing edge detection on the tooth space gray level image to obtain a tooth line of the gear and an edge line of a shadow area; obtaining the shortest distance between the tooth lines and the pixel points of the edge lines of the shadow area, taking the mean value of the shortest distance as the average width of the shadow area, and obtaining the variance of the width; obtaining a light source angle adjustment target function according to the area of a tooth socket region, the area of each highlight region, and the average width and variance of a shadow region in the tooth socket gray level image; adjusting the light source according to the light source angle adjusting target function, and obtaining an optimal tooth socket gray image when the target function obtains a minimum value; based on highlight pixel points which do not belong to the highlight area in the optimal tooth space gray level image, selecting a preset number of pixel points with large difference degree with the neighbor pixel points as suspected crack pixel points;
classifying the pixel points of the shadow area by utilizing a preset number of suspected crack pixel points and different gray gradient thresholds; according to the gray gradient threshold, enhancing the same type of pixel points and other pixel points corresponding to the gray gradient threshold to different degrees; and obtaining the contrast between various pixel points and other pixel points in the enhanced shadow area, and judging whether the pixel points of the corresponding category are crack pixel points or not.
Preferably, the central point of the tooth socket gray level image is taken as an initial clustering central point, wherein the clustering radius is a preset radius, the clustering density is a preset density, and only highlight pixel points are arranged in a clustering circle in the clustering process; in the subsequent clustering process, stopping clustering until highlight pixel points do not appear in the clustering radiuses corresponding to all clustering centers to obtain a plurality of highlight areas; because the shadow area may have cracks, part of the highlight pixels at the boundary of the shadow area do not meet the clustering condition, and the part of the highlight pixels are suspected crack pixels.
Preferably, the light source angle adjustment objective function is obtained by summing the difference between the area of the gullet region and the sum of the areas of the plurality of highlight regions and the width mean and variance of the shadow region.
Preferably, the different gray gradient thresholds specifically include: setting an initial gray gradient threshold, and updating the initial gray gradient threshold according to the gray gradient values of the pixel points of the shadow area and the suspected crack pixel points; arranging the initial gray gradient threshold value and the updated gray gradient threshold value according to an ascending order; and sequentially obtaining an initial gray gradient threshold as a first threshold, and obtaining a gray gradient threshold as a second threshold by second updating until all pixel points in the shadow area participate in the classification of gray gradients, and stopping updating the initial gray gradient threshold.
Preferably, a suspected crack pixel point with the maximum gradient with the neighborhood pixel point is selected as a starting point, the gray gradient between the pixel point in the neighborhood and the suspected pixel point is obtained, and the pixel points smaller than the first threshold are the same type of pixel points; moving the neighborhood of the suspected crack pixel point to the shadow area, and taking the pixel point with the gray gradient smaller than the first threshold value in the neighborhood as the next neighborhood center pixel point after entering the shadow area; classifying the pixel points in the shadow area which do not meet the first gray threshold value by using a second threshold value; and continuously selecting the gray gradient threshold according to the sequence of the preset gray gradient threshold to classify the pixel points in the shadow area, and stopping classification until the pixel points in the shadow area all participate in gray gradient classification.
Preferably, before enhancing the same type of pixel points and other pixel points in the shadow region corresponding to the gray gradient threshold value in different degrees according to the gray gradient threshold value, the method further includes establishing an image enhancement model, specifically:
Z＝MvI+(1-Mv)I′
wherein Z represents the enhanced gullet gray level image; mVExpressing an enhancement coefficient corresponding to the V-th gray gradient threshold after normalization of each gray gradient threshold; i represents the pixel point of the same type of shadow region corresponding to the V-th gray gradient threshold; and I' represents other pixel points of the shadow region except the pixel point of the same type of shadow region corresponding to the V-th gray gradient threshold value.
Preferably, the contrast between the pixel point of the same kind of shadow region and other pixel points of the shadow region is obtained, if the contrast is greater than a preset contrast threshold value, the pixel point is a crack pixel point, and the position of the crack pixel point is marked; and similarly, judging whether the pixel points of other corresponding category shadow areas are crack pixel points or not.
In a second aspect, another embodiment of the present invention provides a computer-vision gear defect detection system, comprising:
the suspected crack pixel point acquisition module is used for acquiring a tooth space gray image of a tooth space area, wherein the tooth space gray image comprises a gear and a shadow area at a tooth root; dividing pixel points of the tooth space gray image into highlight pixel points and shadow pixel points according to a preset gray threshold value; clustering the highlight pixel points to obtain a plurality of highlight areas and areas thereof;
the optimal tooth space gray level image acquisition module is used for carrying out edge detection on the tooth space gray level image to obtain the tooth line of the gear and the edge line of a shadow area; obtaining the shortest distance between the tooth lines and the pixel points of the edge lines of the shadow area, taking the mean value of the shortest distance as the average width of the shadow area, and obtaining the variance of the width of the shadow area; obtaining a light source angle adjustment target function according to the area of a tooth socket region, the area of each highlight region, and the average width and variance of a shadow region in the tooth socket gray level image; adjusting the light source according to the light source angle adjusting target function, and obtaining an optimal tooth space gray image when the target function obtains a minimum value; selecting a preset number of high-brightness pixel points which are different from the adjacent pixel points to be suspected crack pixel points based on the high-brightness pixel points which do not belong to the high-brightness area in the optimal tooth space gray level image;
the crack detection module is used for classifying the pixel points in the shadow area by utilizing a preset number of suspected crack pixel points and different gray gradient thresholds; enhancing the similar pixel points and other pixel points corresponding to the gray gradient threshold value to different degrees according to the gray gradient threshold value; and obtaining the contrast between various pixel points and other pixel points in the enhanced shadow area, and judging whether the pixel points of the corresponding category are crack pixel points or not.
Preferably, the suspected crack pixel point obtaining module is further configured to use a center point of the tooth space grayscale image as an initial clustering center point, where a clustering radius is a preset radius, a clustering density is a preset density, and only highlight pixel points are located in a clustering circle in a clustering process; in the subsequent clustering process, stopping clustering until highlight pixel points do not appear in the clustering radiuses corresponding to all clustering centers to obtain a plurality of highlight areas; because the shadow area may have cracks, part of the highlight pixels at the boundary of the shadow area do not meet the clustering condition, and the part of the highlight pixels are suspected crack pixels.
Preferably, the optimal tooth space grayscale image obtaining module is further configured to obtain a light source angle adjustment target function, specifically: and summing the difference value of the area of the tooth space region and the sum of the areas of the plurality of highlight regions and the width mean value and the variance of the shadow region to obtain a light source angle adjustment target function.
The embodiment of the invention at least has the following beneficial effects: based on the fact that the light source angle is adjusted through the characteristics of the highlight area and the width of the shadow area at the tooth root, compared with the prior art, the method has the advantages that the area of the highlight area in each tooth socket area in the tooth socket gray scale image can be increased as much as possible, the influence of the shadow at the tooth root is reduced, the crack detection difficulty caused by the shadow generated at the tooth root of the tooth socket area is reduced, and the overall detection efficiency and accuracy are improved; based on the fact that the suspected crack pixel points at the junction of the highlight area and the shadow area at the tooth trace are used as crack initial points to conduct gray gradient threshold segmentation, the pixel points of the shadow area are classified to obtain all segmentation areas which are possibly cracks in the shadow area at the tooth trace, the pixel points of the segmentation areas and other pixel points of the shadow area are enhanced to different degrees, and then crack detection is conducted.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for detecting gear defects based on machine vision.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description will be given of a gear defect detecting method and system based on computer vision according to the present invention with reference to the accompanying drawings and preferred embodiments, and the detailed description thereof, the structure, the features and the effects thereof. In the following description, the different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
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 following describes a specific scheme of the gear defect detection method based on computer vision in detail with reference to the accompanying drawings.
The main application scenarios of the invention are as follows: the method comprises the steps that in a mechanical gear tooth socket detection scene, an adjustable light source and a high-resolution camera are used for collecting images of tooth sockets, the angle of the light source is adjusted in a self-adaptive mode, a single tooth socket image sequence is obtained, and the camera visual angle is used for shooting for a front-view visual angle. The invention only researches and explains the crack defect at the tooth root in the tooth groove area between the teeth without considering the condition of oil stain on the gear
Example 1
The following specifically describes a specific scheme of the gear defect detection method based on computer vision, which is provided by the invention, with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for detecting gear defects based on computer vision according to an embodiment of the present invention is shown, where the method includes the following steps:
the method comprises the following steps: obtaining a tooth socket gray image and the area of a tooth socket area in the image, wherein the image comprises a gear and a shadow area at a tooth root; dividing pixel points of the tooth space gray image into highlight pixel points and shadow pixel points according to a preset gray threshold value; and clustering the highlight pixel points to obtain a plurality of highlight areas and areas thereof, wherein the highlight pixel points which do not belong to the highlight areas are suspected crack pixel points.
Before the above operation, an image of a gear tooth groove needs to be acquired and preprocessed, specifically: and acquiring a tooth socket RGB image, carrying out denoising treatment, and avoiding influencing subsequent tooth socket defect detection when the tooth socket image obtained after denoising is subjected to crack detection. The method comprises the steps of collecting an RGB (red, green and blue) image of a gear tooth socket (between teeth) through a camera, carrying out graying on the tooth socket image, carrying out average graying on the graying to obtain a tooth socket grayscale image, carrying out median filtering denoising on the grayscale image, and removing salt and pepper noise possibly existing in the image.
Obtaining highlight pixel points in the tooth socket gray image: performing threshold segmentation on the tooth space gray level image, taking the gray level characteristic value of a pixel point on the tooth space gray level image as a brightness characteristic due to the absence of noise and oil pollution interference, setting a preset gray level threshold value N as 200, and processing the gray level value G in a tooth space area in the tooth space gray level imagei>And all the N pixel points are regarded as highlight pixel points, and the pixel points smaller than the preset gray threshold are shadow pixel points.
Clustering the highlight pixel points in the gullet area, wherein the clustering algorithm adopts a DBSCAN algorithm, the central point of the gullet gray level image is used as an initial clustering central point, because the light receiving surface of the gullet gray level image central area is the largest, a clustering radius is set, preferably, the preset clustering radius r is 3, all the highlight pixel points in a circle with the radius of 3 are clustered together to form a highlight area, other pixel points are required to be ensured not to be contained in the clustering circle in the clustering process, the clustering density in the clustering circle is set, and preferably, the preset clustering density is 1; then, selecting edge pixel points of the clustering circle region as clustering center points to perform subsequent clustering until no highlight pixel points appear in the clustering radius, and obtaining a highlight region corresponding to the cluster of the highlight pixel points; if the tooth space gray level image still has highlight pixel points which do not participate in clustering, any highlight pixel point is selected as a clustering center point to continue to perform DBSCAN clustering with the clustering radius of 3 until all clustering centers perform clustering, the highlight pixel points do not appear in the clustering radius, and the remaining highlight pixel points which do not belong to highlight areas are used as suspected cracksThe pattern pixel points are used for detecting cracks, so that a plurality of highlight areas are obtained; obtaining the area S of the gullet region and the area S of the highlight region in the gullet gray level imagekAnd k denotes a kth highlight region.
Step two: obtaining edge lines of a shadow area, wherein one edge line is a tooth line of a gear; obtaining the shortest distance between the tooth line and the pixel point of the other edge line of the shadow area, taking the mean value of the shortest distance as the average width of the shadow area, and obtaining the variance of the width; obtaining a light source angle adjusting objective function according to the area of the tooth space region, the area of each highlight region, and the average width and variance of the shadow region; adjusting the light source according to the light source angle adjusting target function, and obtaining an optimal tooth space gray image when the target function obtains a minimum value; and selecting a predetermined number of suspected crack pixel points in the optimal tooth space gray level image with large difference degree with the adjacent pixel points.
Obtaining a shadow area at a tooth root tooth trace in the tooth space gray level image, and obtaining corresponding characteristics of the shadow area, wherein the specific process is as follows: edge detection is carried out on the tooth space gray level image through a Canny edge detection algorithm, edge lines of shadow areas at tooth roots in the tooth space gray level image are obtained, one edge line is a tooth line of a gear, shadow possibly exists in partial areas at the tooth roots due to the light source angle, and the other edge line of the tooth line and the other edge line of the shadow areas are two edge lines of the shadow areas; because the angle of the light source is uncertain, the shape of a connected domain formed by the tooth line and the other edge line of the shadow area can be irregular, namely the shape of the shadow area can be irregular; obtaining the widths W of different positions of the shadow region through the distance between the pixel points on the same horizontal plane on the tooth line and the other edge line of the shadow region, namely the shortest distance between the pixel points on the tooth line and the other edge line of the shadow region, and obtaining the width W of the shadow region at each edge pixel pointjRepresenting the width at the jth edge pixel point, the mean value of the width of the connected component, i.e., the shaded area, is μWSum variance
Figure BDA0003576776330000061
As a shadow zoneAnd (4) evaluating indexes of domain features, wherein the mean value represents the average width of the shadow region, and the variance is used for representing whether the shape of the whole shadow region is regular or not.
Setting a light source angle adjusting objective function through the characteristics of the tooth space area and the characteristics of the shadow area in the tooth space gray level image, wherein the light source angle adjusting objective function is used for adjusting the angle of a light source, and for the tooth space gray level image used for detecting cracks at the tooth space between teeth, the optimal solution of the light source angle during camera shooting is as follows: the highlight area in the tooth space area is as large as possible, the width of the shadow area at the tooth root is as small as possible, and the shape of the edge of the shadow area is as close to regular as possible, namely close to the edge of a rectangle and consistent with the vertical direction of an image as far as possible; the light source angle adjustment objective function is specifically as follows:
Figure BDA0003576776330000062
wherein F represents a light source angle adjustment target function, S' represents the whole area of the tooth space region, and SkDenotes the area of the kth highlight region, μWThe average width of the shaded area is,
Figure BDA0003576776330000063
representing the width variance of the shaded area.
And adjusting the angle of the dynamic light source to obtain an optimal solution, namely obtaining the minimum value, of the light source angle adjustment target function, obtaining a tooth space image under the light source at the moment, and obtaining an optimal tooth space gray level image for subsequent crack detection at the tooth trace.
And crack detection is carried out by utilizing the optimal tooth space gray level image, so that accurate crack detection of a shadow area at a tooth trace can be realized. The reason for generating the suspected crack pixel points is that the shadow area has cracks, and the general growth distribution rules of the cracks are irregular, so that crack growth directions in multiple random directions can be generated, and the irregular crack growth causes the intersecting edge of the shadow area and the highlight area at the tooth trace to be unsmooth, so that in the clustering process, part of the highlight pixel points cannot meet the clustering condition, do not participate in clustering, and serve as the suspected crack pixel points. And when the optimal tooth socket gray level image is obtained, the area of the shadow area at the tooth trace is small enough, and by combining the irregularity of crack growth, if cracks exist in the shadow area, suspected crack pixel points exist at the boundary of the highlight area and the shadow area.
Screening the suspected crack pixel points according to the difference degree between the suspected crack pixel points in the optimal tooth space gray level image and the pixel points in the neighborhood, wherein the screening method specifically comprises the following steps: the method comprises the steps of obtaining gray gradients of a suspected crack pixel point and other pixel points in the neighborhood, obtaining a gray gradient mean value H of the suspected crack pixel point and the neighborhood pixel point, preferably setting the size of the neighborhood to be 8 neighborhoods, sorting the suspected crack pixel points according to the gray gradient mean value, selecting the suspected crack pixel points corresponding to K largest gray gradient mean values to detect, and if the suspected crack pixel points are caused by cracks in a shadow area, greatly changing the gray values of the suspected crack pixel points and other pixel points in the neighborhood, so that the gray gradient is large.
Step three: setting an initial gray gradient threshold value and continuously updating to obtain different gray gradient threshold values; classifying the pixel points of the shadow area by utilizing a preset number of suspected crack pixel points and different gray gradient thresholds; enhancing the same type of pixel points and other pixel points in the shadow area corresponding to the gray gradient threshold value to different degrees according to the gray gradient threshold value; and obtaining the contrast between the pixel points in the various enhanced shadow areas and other pixel points in the shadow areas, and judging whether the pixel points are crack pixel points or not.
Firstly, setting an initial gray gradient threshold, and updating the initial gray gradient threshold according to the gray gradient values of pixel points of a shadow area and suspected crack pixel points; arranging the initial gray gradient threshold value and the updated gray gradient threshold value according to an ascending order; sequentially obtaining an initial gray gradient threshold as a first threshold, and a second updated gray gradient threshold as a second threshold until all pixel points in the shadow region participate in the classification of gray gradients, and stopping updating the initial gray gradient threshold
Further, selecting the selected maximum gray level gradient mean value in the optimal gray level imageThe suspected crack pixel point is taken as an initial point, wherein the suspected crack pixel point in the optimal gray level image is marked as QqThe suspected crack pixel point may be caused by the fact that the crack growth of the shadow area at the tooth trace extends to the highlight area of the tooth space gray level image. Will initial point Q0The gray value of the gray scale and the pixel points in the neighborhood are subjected to gray scale gradient calculation, and an initial gray scale gradient threshold value Y is set1And (3) specifically updating according to the difference degree of the gray values of the suspected crack pixel points and the pixel points in the tooth root shadow area, and selecting the pixel points with the gray gradient smaller than a first threshold value as the pixel points of the same gray class, wherein the pixel points are classified as first-class pixel points. The neighborhood pixel points refer to: clustering is carried out from the suspected crack pixel points to the pixel points in the shadow area at the tooth root, and the purpose is to obtain the positions of the pixel points of the shadow area at the tooth trace, which belong to the cracks.
Then, let the initial point Q continue0Carrying out gray gradient calculation with the pixel points in the next 8-neighborhood range, wherein the pixel points in the 8-neighborhood range are located in the shadow region at the edge of the shadow region at the tooth trace due to the suspected crack pixel points, and when the first threshold Y of the gray gradient is not met1When the pixel points in the shadow area are all based on the initial point Q, the pixel points in the shadow area continue to participate in the subsequent gray gradient calculation as the unclassified pixel points, the pixel points which are classified as the first threshold value of the gray gradient do not participate in the subsequent clustering any more, then the neighborhood pixel points which meet the first threshold value are selected as the central pixel points, the pixel points in the corresponding 8 neighborhood range are selected for continuing the gray gradient judgment, and the gray gradients of the pixel points in the shadow area are all based on the initial point Q0And calculating, classifying the pixels meeting the first threshold of the gray gradient into a first class until the pixels which are adjacent in position in the shadow area and have the gray values close to each other and meet the first threshold are completely found out, and stopping classifying the pixels in the shadow area by using the first threshold.
Using a first threshold value Y1In the process of selecting the pixel points belonging to the first class in the shadow area, if the pixel points which do not meet the gray gradient first threshold exist, the initial gray gradient threshold is updated to obtain a second threshold Y25, from the initial according to the second threshold of the grey gradientPoint Q0And selecting the pixel points which do not meet the first threshold value of the gray gradient from the pixel points in each neighborhood to carry out gray gradient calculation, and obtaining the pixel point positions of which the shadow areas at the tooth lines meet the second threshold value of the gray gradient.
Then, for the initial point Q satisfying the second threshold value of the gray gradient in the shadow region at the tooth trace0And (4) judging the gray gradient of the 8-neighborhood pixels, and classifying the pixels meeting the second threshold of the gray gradient into a second class. And continuously judging until all pixel points in the shadow area at the tooth trace are traversed, and finishing the division of pixel point areas which are adjacent in space and have similar gray values.
In the process of traversing by using the second threshold, if pixel points which do not meet the gray gradient first threshold and the gray gradient second threshold still exist, the initial gray gradient is continuously updated to obtain a third threshold Y3Judging the pixel points in the shadow area which do not meet the first threshold value and the second threshold value until all the pixel points in the shadow area participate in gray gradient classification; the number of the gray gradient thresholds can be regarded as the number of times for classification, and under normal conditions, the types of the gray pixel points in the shadow region at the tooth trace are only the pixel points in the normal region and the pixel points in the crack region, so the updating number of the initial gray gradient thresholds is not very large and is generally 2, namely only two gradient thresholds are needed; the pixel points in the shadow area at the tooth trace are classified, and then in the process of dividing the area, the distributed scattered pixel points which are the same or different with the classified pixel points may occur, and the distributed scattered pixel points can be ignored. After the pixels in the shadow area are classified, the pixel areas which are adjacent in space and similar in gray value and belong to the same type are classified.
The positions of the suspected crack pixel points are located at the boundary of the highlight area and the shadow area at the tooth trace, so that the suspected crack pixel points also belong to the highlight area. The gray value of a suspected crack pixel point is inevitably different from the gray value of a crack pixel point in a shadow area in an obvious gradient manner, and the gray values of the pixel point participating in classification in the shadow area and other pixel points in the shadow area are also different in the same way, but the difference between the pixel point participating in classification in the shadow area and the pixel point not subjected to classification in the shadow area is possibly not obvious, so that the pixel point subjected to classification and the pixel point not subjected to classification are enhanced in different degrees; by the idea of a dark channel prior enhancement algorithm, an image enhancement model is constructed as follows:
Z＝MvI+(1-Mv)I′
wherein Z represents the enhanced gullet gray level image; m is a group ofVExpressing an enhancement coefficient corresponding to the V-th gray gradient threshold after normalization of each gray gradient threshold; i represents the same type of pixel points in a shadow region corresponding to the V-th gray gradient threshold; and I' represents other pixel points except the same type of pixel points in the shadow region corresponding to the V-th gray gradient threshold value. Enhancing according to each gray gradient threshold, performing different degrees of enhancement on pixel points in shadow region categories and unclassified pixel points once a gray gradient threshold is utilized for classification, obtaining an enhanced tooth space gray image, obtaining the enhanced tooth space gray image corresponding to different pixel points of each category of shadow region, and obtaining an enhanced image sequence [ Z ] of the enhanced image sequence1,Z2,…,Zn]。
And then, detecting the image of the shadow area at the tooth root according to the enhanced image sequence, and acquiring the contrast C of the shadow area of the enhanced image through a gray level co-occurrence matrix, wherein the value range is (0, 1), the contrast reflects the local change of pixel points of the shadow area in the image, so as to obtain the depth information of the texture groove, and the deeper the texture groove, the higher the contrast and the smaller the contrast. And obtaining pixel points with high contrast according to the contrast C information, marking the pixel points as crack pixel points, setting a contrast threshold value B to be 0.8, marking the pixel points with the contrast C greater than B as crack pixel points, analyzing the principal component of Top 2 at the positions of the crack pixel points by using a principal component analysis algorithm, and completing the crack detection of the tooth trace region by using a PCA algorithm.
Example 2
The present embodiment provides a system embodiment. A computer vision based gear defect detection system, the system comprising: the crack-like pixel point acquisition module is used for acquiring a tooth space gray image of a tooth space area, wherein the tooth space gray image comprises a gear and a shadow area at a tooth root; dividing pixel points of the tooth space gray image into highlight pixel points and shadow pixel points according to a preset gray threshold value; clustering the highlight pixel points to obtain a plurality of highlight areas and areas thereof;
the optimal tooth space gray level image acquisition module is used for carrying out edge detection on the tooth space gray level image to obtain tooth lines of the gear and edge lines of a shadow area; obtaining the shortest distance between the tooth lines and the pixel points of the edge lines of the shadow area, taking the mean value of the shortest distance as the average width of the shadow area, and obtaining the variance of the width; obtaining a light source angle adjustment target function according to the area of a tooth socket region, the area of each highlight region, and the average width and variance of a shadow region in the tooth socket gray level image; adjusting the light source according to the light source angle adjusting target function, and obtaining an optimal tooth socket gray image when the target function obtains a minimum value; selecting a preset number of high-brightness pixel points which are different from the adjacent pixel points to be suspected crack pixel points based on the high-brightness pixel points which do not belong to the high-brightness area in the optimal tooth space gray level image;
the crack detection module is used for classifying the pixel points in the shadow area by utilizing a preset number of suspected crack pixel points and different gray gradient thresholds; enhancing the similar pixel points and other pixel points corresponding to the gray gradient threshold value to different degrees according to the gray gradient threshold value; and obtaining the contrast between various pixel points and other pixel points in the enhanced shadow area, and judging whether the pixel points of the corresponding category are crack pixel points or not.
The suspected crack pixel point acquisition module is also used for taking a central point of the tooth socket gray image as an initial clustering central point, wherein the clustering radius is a preset radius, the clustering density is a preset density, and only highlight pixel points exist in a clustering circle in the clustering process; in the subsequent clustering process, stopping clustering until highlight pixel points do not appear in the clustering radiuses corresponding to all clustering centers to obtain a plurality of highlight areas; because the shadow area may have cracks, part of the highlight pixels at the boundary of the shadow area do not meet the clustering condition, and the part of the highlight pixels are suspected crack pixels.
The optimal tooth socket gray scale image acquisition module is further used for acquiring a light source angle adjustment target function, and specifically comprises the following steps: and summing the difference value of the area of the tooth space region and the sum of the areas of the plurality of highlight regions and the width mean value and the variance of the shadow region to obtain a light source angle adjustment target function.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (10)

1. A gear defect detection method based on computer vision is characterized by comprising the following steps: obtaining a tooth space gray level image of a tooth space area, wherein the tooth space gray level image comprises a gear and a shadow area at a tooth root; dividing pixel points of the tooth space gray image into highlight pixel points and shadow pixel points according to a preset gray threshold value; clustering the highlight pixel points to obtain a plurality of highlight areas and areas thereof;
performing edge detection on the tooth space gray level image to obtain a tooth line of the gear and an edge line of a shadow area; obtaining the shortest distance between the tooth lines and the pixel points of the edge lines of the shadow area, taking the mean value of the shortest distance as the average width of the shadow area, and obtaining the variance of the width; obtaining a light source angle adjustment target function according to the area of a tooth socket region, the area of each highlight region, and the average width and variance of a shadow region in the tooth socket gray level image; adjusting the light source according to the light source angle adjusting target function, and obtaining an optimal tooth space gray image when the target function obtains a minimum value; selecting a preset number of high-brightness pixel points which are different from the adjacent pixel points to be suspected crack pixel points based on the high-brightness pixel points which do not belong to the high-brightness area in the optimal tooth space gray level image;
classifying the pixel points of the shadow area by utilizing a preset number of suspected crack pixel points and different gray gradient thresholds; enhancing the similar pixel points and other pixel points corresponding to the gray gradient threshold value to different degrees according to the gray gradient threshold value; and obtaining the contrast between various pixel points and other pixel points in the enhanced shadow area, and judging whether the pixel points of the corresponding category are crack pixel points or not.
2. The computer vision-based gear defect detection method according to claim 1, wherein the clustering highlight pixel points specifically comprises: taking the central point of the tooth socket gray image as an initial clustering central point, wherein the clustering radius is a preset radius, the clustering density is a preset density, and only highlight pixel points exist in a clustering circle in the clustering process; in the subsequent clustering process, stopping clustering until highlight pixel points do not appear in the clustering radiuses corresponding to all clustering centers to obtain a plurality of highlight areas; because the shadow area may have cracks, part of the highlight pixels at the boundary of the shadow area do not meet the clustering condition, and the part of the highlight pixels are suspected crack pixels.
3. The computer vision-based gear defect detection method according to claim 1, wherein the light source angle adjustment objective function is specifically: and summing the difference value of the area of the tooth space region and the sum of the areas of the plurality of highlight regions and the width mean value and the variance of the shadow region to obtain a light source angle adjustment target function.
4. The computer vision-based gear defect detection method according to claim 1, wherein the different gray gradient thresholds specifically include: setting an initial gray gradient threshold, and updating the initial gray gradient threshold according to the gray gradient values of the pixel points of the shadow area and the suspected crack pixel points; arranging the initial gray gradient threshold value and the updated gray gradient threshold value according to an ascending order; and sequentially obtaining an initial gray gradient threshold as a first threshold, and obtaining a gray gradient threshold as a second threshold by second updating until all pixel points in the shadow area participate in the classification of gray gradients, and stopping updating the initial gray gradient threshold.
5. The computer vision-based gear defect detection method of claim 1, wherein classifying the pixels of the shadow region using a predetermined number of suspected crack pixels and different gray gradient thresholds comprises: selecting a suspected crack pixel point with the maximum gradient with the neighborhood pixel point as a starting point, obtaining the gray gradient of the pixel point in the neighborhood and the suspected pixel point, wherein the pixel point smaller than a first threshold value is the same type of pixel point; moving the neighborhood of the suspected crack pixel point to the shadow area, and taking the pixel point with the gray gradient smaller than the first threshold value in the neighborhood as the next neighborhood center pixel point after entering the shadow area; classifying the pixel points of the shadow area which do not meet the first gray threshold by using a second threshold; and continuously selecting the gray gradient threshold according to the sequence of the preset gray gradient threshold to classify the pixel points in the shadow area, and stopping classification until the pixel points in the shadow area all participate in gray gradient classification.
6. The method for detecting the gear defect based on the computer vision according to claim 1, wherein before enhancing the same type of pixel points and other pixel points in the shadow region corresponding to the gray gradient threshold value to different degrees according to the gray gradient threshold value, an image enhancement model is established, specifically:
Z＝MvI+(1-Mv)I′
wherein Z represents the enhanced gullet gray level image; mVExpressing an enhancement coefficient corresponding to the V-th gray gradient threshold after normalization of each gray gradient threshold; i represents the pixel point of the same type of shadow region corresponding to the V-th gray gradient threshold; i is′And expressing other pixel points of the shadow region except the pixel point of the same type of shadow region corresponding to the V-th gray gradient threshold value.
7. The method for detecting the gear defect based on the computer vision as claimed in claim 1, wherein the step of obtaining the contrast between the pixel point in each kind of the enhanced shadow area and other pixel points in the shadow area and judging whether the pixel point is a crack pixel point comprises the steps of: obtaining the contrast ratio of the pixel point of the similar shadow area to other pixel points of the shadow area, if the contrast ratio is greater than a preset contrast ratio threshold value, marking the position of the pixel point as a crack pixel point; and similarly, judging whether the pixel points of other various shadow areas are crack pixel points or not.
8. A computer vision based gear defect detection system, comprising: the suspected crack pixel point acquisition module is used for acquiring a tooth space gray image of a tooth space area, wherein the tooth space gray image comprises a gear and a shadow area at a tooth root; dividing pixel points of the tooth space gray image into highlight pixel points and shadow pixel points according to a preset gray threshold value; clustering the highlight pixel points to obtain a plurality of highlight areas and areas thereof;
the optimal tooth space gray level image acquisition module is used for carrying out edge detection on the tooth space gray level image to obtain the tooth line of the gear and the edge line of a shadow area; obtaining the shortest distance between the tooth lines and the pixel points of the edge lines of the shadow area, taking the mean value of the shortest distance as the average width of the shadow area, and obtaining the variance of the width of the shadow area; obtaining a light source angle adjustment target function according to the area of a tooth socket region, the area of each highlight region, and the average width and variance of a shadow region in the tooth socket gray level image; adjusting the light source according to the light source angle adjusting target function, and obtaining an optimal tooth space gray image when the target function obtains a minimum value; based on highlight pixel points which do not belong to the highlight area in the optimal tooth space gray level image, selecting a preset number of pixel points with large difference degree with the neighbor pixel points as suspected crack pixel points;
the crack detection module is used for classifying the pixel points in the shadow area by utilizing a preset number of suspected crack pixel points and different gray gradient thresholds; enhancing the similar pixel points and other pixel points corresponding to the gray gradient threshold value to different degrees according to the gray gradient threshold value; and obtaining the contrast between various pixel points and other pixel points in the enhanced shadow area, and judging whether the pixel points of the corresponding category are crack pixel points or not.
9. The computer vision-based gear defect detection system of claim 8, wherein the suspected crack pixel point acquisition module is further configured to use a center point of the gullet gray image as an initial clustering center point, wherein a clustering radius is a preset radius, a clustering density is a preset density, and only highlight pixel points are located in a clustering circle during clustering; in the subsequent clustering process, stopping clustering until highlight pixel points do not appear in the clustering radiuses corresponding to all clustering centers to obtain a plurality of highlight areas; because the shadow area may have cracks, part of the highlight pixels at the boundary of the shadow area do not meet the clustering condition, and the part of the highlight pixels are suspected crack pixels.
10. The computer vision-based gear defect detection system of claim 8, wherein the optimal tooth space grayscale image acquisition module is further configured to acquire an acquisition of a light source angle adjustment objective function, specifically: and summing the difference value of the area of the gullet area and the sum of the areas of the plurality of highlight areas and the width mean value and the variance of the shadow area to obtain a light source angle adjustment target function.
CN202210346775.9A 2022-03-31 2022-03-31 Gear defect detection method and system based on computer vision Active CN114723701B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210346775.9A CN114723701B (en) 2022-03-31 2022-03-31 Gear defect detection method and system based on computer vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210346775.9A CN114723701B (en) 2022-03-31 2022-03-31 Gear defect detection method and system based on computer vision

Publications (2)

Publication Number Publication Date
CN114723701A true CN114723701A (en) 2022-07-08
CN114723701B CN114723701B (en) 2023-04-18

Family

ID=82241447

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210346775.9A Active CN114723701B (en) 2022-03-31 2022-03-31 Gear defect detection method and system based on computer vision

Country Status (1)

Country Link
CN (1) CN114723701B (en)

Cited By (74)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114897896A (en) * 2022-07-11 2022-08-12 南通东方雨虹建筑材料有限公司 Building wood defect detection method based on gray level transformation
CN114972343A (en) * 2022-07-29 2022-08-30 山东睿鑫激光科技有限公司 Method for detecting production abnormity of laser welding product
CN114972892A (en) * 2022-07-12 2022-08-30 山东嘉通专用汽车制造有限公司 Automobile brake pad defect classification method based on computer vision
CN114998350A (en) * 2022-08-04 2022-09-02 山东泗水泰和石材有限公司 Stone defect detection method based on image processing
CN114998333A (en) * 2022-08-02 2022-09-02 山东第一医科大学(山东省医学科学院) Computer vision detection method and system for light source characteristics
CN115018834A (en) * 2022-08-08 2022-09-06 山东光岳九州半导体科技有限公司 Semiconductor wafer image alignment method
CN115018833A (en) * 2022-08-05 2022-09-06 山东鲁芯之光半导体制造有限公司 Processing defect detection method of semiconductor device
CN115018828A (en) * 2022-08-03 2022-09-06 深圳市尹泰明电子有限公司 Defect detection method for electronic component
CN115035122A (en) * 2022-08-12 2022-09-09 宁波鑫芯微电子科技有限公司 Artificial intelligence-based integrated circuit wafer surface defect detection method
CN115032202A (en) * 2022-08-10 2022-09-09 山东唐乐生物科技股份有限公司 Method for removing residual impurities of stevioside product
CN115035107A (en) * 2022-08-10 2022-09-09 山东正阳机械股份有限公司 Axle gear working error detection method based on image processing
CN115049670A (en) * 2022-08-16 2022-09-13 南通兴拓精密机械有限公司 Tooth profile defect detection method based on gear
CN115049667A (en) * 2022-08-16 2022-09-13 启东市群鹤机械设备有限公司 Gear defect detection method
CN115063430A (en) * 2022-08-19 2022-09-16 南通金茂防爆电气有限公司 Electric pipeline crack detection method based on image processing
CN115082744A (en) * 2022-08-22 2022-09-20 启东市罗源光伏设备有限公司 Solar energy heat collection efficiency analysis method and system based on artificial intelligence
CN115082445A (en) * 2022-07-25 2022-09-20 山东鲁泰防水科技有限公司 Method for detecting surface defects of building waterproof roll
CN115082462A (en) * 2022-08-22 2022-09-20 山东海鑫达石油机械有限公司 Method and system for detecting appearance quality of fluid conveying pipe
CN115082419A (en) * 2022-07-14 2022-09-20 江苏诺阳家居科技有限公司 Blow-molded luggage production defect detection method
CN115082485A (en) * 2022-08-23 2022-09-20 南通华烨塑料工业有限公司 Method and system for detecting bubble defects on surface of injection molding product
CN115082484A (en) * 2022-08-23 2022-09-20 山东光岳九州半导体科技有限公司 Automatic semiconductor partitioning method based on image processing
CN115115622A (en) * 2022-08-24 2022-09-27 苏州新实达精密电子科技有限公司 Punching press terminal visual detection device
CN115147416A (en) * 2022-09-02 2022-10-04 山东大山不锈钢制品有限公司 Rope disorder detection method and device for rope rewinder and computer equipment
CN115147407A (en) * 2022-08-29 2022-10-04 聊城市博源节能科技有限公司 Bearing quality detection method based on computer vision
CN115170570A (en) * 2022-09-07 2022-10-11 南通睿谷纺织科技有限公司 Fabric fuzzing and pilling detection method based on gray level run-length matrix
CN115222733A (en) * 2022-09-19 2022-10-21 山东金源不锈钢制品有限公司 Metal component surface defect detection method based on image recognition
CN115330878A (en) * 2022-10-18 2022-11-11 山东特联信息科技有限公司 Tank mouth visual positioning method for tank car
CN115345525A (en) * 2022-10-17 2022-11-15 江苏鑫缘医疗科技有限公司 Muscle bandage online production testing system and method based on machine vision
CN115359237A (en) * 2022-10-19 2022-11-18 镭戈斯智能装备江苏有限公司 Gear broken tooth identification method based on pattern identification
CN115359042A (en) * 2022-10-17 2022-11-18 博格达智能装备(南通)有限公司 Defect detection method of wood-plastic new material door based on optical vision
CN115359043A (en) * 2022-10-18 2022-11-18 启东市航新实用技术研究所 Intelligent detection method for foreign matters on PCB surface
CN115375676A (en) * 2022-10-24 2022-11-22 微山三利特不锈钢有限公司 Stainless steel product quality detection method based on image recognition
CN115439474A (en) * 2022-11-07 2022-12-06 山东天意机械股份有限公司 Rapid positioning method for power equipment fault
CN115452845A (en) * 2022-11-14 2022-12-09 深圳市晶台股份有限公司 LED screen surface damage detection method based on machine vision
CN115493843A (en) * 2022-11-18 2022-12-20 聊城市义和轴承配件有限公司 Quality monitoring method and equipment based on bearing retainer
CN115601367A (en) * 2022-12-15 2023-01-13 苏州迈创信息技术有限公司（Cn） LED lamp wick defect detection method
CN115760884A (en) * 2023-01-06 2023-03-07 山东恩信特种车辆制造有限公司 Semitrailer surface welding slag optimization segmentation method based on image processing
CN115797872A (en) * 2023-01-31 2023-03-14 捷易(天津)包装制品有限公司 Machine vision-based packaging defect identification method, system, equipment and medium
CN115880285A (en) * 2023-02-07 2023-03-31 南通南铭电子有限公司 Method for identifying abnormality of lead-out wire of aluminum electrolytic capacitor
CN115880248A (en) * 2022-12-13 2023-03-31 哈尔滨耐是智能科技有限公司 Surface scratch defect identification method and visual detection equipment
CN115984836A (en) * 2023-03-20 2023-04-18 山东杨嘉汽车制造有限公司 Tank opening identification and positioning method for railway tank wagon
CN115994904A (en) * 2023-03-22 2023-04-21 山东万重山电子有限公司 Garment steamer panel production quality detection method based on computer vision
CN116012384A (en) * 2023-03-28 2023-04-25 梁山水泊胶带股份有限公司 Method for detecting surface defects of whole-core flame-retardant conveying belt
CN116071387A (en) * 2023-03-06 2023-05-05 曲阜市巨力铁路轨道工程股份有限公司 Sleeper rail production quality detection method based on machine vision
CN116152749A (en) * 2023-04-20 2023-05-23 青岛义龙包装机械有限公司 Intelligent gear wear monitoring method based on digital twin
CN116385429A (en) * 2023-05-26 2023-07-04 山东中泳电子股份有限公司 Intelligent management method and system for backstroke departure device production line
CN116485832A (en) * 2023-06-25 2023-07-25 山东九思新材料科技有限责任公司 Method for accurately detecting edges of non-uniform fluid impurities for recycling waste silicon wafers
CN116485787A (en) * 2023-06-15 2023-07-25 东莞市立时电子有限公司 Method for detecting appearance defects of data line molding outer die
CN116664572A (en) * 2023-07-31 2023-08-29 聊城市瀚格智能科技有限公司 Rapid highway pavement crack detection method based on image data
CN116664584A (en) * 2023-08-02 2023-08-29 东莞市旺佳五金制品有限公司 Intelligent feedback regulating system for production of thin-wall zinc alloy die casting die
CN116682112A (en) * 2023-07-28 2023-09-01 青岛虹竹生物科技有限公司 Polysaccharide test data storage and digitizing method
CN116704177A (en) * 2023-08-01 2023-09-05 东莞市零越传动科技有限公司 Gear box fault detection method based on image data
CN116740070A (en) * 2023-08-15 2023-09-12 青岛宇通管业有限公司 Plastic pipeline appearance defect detection method based on machine vision
CN116758057A (en) * 2023-08-10 2023-09-15 山东贺铭电气有限公司 Communication equipment defect detection method based on artificial intelligence
CN116843678A (en) * 2023-08-28 2023-10-03 青岛冠宝林活性炭有限公司 Hard carbon electrode production quality detection method
CN116862908A (en) * 2023-09-01 2023-10-10 菏泽学院 Metal gear meshing defect detection method based on image processing
CN116883392A (en) * 2023-09-05 2023-10-13 烟台金丝猴食品科技有限公司 Feeding control method and system based on image processing
CN116883408A (en) * 2023-09-08 2023-10-13 威海坤科流量仪表股份有限公司 Integrating instrument shell defect detection method based on artificial intelligence
CN116883407A (en) * 2023-09-08 2023-10-13 山东省永星食品饮料有限公司 Bottled water impurity detection method based on artificial intelligence
CN116912254A (en) * 2023-09-14 2023-10-20 山东博诚电气有限公司 Cable defect identification method based on data enhancement preprocessing
CN116993696A (en) * 2023-08-03 2023-11-03 苏州阿普奇物联网科技有限公司 Diamond saw blade crack detection method and device based on machine vision
CN117036341A (en) * 2023-10-07 2023-11-10 青岛奥维特智能科技有限公司 Pavement crack detection method based on image processing
CN117079197A (en) * 2023-10-18 2023-11-17 山东诚祥建设集团股份有限公司 Intelligent building site management method and system
CN115100221B (en) * 2022-08-22 2023-11-17 太仓卓高玻璃制品有限公司 Glass defect segmentation method
CN117095004A (en) * 2023-10-20 2023-11-21 金成技术股份有限公司 Excavator walking frame main body welding deformation detection method based on computer vision
CN117197141A (en) * 2023-11-07 2023-12-08 山东远盾网络技术股份有限公司 Method for detecting surface defects of automobile parts
CN117197130A (en) * 2023-11-03 2023-12-08 山东太阳耐磨件有限公司 Driving tooth angle defect identification method based on machine vision
CN117237362A (en) * 2023-11-16 2023-12-15 山东嘉源复合材料有限公司 Vision-based propylene glycol diacetate canning sealing detection method
CN117274241A (en) * 2023-11-17 2023-12-22 四川赢信汇通实业有限公司 Brake drum surface damage detection method and device based on rapid image analysis
CN117474927A (en) * 2023-12-28 2024-01-30 山东太阳耐磨件有限公司 Driving tooth production quality detection method based on artificial intelligence
CN117474891A (en) * 2023-11-10 2024-01-30 艾普零件制造（苏州）股份有限公司 Gear heat treatment defect detection method
CN117788467A (en) * 2024-02-26 2024-03-29 宝鸡百润万德钛业有限公司 Defect image classification method for titanium metal plate
CN118052824A (en) * 2024-04-16 2024-05-17 济宁丰玺生物材料有限公司 Rice hull degradable cutlery box defect detection method
CN118154586A (en) * 2024-05-09 2024-06-07 深圳市冠森高捷电子技术有限公司 Intelligent connector crack defect detection method based on machine vision
CN118052824B (en) * 2024-04-16 2024-06-28 济宁丰玺生物材料有限公司 Rice hull degradable cutlery box defect detection method

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1871506A (en) * 2003-10-21 2006-11-29 大发工业株式会社 Method and device for inspecting surface to be inspected
CN101621607A (en) * 2009-07-24 2010-01-06 天津三星光电子有限公司 Method for eliminating image shades of digital camera
US20130034305A1 (en) * 2011-08-04 2013-02-07 University Of Southern California Image-based crack quantification
CN105374018A (en) * 2015-12-18 2016-03-02 厦门大学 Method for performing area enhancement on image
US20170140516A1 (en) * 2015-11-18 2017-05-18 Kla-Tencor Corporation Systems and Methods for Region-Adaptive Defect Detection
CN106846270A (en) * 2017-01-05 2017-06-13 浙江大华技术股份有限公司 A kind of image edge enhancement method and device
CN107490582A (en) * 2017-09-20 2017-12-19 深圳市晟达机械设计有限公司 A kind of streamline Work Piece Verification System Based
JP2018017639A (en) * 2016-07-29 2018-02-01 株式会社 深見製作所 Surface defect inspection method and surface defect inspection device
CN109754442A (en) * 2019-01-10 2019-05-14 重庆大学 A kind of gear pitting corrosion detection system based on machine vision
CN110426400A (en) * 2019-07-18 2019-11-08 成都新西旺自动化科技有限公司 For touch screen can operating space automatic polisher and its automatic method for polishing
CN111462113A (en) * 2020-04-24 2020-07-28 上海精测半导体技术有限公司 Rechecking method of non-pattern wafer
CN113129304A (en) * 2021-05-18 2021-07-16 郑州轻工业大学 Part detection method based on machine vision
CN113538433A (en) * 2021-09-17 2021-10-22 海门市创睿机械有限公司 Mechanical casting defect detection method and system based on artificial intelligence
CN113935992A (en) * 2021-12-15 2022-01-14 武汉和众成设备工贸有限公司 Image processing-based oil pollution interference resistant gear crack detection method and system

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1871506A (en) * 2003-10-21 2006-11-29 大发工业株式会社 Method and device for inspecting surface to be inspected
CN101621607A (en) * 2009-07-24 2010-01-06 天津三星光电子有限公司 Method for eliminating image shades of digital camera
US20130034305A1 (en) * 2011-08-04 2013-02-07 University Of Southern California Image-based crack quantification
US20170140516A1 (en) * 2015-11-18 2017-05-18 Kla-Tencor Corporation Systems and Methods for Region-Adaptive Defect Detection
CN105374018A (en) * 2015-12-18 2016-03-02 厦门大学 Method for performing area enhancement on image
JP2018017639A (en) * 2016-07-29 2018-02-01 株式会社 深見製作所 Surface defect inspection method and surface defect inspection device
CN106846270A (en) * 2017-01-05 2017-06-13 浙江大华技术股份有限公司 A kind of image edge enhancement method and device
CN107490582A (en) * 2017-09-20 2017-12-19 深圳市晟达机械设计有限公司 A kind of streamline Work Piece Verification System Based
CN109754442A (en) * 2019-01-10 2019-05-14 重庆大学 A kind of gear pitting corrosion detection system based on machine vision
CN110426400A (en) * 2019-07-18 2019-11-08 成都新西旺自动化科技有限公司 For touch screen can operating space automatic polisher and its automatic method for polishing
CN111462113A (en) * 2020-04-24 2020-07-28 上海精测半导体技术有限公司 Rechecking method of non-pattern wafer
CN113129304A (en) * 2021-05-18 2021-07-16 郑州轻工业大学 Part detection method based on machine vision
CN113538433A (en) * 2021-09-17 2021-10-22 海门市创睿机械有限公司 Mechanical casting defect detection method and system based on artificial intelligence
CN113935992A (en) * 2021-12-15 2022-01-14 武汉和众成设备工贸有限公司 Image processing-based oil pollution interference resistant gear crack detection method and system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
JIAXU DUAN; LIN LUO; JINLONG LI; XIAORONG GAO; WEN ZHANG: "Measuring of train wheel surface defect based on linear CCD imaging", 《2016 18TH INTERNATIONAL WHEELSET CONGRESS (IWC)》 *
范王展: "齿轮轴表面裂纹缺陷分析", 《金属加工(热加工)》 *

Cited By (117)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114897896A (en) * 2022-07-11 2022-08-12 南通东方雨虹建筑材料有限公司 Building wood defect detection method based on gray level transformation
CN114897896B (en) * 2022-07-11 2022-09-20 南通东方雨虹建筑材料有限公司 Building wood defect detection method based on gray level transformation
CN114972892A (en) * 2022-07-12 2022-08-30 山东嘉通专用汽车制造有限公司 Automobile brake pad defect classification method based on computer vision
CN114972892B (en) * 2022-07-12 2022-10-21 山东嘉通专用汽车制造有限公司 Automobile brake pad defect classification method based on computer vision
CN115082419A (en) * 2022-07-14 2022-09-20 江苏诺阳家居科技有限公司 Blow-molded luggage production defect detection method
CN115082445A (en) * 2022-07-25 2022-09-20 山东鲁泰防水科技有限公司 Method for detecting surface defects of building waterproof roll
CN114972343A (en) * 2022-07-29 2022-08-30 山东睿鑫激光科技有限公司 Method for detecting production abnormity of laser welding product
CN114972343B (en) * 2022-07-29 2022-10-25 山东睿鑫激光科技有限公司 Method for detecting production abnormity of laser welding product
CN114998333A (en) * 2022-08-02 2022-09-02 山东第一医科大学(山东省医学科学院) Computer vision detection method and system for light source characteristics
CN115018828A (en) * 2022-08-03 2022-09-06 深圳市尹泰明电子有限公司 Defect detection method for electronic component
CN114998350A (en) * 2022-08-04 2022-09-02 山东泗水泰和石材有限公司 Stone defect detection method based on image processing
CN114998350B (en) * 2022-08-04 2022-10-25 山东泗水泰和石材有限公司 Stone defect detection method based on image processing
CN115018833A (en) * 2022-08-05 2022-09-06 山东鲁芯之光半导体制造有限公司 Processing defect detection method of semiconductor device
CN115018834A (en) * 2022-08-08 2022-09-06 山东光岳九州半导体科技有限公司 Semiconductor wafer image alignment method
CN115032202B (en) * 2022-08-10 2022-11-08 山东唐乐生物科技股份有限公司 Method for removing residual impurities of stevioside product
CN115035107A (en) * 2022-08-10 2022-09-09 山东正阳机械股份有限公司 Axle gear working error detection method based on image processing
CN115035107B (en) * 2022-08-10 2022-11-08 山东正阳机械股份有限公司 Axle gear working error detection method based on image processing
CN115032202A (en) * 2022-08-10 2022-09-09 山东唐乐生物科技股份有限公司 Method for removing residual impurities of stevioside product
CN115035122A (en) * 2022-08-12 2022-09-09 宁波鑫芯微电子科技有限公司 Artificial intelligence-based integrated circuit wafer surface defect detection method
CN115049667A (en) * 2022-08-16 2022-09-13 启东市群鹤机械设备有限公司 Gear defect detection method
CN115049670A (en) * 2022-08-16 2022-09-13 南通兴拓精密机械有限公司 Tooth profile defect detection method based on gear
CN115063430A (en) * 2022-08-19 2022-09-16 南通金茂防爆电气有限公司 Electric pipeline crack detection method based on image processing
CN115082462A (en) * 2022-08-22 2022-09-20 山东海鑫达石油机械有限公司 Method and system for detecting appearance quality of fluid conveying pipe
CN115082744A (en) * 2022-08-22 2022-09-20 启东市罗源光伏设备有限公司 Solar energy heat collection efficiency analysis method and system based on artificial intelligence
CN115082462B (en) * 2022-08-22 2022-11-08 山东海鑫达石油机械有限公司 Method and system for detecting appearance quality of fluid conveying pipe
CN115082744B (en) * 2022-08-22 2023-09-08 深圳烁圣数字能源有限公司 Artificial intelligence-based solar heat collection efficiency analysis method and system
CN115100221B (en) * 2022-08-22 2023-11-17 太仓卓高玻璃制品有限公司 Glass defect segmentation method
CN115082484A (en) * 2022-08-23 2022-09-20 山东光岳九州半导体科技有限公司 Automatic semiconductor partitioning method based on image processing
CN115082485A (en) * 2022-08-23 2022-09-20 南通华烨塑料工业有限公司 Method and system for detecting bubble defects on surface of injection molding product
CN115082485B (en) * 2022-08-23 2023-08-29 广东欧达雅包装制品有限公司 Method and system for detecting bubble defects on surface of injection molding product
CN115115622A (en) * 2022-08-24 2022-09-27 苏州新实达精密电子科技有限公司 Punching press terminal visual detection device
CN115147407A (en) * 2022-08-29 2022-10-04 聊城市博源节能科技有限公司 Bearing quality detection method based on computer vision
CN115147416A (en) * 2022-09-02 2022-10-04 山东大山不锈钢制品有限公司 Rope disorder detection method and device for rope rewinder and computer equipment
CN115170570A (en) * 2022-09-07 2022-10-11 南通睿谷纺织科技有限公司 Fabric fuzzing and pilling detection method based on gray level run-length matrix
CN115222733A (en) * 2022-09-19 2022-10-21 山东金源不锈钢制品有限公司 Metal component surface defect detection method based on image recognition
CN115345525A (en) * 2022-10-17 2022-11-15 江苏鑫缘医疗科技有限公司 Muscle bandage online production testing system and method based on machine vision
CN115359042A (en) * 2022-10-17 2022-11-18 博格达智能装备(南通)有限公司 Defect detection method of wood-plastic new material door based on optical vision
CN115330878B (en) * 2022-10-18 2023-01-24 山东特联信息科技有限公司 Tank mouth visual positioning method for tank car
CN115330878A (en) * 2022-10-18 2022-11-11 山东特联信息科技有限公司 Tank mouth visual positioning method for tank car
CN115359043B (en) * 2022-10-18 2023-08-22 浙江晶引电子科技有限公司 Intelligent detection method for foreign matters on PCB (printed circuit board)
CN115359043A (en) * 2022-10-18 2022-11-18 启东市航新实用技术研究所 Intelligent detection method for foreign matters on PCB surface
CN115359237A (en) * 2022-10-19 2022-11-18 镭戈斯智能装备江苏有限公司 Gear broken tooth identification method based on pattern identification
CN115359237B (en) * 2022-10-19 2023-03-24 镭戈斯智能装备江苏有限公司 Gear broken tooth identification method based on pattern identification
CN115375676A (en) * 2022-10-24 2022-11-22 微山三利特不锈钢有限公司 Stainless steel product quality detection method based on image recognition
CN115375676B (en) * 2022-10-24 2023-01-24 微山三利特不锈钢有限公司 Stainless steel product quality detection method based on image recognition
CN115439474B (en) * 2022-11-07 2023-01-24 山东天意机械股份有限公司 Rapid positioning method for power equipment fault
CN115439474A (en) * 2022-11-07 2022-12-06 山东天意机械股份有限公司 Rapid positioning method for power equipment fault
CN115452845B (en) * 2022-11-14 2023-01-13 深圳市晶台股份有限公司 LED screen surface damage detection method based on machine vision
CN115452845A (en) * 2022-11-14 2022-12-09 深圳市晶台股份有限公司 LED screen surface damage detection method based on machine vision
CN115493843B (en) * 2022-11-18 2023-03-10 聊城市义和轴承配件有限公司 Quality monitoring method and equipment based on bearing retainer
CN115493843A (en) * 2022-11-18 2022-12-20 聊城市义和轴承配件有限公司 Quality monitoring method and equipment based on bearing retainer
CN115880248B (en) * 2022-12-13 2024-02-09 哈尔滨耐是智能科技有限公司 Surface scratch defect identification method and visual detection equipment
CN115880248A (en) * 2022-12-13 2023-03-31 哈尔滨耐是智能科技有限公司 Surface scratch defect identification method and visual detection equipment
WO2023134792A3 (en) * 2022-12-15 2023-09-07 苏州迈创信息技术有限公司 Led lamp wick defect detection method
CN115601367A (en) * 2022-12-15 2023-01-13 苏州迈创信息技术有限公司（Cn） LED lamp wick defect detection method
CN115760884A (en) * 2023-01-06 2023-03-07 山东恩信特种车辆制造有限公司 Semitrailer surface welding slag optimization segmentation method based on image processing
CN115760884B (en) * 2023-01-06 2023-04-14 山东恩信特种车辆制造有限公司 Semitrailer surface welding slag optimization segmentation method based on image processing
CN115797872A (en) * 2023-01-31 2023-03-14 捷易(天津)包装制品有限公司 Machine vision-based packaging defect identification method, system, equipment and medium
CN115880285A (en) * 2023-02-07 2023-03-31 南通南铭电子有限公司 Method for identifying abnormality of lead-out wire of aluminum electrolytic capacitor
CN116071387A (en) * 2023-03-06 2023-05-05 曲阜市巨力铁路轨道工程股份有限公司 Sleeper rail production quality detection method based on machine vision
CN115984836A (en) * 2023-03-20 2023-04-18 山东杨嘉汽车制造有限公司 Tank opening identification and positioning method for railway tank wagon
CN115994904A (en) * 2023-03-22 2023-04-21 山东万重山电子有限公司 Garment steamer panel production quality detection method based on computer vision
CN116012384B (en) * 2023-03-28 2023-06-30 梁山水泊胶带股份有限公司 Method for detecting surface defects of whole-core flame-retardant conveying belt
CN116012384A (en) * 2023-03-28 2023-04-25 梁山水泊胶带股份有限公司 Method for detecting surface defects of whole-core flame-retardant conveying belt
CN116152749A (en) * 2023-04-20 2023-05-23 青岛义龙包装机械有限公司 Intelligent gear wear monitoring method based on digital twin
CN116152749B (en) * 2023-04-20 2023-06-23 青岛义龙包装机械有限公司 Intelligent gear wear monitoring method based on digital twin
CN116385429B (en) * 2023-05-26 2023-08-11 山东中泳电子股份有限公司 Intelligent management method and system for backstroke departure device production line
CN116385429A (en) * 2023-05-26 2023-07-04 山东中泳电子股份有限公司 Intelligent management method and system for backstroke departure device production line
CN116485787B (en) * 2023-06-15 2023-08-22 东莞市立时电子有限公司 Method for detecting appearance defects of data line molding outer die
CN116485787A (en) * 2023-06-15 2023-07-25 东莞市立时电子有限公司 Method for detecting appearance defects of data line molding outer die
CN116485832B (en) * 2023-06-25 2023-08-29 山东九思新材料科技有限责任公司 Method for accurately detecting edges of non-uniform fluid impurities for recycling waste silicon wafers
CN116485832A (en) * 2023-06-25 2023-07-25 山东九思新材料科技有限责任公司 Method for accurately detecting edges of non-uniform fluid impurities for recycling waste silicon wafers
CN116682112A (en) * 2023-07-28 2023-09-01 青岛虹竹生物科技有限公司 Polysaccharide test data storage and digitizing method
CN116682112B (en) * 2023-07-28 2023-10-17 青岛虹竹生物科技有限公司 Polysaccharide test data storage and digitizing method
CN116664572B (en) * 2023-07-31 2023-10-13 聊城市瀚格智能科技有限公司 Rapid highway pavement crack detection method based on image data
CN116664572A (en) * 2023-07-31 2023-08-29 聊城市瀚格智能科技有限公司 Rapid highway pavement crack detection method based on image data
CN116704177B (en) * 2023-08-01 2023-11-17 东莞市零越传动科技有限公司 Gear box fault detection method based on image data
CN116704177A (en) * 2023-08-01 2023-09-05 东莞市零越传动科技有限公司 Gear box fault detection method based on image data
CN116664584B (en) * 2023-08-02 2023-11-28 东莞市旺佳五金制品有限公司 Intelligent feedback regulating system for production of thin-wall zinc alloy die casting die
CN116664584A (en) * 2023-08-02 2023-08-29 东莞市旺佳五金制品有限公司 Intelligent feedback regulating system for production of thin-wall zinc alloy die casting die
CN116993696A (en) * 2023-08-03 2023-11-03 苏州阿普奇物联网科技有限公司 Diamond saw blade crack detection method and device based on machine vision
CN116758057A (en) * 2023-08-10 2023-09-15 山东贺铭电气有限公司 Communication equipment defect detection method based on artificial intelligence
CN116740070A (en) * 2023-08-15 2023-09-12 青岛宇通管业有限公司 Plastic pipeline appearance defect detection method based on machine vision
CN116740070B (en) * 2023-08-15 2023-10-24 青岛宇通管业有限公司 Plastic pipeline appearance defect detection method based on machine vision
CN116843678A (en) * 2023-08-28 2023-10-03 青岛冠宝林活性炭有限公司 Hard carbon electrode production quality detection method
CN116843678B (en) * 2023-08-28 2023-11-21 青岛冠宝林活性炭有限公司 Hard carbon electrode production quality detection method
CN116862908A (en) * 2023-09-01 2023-10-10 菏泽学院 Metal gear meshing defect detection method based on image processing
CN116862908B (en) * 2023-09-01 2023-11-24 菏泽学院 Metal gear meshing defect detection method based on image processing
CN116883392A (en) * 2023-09-05 2023-10-13 烟台金丝猴食品科技有限公司 Feeding control method and system based on image processing
CN116883392B (en) * 2023-09-05 2023-11-17 烟台金丝猴食品科技有限公司 Feeding control method and system based on image processing
CN116883408B (en) * 2023-09-08 2023-11-07 威海坤科流量仪表股份有限公司 Integrating instrument shell defect detection method based on artificial intelligence
CN116883407A (en) * 2023-09-08 2023-10-13 山东省永星食品饮料有限公司 Bottled water impurity detection method based on artificial intelligence
CN116883407B (en) * 2023-09-08 2023-11-24 山东省永星食品饮料有限公司 Bottled water impurity detection method based on artificial intelligence
CN116883408A (en) * 2023-09-08 2023-10-13 威海坤科流量仪表股份有限公司 Integrating instrument shell defect detection method based on artificial intelligence
CN116912254B (en) * 2023-09-14 2023-12-08 山东博诚电气有限公司 Cable defect identification method based on data enhancement preprocessing
CN116912254A (en) * 2023-09-14 2023-10-20 山东博诚电气有限公司 Cable defect identification method based on data enhancement preprocessing
CN117036341A (en) * 2023-10-07 2023-11-10 青岛奥维特智能科技有限公司 Pavement crack detection method based on image processing
CN117079197B (en) * 2023-10-18 2024-03-05 山东诚祥建设集团股份有限公司 Intelligent building site management method and system
CN117079197A (en) * 2023-10-18 2023-11-17 山东诚祥建设集团股份有限公司 Intelligent building site management method and system
CN117095004A (en) * 2023-10-20 2023-11-21 金成技术股份有限公司 Excavator walking frame main body welding deformation detection method based on computer vision
CN117095004B (en) * 2023-10-20 2024-01-12 金成技术股份有限公司 Excavator walking frame main body welding deformation detection method based on computer vision
CN117197130B (en) * 2023-11-03 2024-01-26 山东太阳耐磨件有限公司 Driving tooth angle defect identification method based on machine vision
CN117197130A (en) * 2023-11-03 2023-12-08 山东太阳耐磨件有限公司 Driving tooth angle defect identification method based on machine vision
CN117197141B (en) * 2023-11-07 2024-01-26 山东远盾网络技术股份有限公司 Method for detecting surface defects of automobile parts
CN117197141A (en) * 2023-11-07 2023-12-08 山东远盾网络技术股份有限公司 Method for detecting surface defects of automobile parts
CN117474891A (en) * 2023-11-10 2024-01-30 艾普零件制造（苏州）股份有限公司 Gear heat treatment defect detection method
CN117237362B (en) * 2023-11-16 2024-01-26 山东嘉源复合材料有限公司 Vision-based propylene glycol diacetate canning sealing detection method
CN117237362A (en) * 2023-11-16 2023-12-15 山东嘉源复合材料有限公司 Vision-based propylene glycol diacetate canning sealing detection method
CN117274241B (en) * 2023-11-17 2024-02-09 四川赢信汇通实业有限公司 Brake drum surface damage detection method and device based on rapid image analysis
CN117274241A (en) * 2023-11-17 2023-12-22 四川赢信汇通实业有限公司 Brake drum surface damage detection method and device based on rapid image analysis
CN117474927A (en) * 2023-12-28 2024-01-30 山东太阳耐磨件有限公司 Driving tooth production quality detection method based on artificial intelligence
CN117474927B (en) * 2023-12-28 2024-03-26 山东太阳耐磨件有限公司 Driving tooth production quality detection method based on artificial intelligence
CN117788467A (en) * 2024-02-26 2024-03-29 宝鸡百润万德钛业有限公司 Defect image classification method for titanium metal plate
CN117788467B (en) * 2024-02-26 2024-04-26 宝鸡百润万德钛业有限公司 Defect image classification method for titanium metal plate
CN118052824A (en) * 2024-04-16 2024-05-17 济宁丰玺生物材料有限公司 Rice hull degradable cutlery box defect detection method
CN118052824B (en) * 2024-04-16 2024-06-28 济宁丰玺生物材料有限公司 Rice hull degradable cutlery box defect detection method
CN118154586A (en) * 2024-05-09 2024-06-07 深圳市冠森高捷电子技术有限公司 Intelligent connector crack defect detection method based on machine vision

Also Published As

Publication number Publication date
CN114723701B (en) 2023-04-18

Similar Documents

Publication Publication Date Title
CN114723701B (en) Gear defect detection method and system based on computer vision
CN109872300B (en) Visual saliency detection method for appearance defects of friction plate
CN115222733B (en) Metal component surface defect detection method based on image recognition
CN113808138B (en) Artificial intelligence-based wire and cable surface defect detection method
JP4139571B2 (en) Color image segmentation
CN113658133A (en) Gear surface defect detection method and system based on image processing
CN114219805B (en) Intelligent detection method for glass defects
CN115082683A (en) Injection molding defect detection method based on image processing
CN116758061A (en) Casting surface defect detection method based on computer vision
CN115082451B (en) Stainless steel soup ladle defect detection method based on image processing
CN115797342B (en) Industrial control capacitive touch LCD display assembly defect detection method
CN115578374A (en) Mechanical part casting quality evaluation method and system
CN111354047B (en) Computer vision-based camera module positioning method and system
CN115131359B (en) Method for detecting pitting defects on surface of metal workpiece
CN115294159B (en) Method for dividing corroded area of metal fastener
CN116977342B (en) PCB circuit detection method based on image segmentation
CN115330772A (en) Online welding spot quality detection method
CN115018765A (en) Powder metallurgy part finished product detection method based on gray level gradient co-occurrence matrix
CN115100206A (en) Printing defect identification method for textile with periodic pattern
CN115861320A (en) Intelligent detection method for automobile part machining information
CN115311289A (en) Method for detecting oil stain defects of plain-color cloth
CN117274113B (en) Broken silicon wafer cleaning effect visual detection method based on image enhancement
CN109544513A (en) A kind of steel pipe end surface defect extraction knowledge method for distinguishing
CN114863492A (en) Method and device for repairing low-quality fingerprint image
CN113962994A (en) Method for detecting cleanliness of lock pin on three-connecting-rod based on image processing

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
TA01 Transfer of patent application right

Effective date of registration: 20230323

Address after: Unit 204A, No. 15, Wangwanghai Road, Software Park, Xiamen City, Fujian Province, 361001

Applicant after: Xiamen Lixing Automation Co.,Ltd.

Address before: No. 12, Chuangye Road, Yudong Town, Haimen District, Nantong City, Jiangsu Province, 226000

Applicant before: Nantong Boying Machinery Casting Co.,Ltd.

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant