CN114894804A - Method for detecting surface cracks of precision standard part - Google Patents
Method for detecting surface cracks of precision standard part Download PDFInfo
- Publication number
- CN114894804A CN114894804A CN202210432068.1A CN202210432068A CN114894804A CN 114894804 A CN114894804 A CN 114894804A CN 202210432068 A CN202210432068 A CN 202210432068A CN 114894804 A CN114894804 A CN 114894804A
- Authority
- CN
- China
- Prior art keywords
- crack
- mapping
- value
- parallel light
- determining
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000013507 mapping Methods 0.000 claims description 163
- 238000005286 illumination Methods 0.000 claims description 65
- 238000004364 calculation method Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000001514 detection method Methods 0.000 abstract description 14
- 238000004458 analytical method Methods 0.000 abstract description 13
- 238000012360 testing method Methods 0.000 abstract description 5
- 238000004154 testing of material Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 3
- 230000001788 irregular Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to the technical field of material testing and analysis, in particular to a method for detecting surface cracks of a precision standard part, which utilizes visible light to obtain a divergent light surface image of the precision standard part to be detected, and performs material analysis on the divergent light surface image so as to determine each crack area; and according to the position of each crack area, acquiring parallel light surface images corresponding to different incidence included angles of each crack area by using visible light, carrying out material analysis on the parallel light surface images, and determining the crack hazard grade of the precision standard component to be detected by combining the divergent light surface images. The method and the device utilize visible light to obtain the divergent light surface image and the parallel light surface image of the precision standard component to be detected, and perform material analysis and test based on the images, thereby realizing the crack analysis of the surface of the precision standard component and effectively improving the crack detection accuracy of the standard component.
Description
Technical Field
The invention relates to the technical field of material testing and analysis, in particular to a method for detecting surface cracks of a precision standard component.
Background
In the production process of the precision standard component, cracks of different degrees are often generated on the surface of the component due to misoperation in the production process, the functions and the attractive effects of the component are seriously affected by the cracks, and therefore the crack detection is often required after the component is produced.
At present, the surface crack of the part is often measured manually, the manual detection is easily interfered by external factors, the consumed time is long, the cost is high, the efficiency is low, and the precision cannot be guaranteed. With the development of visible light images and computer technology, material analysis and testing can be performed according to the visible light images, so that crack detection on the surface of the part can be realized. Compared with manual detection, the detection mode effectively improves the efficiency and accuracy of crack detection, but the detection mode can only detect the size of a crack area and cannot realize comprehensive characteristic detection of cracks, so that finally detected cracks are not accurate enough.
Disclosure of Invention
The invention aims to provide a method for detecting surface cracks of a precision standard component, which is used for solving the problem that the existing crack detection is not accurate enough.
In order to solve the technical problem, the invention provides a method for detecting surface cracks of a precision standard component, which comprises the following steps:
acquiring a divergent light surface image of a precision standard part to be detected, and further acquiring a divergent light surface gray image;
judging whether cracks exist on the surface of the precision standard part to be detected or not according to the gray value of pixel points in the gray image of the surface of the divergent light, and if the cracks exist, determining each crack area;
acquiring parallel light surface images corresponding to different incidence included angles of each crack area according to the position of each crack area, and further acquiring parallel light surface gray level images corresponding to different incidence included angles of each crack area;
determining each mapping crack area corresponding to each crack area in the parallel light surface gray level image corresponding to different incidence included angles according to the position of each crack area, and determining the edge length value and the width value of each mapping crack area;
determining the number of illumination pixel points and the number of non-illumination pixel points of each parallel light related line segment in each mapping crack region under different incidence angles and the length of each parallel light related line segment according to the gray values of the pixel points in each mapping crack region in the parallel light surface gray images corresponding to different incidence angles;
determining the maximum depth value and the crack volume value of each mapping crack area according to the number of illumination pixel points and the number of non-illumination pixel points corresponding to each parallel light related line segment in each mapping crack area under different incidence included angles, the length of each parallel light related line segment and the corresponding different incidence included angles;
and determining the overall crack damage degree value of the precision standard part to be detected according to the edge length value, the width value, the maximum depth value and the volume value of each mapping crack area and the size value of the precision standard part to be detected, and further determining the crack damage grade of the precision standard part to be detected.
Further, the step of determining the maximum depth value of each mapped crack region comprises:
determining the depth value corresponding to each parallel light related line segment in each mapping crack area under different incidence included angles according to the number of illumination pixel points and the number of non-illumination pixel points corresponding to each parallel light related line segment in each mapping crack area under different incidence included angles, the length of each parallel light related line segment and the corresponding different incidence included angles;
and determining the maximum depth value of each mapping crack area according to the corresponding depth value of each parallel light related line segment in each mapping crack area under different incidence included angles.
Further, a calculation formula for determining the corresponding depth values of each parallel light related line segment in each mapping crack area under different incident included angles is as follows:
h is the depth value corresponding to each parallel light related line segment in each mapping crack area under the incident included angle theta, and m is b The number of the non-illuminated pixel points m corresponding to each parallel light related line segment in each mapping crack area under the incident included angle theta a And the number of illumination pixel points corresponding to each parallel light related line segment in each mapping crack area under the incident included angle theta is represented by Z, and the length of each parallel light related line segment in each mapping crack area is represented by Z.
Further, the step of determining a volume value for each mapped crack region comprises:
determining the lengths of the illumination line segments corresponding to each parallel light related line segment in each mapping crack region under different incidence angles according to the number of illumination pixel points, the number of non-illumination pixel points and the length of each parallel light related line segment in each mapping crack region under different incidence angles;
determining a crack function expression corresponding to each parallel light related line segment in each mapping crack area according to the length and the depth value of the illumination line segment corresponding to each parallel light related line segment in each mapping crack area under different incidence included angles;
determining a crack volume value corresponding to each parallel light related line segment in each mapping crack area according to a crack function expression corresponding to each parallel light related line segment in each mapping crack area;
and accumulating the crack volume values corresponding to each parallel light related line segment in each mapping crack area so as to obtain the crack volume value of each mapping crack area.
Further, the step of determining the number of the illumination pixel points and the number of the non-illumination pixel points corresponding to each parallel light related line segment in each mapping crack area under different incidence included angles includes:
clustering each pixel point corresponding to each parallel light related line segment in each mapping crack region according to the pixel point gray value in each mapping crack region in the parallel light surface gray image corresponding to different incidence included angles, thereby obtaining two pixel point groups corresponding to each parallel light related line segment in each mapping crack region under different incidence included angles;
and determining an illumination pixel group and an unreceived pixel group in the two pixel groups according to the gray levels of the pixel groups of the two pixel groups corresponding to the parallel light related line segments in the mapping crack regions under different incidence angles, so as to obtain the number of the illumination pixels and the number of the unreceived pixels corresponding to the parallel light related line segments in the mapping crack regions under different incidence angles.
Further, the step of determining the overall crack damage degree value of the precision standard component to be detected comprises the following steps:
determining the crack hazard degree of each mapping crack area according to the edge length value, the width value, the maximum depth value and the size value of the precision standard component to be detected of each mapping crack area;
determining a crack hazard weighted value of each mapping crack area according to the volume value of each mapping crack area and the size value of the precision standard component to be detected;
and determining the overall crack hazard degree value of the precision standard component to be detected according to the crack hazard degree and the crack hazard weighted value of each mapping crack area.
Further, the step of determining the crack hazard level for each mapped crack region comprises:
the shape of the precision standard part to be detected is a cuboid, the size of the precision standard part to be detected comprises length, width and height, and the ratio of the edge length value of each mapping crack area to the length of the precision standard part to be detected, the ratio of the width value of each mapping crack area to the width of the precision standard part to be detected and the ratio of the maximum depth value of each mapping crack area to the height of the precision standard part to be detected are respectively calculated;
and accumulating the three ratios corresponding to each mapping crack area to obtain the crack hazard degree of each mapping crack area.
Further, the step of judging whether the surface of the precision standard component to be detected has cracks comprises the following steps:
performing superpixel segmentation on the divergent light surface gray image according to the gray value of a pixel point in the divergent light surface gray image to obtain each superpixel block;
counting the gray values of the pixel points in each super pixel block to obtain a gray histogram corresponding to each super pixel block;
determining a first characteristic index between any two superpixel blocks according to the gray histogram corresponding to each superpixel block;
determining the number of value intervals corresponding to the first characteristic indexes between any one superpixel block and other superpixel blocks, further determining the target number of the value intervals, judging that no crack exists on the surface of the precision standard component to be detected if the target number is 1, and otherwise judging that a crack exists on the surface of the precision standard component to be detected.
Further, if there is a crack, the step of determining each crack region includes:
determining a second characteristic index between any two superpixel blocks according to the position coordinates of the seed points corresponding to the superpixel blocks;
dividing each super pixel block into K super pixel block groups according to a first characteristic index and a second characteristic index between any two super pixel blocks, wherein K is the target number of a value interval;
determining K-1 crack superpixel block groups in the K superpixel block groups according to the gray levels of pixel points in the K superpixel block groups;
and determining K-1 crack regions corresponding to the K-1 crack superpixel groups according to the gray value of the pixel points in the K-1 crack superpixel groups.
Further, the calculation formula for determining the correspondence of the first characteristic index between any two super pixel blocks is as follows:
wherein Q is a first characteristic index between any two superpixel blocks, p 1i For the frequency value, p, corresponding to the ith gray level in the gray histogram corresponding to the first of any two superpixel blocks 2i The frequency value corresponding to the ith gray level in the gray histogram corresponding to the second super-pixel block in any two super-pixel blocks.
The invention has the following beneficial effects: acquiring a divergent light surface image of the precision standard component to be detected by using a visible light means, thereby determining each crack area; and then according to the position of each crack area, acquiring parallel light surface images corresponding to different incident included angles of each crack area by using visible light, carrying out parallel material analysis and test on the parallel light surface images and the divergent light surface images, and determining the edge length value, the width value, the maximum depth value and the volume value of each crack area, thereby determining the whole crack damage degree value of the precision standard component to be detected and further determining the crack damage grade of the precision standard component to be detected. Because the invention utilizes visible light to obtain the divergent light surface image and the parallel light surface image of the precision standard component to be detected, and carries out material analysis and test based on the images, the invention can carry out comprehensive characteristic detection on the crack such as length, width, depth, volume and the like, thereby realizing the precision analysis of the crack on the surface of the precision standard component and effectively improving the precision of crack detection of the standard component.
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 surface cracks of a precision standard component according to the present invention;
FIG. 2 is a schematic diagram illustrating the principle of determining whether cracks exist on the surface of the standard component and the number of the cracks according to the first characteristic index;
FIG. 3 is a schematic view of parallel light-related line segments in a mapped crack region of the present invention;
fig. 4 is a schematic diagram of the gray scale variation of the parallel light related line segment in the mapping crack region according to the present invention.
Detailed Description
To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the embodiments, structures, features and effects of the technical solutions according to the present invention will be given with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily 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.
In order to realize identification and evaluation of the surface crack of the precision standard component, improve the detection efficiency and precision, and reduce the cost, the embodiment provides a method for detecting the surface crack of the precision standard component, and a corresponding flowchart is shown in fig. 1, and includes the following steps:
(1) and acquiring a divergent light surface image of the precision standard component to be detected, and further acquiring a divergent light surface gray image.
On the production line of the precision standard part, a fixed divergent light source is arranged above the precision standard part, wherein the fixed divergent light source refers to a light source which emits light in all directions. Under the irradiation of the fixed divergent light source, a high-precision industrial camera is adopted to collect the surface image of the precision standard part, so that the divergent light surface image of the precision standard part can be obtained. The divergent light surface image is a visible light RGB image, and the RGB image is subjected to graying processing, and the graying processing method adopted in this embodiment is a weighted graying method, so that a divergent light surface grayscale image can be obtained.
(2) And judging whether cracks exist on the surface of the precision standard part to be detected or not according to the gray value of the pixel points in the gray image of the divergent light surface, and if the cracks exist, determining each crack area.
From a priori knowledge, the crack regions are continuous irregular regions which are significantly different from normal regions, and the crack regions tend to take a form of local aggregation. Based on the characteristics, according to the gray value of the pixel point in the divergent light surface gray image, the divergent light surface gray image is firstly subjected to superpixel segmentation, the divergent light surface gray image is segmented into N superpixel blocks, and then the N superpixel blocks are subjected to significant analysis, so that whether cracks exist on the surface of the precision standard component or not and each crack area is determined under the condition that the cracks exist on the surface of the precision standard component.
The specific implementation steps of judging whether cracks exist on the surface of the precision standard part to be detected according to the gray value of a pixel point in the gray image of the divergent light surface comprise:
and (2-1) performing superpixel segmentation on the divergent light surface gray image according to the gray value of the pixel point in the divergent light surface gray image to obtain each superpixel block.
In order to reduce the workload of subsequent calculation, the divergent light surface gray image is subjected to superpixel segmentation based on the gray value of a pixel point in the divergent light surface gray image, so that the divergent light surface gray image can be segmented into N superpixel blocks. Since the specific implementation process of super-pixel block segmentation belongs to the prior art, it is not described here any more.
And (2-2) counting the gray values of the pixel points in each super pixel block so as to obtain a gray histogram corresponding to each super pixel block.
And (3) after each super-pixel block is obtained on the basis of the step (2-1), for each super-pixel block, extracting the number n of the pixel points in the super-pixel block and the gray level L corresponding to each pixel point. When determining the gray level L corresponding to each pixel point, in this embodiment, to reduce the subsequent calculation amount, 256 gray levels, which are 0 to 255 gray levels of the original pixel, are correspondingly compressed into 16 gray levels, which are 0 to 15 gray levels of the pixel. Then, according to the gray level corresponding to each pixel point in each super pixel block, calculating the frequency of each gray level in each super pixel block, and setting the frequency corresponding to the ith gray level as p i At this time have
For each super-pixel block, a histogram is generated with the gray level as abscissa and the frequency as ordinate, and each super-pixel block can correspond to one gray histogram.
(2-3) determining a first characteristic index between any two superpixel blocks according to the gray histogram corresponding to each superpixel block, wherein the corresponding calculation formula is as follows:
wherein Q is a first characteristic index between any two superpixel blocks, p 1i For the frequency value, p, corresponding to the ith gray level in the gray histogram corresponding to the first of any two superpixel blocks 2i The frequency value corresponding to the ith gray level in the gray histogram corresponding to the second super-pixel block in any two super-pixel blocks.
The first characteristic index represents the difference between two different superpixel blocks, and when the difference between the two superpixel blocks is larger, the significance is stronger, and the Q value of the first characteristic index is larger.
And (2-4) determining the number of the value intervals corresponding to the first characteristic indexes between any one superpixel block and other superpixel blocks, further determining the target number of the value intervals, judging that no crack exists on the surface of the precision standard component to be detected if the target number is 1, and otherwise judging that a crack exists on the surface of the precision standard component to be detected.
And (4) on the basis of the step (2-3), according to the first characteristic index Q value between any one superpixel block and other superpixel blocks, preliminarily judging whether cracks exist on the surface of the standard component and the number of the cracks. When the Q value of the first characteristic index is in 1 smaller value interval, the surface of the part is known to have no crack, if the Q value is in 2 smaller value intervals, 1 crack exists, and if the Q value is in 3 smaller value intervals, 2 cracks … … exist.
As shown in fig. 2, two cracks exist on the surface of the precision standard component to be detected, which are respectively the crack 1 and the crack 2, the superpixel blocks 21 and 22 are two superpixel blocks on the crack 1, the superpixel blocks 31 and 32 are two superpixel blocks on the crack 2, and the superpixel blocks 11 and 12 are two superpixel blocks in a non-crack area on the surface of the standard component. Taking the superpixel block 11 as an example, because the superpixel blocks in the non-crack region on the surface of the standard part have similarity, that is, the difference between the superpixel blocks is small, the first characteristic index Q value between the superpixel block 11 and other superpixel blocks (such as the superpixel block 12) in the non-crack region on the surface of the standard part is located in a small value interval, and the value of the first characteristic index Q in the small value interval is relatively small. Because the super-pixel block 11 and the super-pixel block on the crack have a small similarity, that is, the difference between the super-pixel blocks is large, and the degree of similarity between the super-pixel blocks located in the same crack region is high, and the degree of similarity between the super-pixel blocks located in different crack regions is low, the first characteristic index Q between the super-pixel block 11 and each super-pixel block (super-pixel blocks 21 and 22) on the crack 1 is located in a small value interval, the first characteristic index Q between the super-pixel block 11 and each super-pixel block (super-pixel blocks 31 and 32) on the crack 2 is located in another small value interval, and the value of the first characteristic index Q in the two small value intervals is relatively large.
In order to accurately determine the number of the value intervals corresponding to the first characteristic index between any superpixel block and other superpixel blocks, a clustering algorithm applicable in the prior art can be adopted to cluster the first characteristic index between each superpixel block and other superpixel blocks, the number of the categories obtained by clustering is counted, and the number category with the largest occurrence frequency is used as the final value interval number, namely the target number of the value intervals. And if the target number of the value interval is 1, judging that no crack exists on the surface of the precision standard component to be detected, otherwise, judging that the crack exists on the surface of the precision standard component to be detected.
When the surface of the precision standard part to be detected is judged to have cracks, determining each crack area according to the gray value of pixel points in the gray image of the divergent light surface, wherein the specific implementation steps comprise:
and (2-5) determining a second characteristic index between any two superpixel blocks according to the position coordinates of the seed points corresponding to the superpixel blocks.
Since the cracks are continuous and irregular and the crack area is much smaller than the normal area, a significant second characteristic index can be characterized according to the distance between the superpixel blocks. To determine the distance between superpixels, at the final segmentation of the superpixels, each superpixel block has a seed point whose coordinates are denoted as (x, y). Calculating the distance between the position coordinates of the seed points corresponding to any two superpixel blocks, and taking the distance as a second characteristic index between the two superpixel blocks, wherein the corresponding calculation formula is as follows:
where W is the second characteristic index between any two superpixel blocks, (x) a ，y a ) The coordinates of one of any two superpixel blocks, (y) a ，y b ) The coordinates of the other of any two superpixel blocks.
And (2-6) dividing each super pixel block into K super pixel block groups according to a first characteristic index and a second characteristic index between any two super pixel blocks, wherein K is the target number of the value interval.
If the target number of the value interval determined in the step (2-4) is K and K is a positive integer greater than 1, in order to improve the accuracy of subsequent super-pixel block clustering, accurately clustering each super-pixel block by using a K-means clustering algorithm according to a first characteristic index and a second characteristic index between any two super-pixel blocks, namely dividing the super-pixel block with the first characteristic index and the second characteristic index which are relatively smaller into a super-pixel block group, so as to divide each super-pixel block into K super-pixel block groups, namely accurately clustering the divergent light surface gray level image, and dividing the image into a normal area and K-1 crack areas.
And (2-7) determining K-1 crack superpixel blocks in the K superpixel blocks according to the gray levels of the pixel points in the K superpixel blocks.
Because the gray value of the crack pixel point in the divergent light surface gray image is obviously different from the gray value of the normal pixel point, and the gray value of the normal pixel point is relatively larger, the super pixel block group with the largest gray value of the pixel points in the K super pixel block groups can be used as the normal super pixel block group, and the other K-1 super pixel block groups are used as the K-1 crack super pixel block groups according to the gray values of the pixel points in the K super pixel block groups.
And (2-8) determining K-1 crack regions corresponding to the K-1 crack superpixel groups according to the gray value of the pixel points in the K-1 crack superpixel groups.
For each crack superpixel block group, clustering all pixel points in the crack superpixel block group into two classes according to the gray value of the pixel points in the crack superpixel block group, and taking the class with the lower gray value of the pixel in the two classes as a corresponding crack area.
(3) And acquiring parallel light surface images corresponding to different incidence included angles of each crack area according to the position of each crack area, and further acquiring parallel light surface gray level images corresponding to different incidence included angles of each crack area.
After determining each crack region through the step (2), acquiring parallel light surface images of each crack region under different incidence angles according to the specific position of each crack region. When parallel light surface images of each crack area under different incidence included angles are collected, the position of the high-precision industrial camera is adjusted to be located right above the crack area, the light source is adjusted to be parallel light incidence, the incidence included angle is theta, and namely the included angle between the parallel light rays and the horizontal surface of the standard component is theta.
When parallel light is incident at an incident angle theta, for a crack area, due to the problem of the illumination angle, light rays in some areas in the crack cannot be irradiated, a shadow part can appear when an image is collected, the depth h of the crack can be calculated according to the size of the shadow part and the incident angle theta, and the incident angle theta is continuously adjusted to enable theta to be within 0 degrees and 90 degrees]The deepest depth h of the crack can be calculated max And the overall volume V of the crack can be determined.
After parallel light surface images corresponding to different incidence angles theta epsilon [0 degrees and 90 degrees ] of all crack regions are obtained, weighted graying is carried out on the parallel light surface images, and therefore parallel light surface gray level images corresponding to different incidence angles theta epsilon [0 degrees and 90 degrees ] of all crack regions are obtained.
(4) And determining each mapping crack area corresponding to each crack area in the parallel light surface gray scale image corresponding to different incidence included angles according to the position of each crack area, and determining the edge length value and the width value of each mapping crack area.
For each crack region, the corresponding crack region can be found in the parallel light surface grayscale images corresponding to different incident angles according to the position of the crack region, and for convenience of distinguishing, the corresponding crack region is referred to as a mapping crack region. It should be noted that each crack region corresponds to a plurality of parallel light surface gray scale images, and a mapping crack region exists in each parallel light surface gray scale image, and the mapping crack regions have the same size, but the gray scales of the pixel points in the mapping crack regions are different. Therefore, after obtaining each mapped crack region corresponding to each crack region, the edge length value and the width value of one of the mapped crack regions, that is, the actual maximum length and the maximum width of the mapped crack region, may be determined and used as the edge length value and the width value of each mapped crack region. Because cracks are generally slender and the edges of the cracks are continuous and irregular closed curves, when the length value of the edge of the mapping crack area is determined, the perimeter of the edge of the mapping crack area can be obtained through a chain code method, and then half of the perimeter of the edge is taken as the length value of the edge of the mapping crack area.
(5) And determining the number of illumination pixel points and the number of non-illumination pixel points of each parallel light related line segment in each mapping crack region under different incidence angles and the length of each parallel light related line segment according to the gray values of the pixel points in each mapping crack region in the parallel light surface gray images corresponding to different incidence angles.
Because the parallel light is incident at an incident angle theta, namely the angle between the parallel light and the edge of the crack region is theta, which belongs to 0 and 90 degrees, a crack region which cannot be irradiated by a part of light exists and is displayed on an image, and the gray value of a region which is not irradiated by the light in the crack region is mapped to be obviously different from the gray value of a region which is irradiated by the light. Because the crack mapping region can be regarded as being formed by sequentially arranging a plurality of horizontal line segments, the included angle between the horizontal line segments and the parallel light is equal to the incident included angle theta, when the parallel light is incident at the incident included angle theta, the gray values of the pixels on the horizontal line segments are obviously different because the gray values of the illuminated region and the non-illuminated region are greatly different.
As shown in fig. 3, when the parallel light is incident at the incident angle θ, the crack mapping region can be regarded as being formed by sequentially arranging a plurality of horizontal line segments l, which are referred to herein as parallel light-related line segments because they are related to the incident angle θ of the parallel light, i.e., the included angle between the horizontal line segments and the parallel light is equal to the incident angle θ. As shown in fig. 4, when the parallel light is incident at the incident angle θ, a certain parallel light related line segment l on the crack region is mapped 1 The right-hand portion pixel gray scale may be significantly lower than the left-hand portion pixel gray scale.
For each mapping crack area, analyzing each parallel light related line segment in the mapping crack area to obtain the number m of pixel points on the parallel light related line segment, and determining the length Z of each parallel light related line segment according to the actual length corresponding to each pixel point because the length on the image and the length between real objects have a corresponding conversion relation. Because the gray value difference between the illumination area on each parallel light related line segment and the area which can not be illuminated is large, the number of illumination pixel points and the number of non-illumination pixel points of each parallel light related line segment in each mapping crack area under different incident included angles can be determined according to the gray value corresponding to each pixel point on the parallel light related line segment, and the specific implementation steps comprise:
(5-1) according to the gray values of the pixel points in each mapping crack area in the gray images of the surfaces of the parallel lights corresponding to different incidence included angles, clustering each pixel point corresponding to each parallel light related line segment in each mapping crack area, and thus obtaining two pixel point groups corresponding to each parallel light related line segment in each mapping crack area under different incidence included angles.
Specifically, according to the gray value of the pixel points of each parallel light related line segment under different incidence angles, performing K-means mean clustering on the corresponding pixel points of each parallel light related line segment under different incidence angles, wherein the number K of clustering centers can be set to be 2, so that two pixel point groups are obtained, one is an illumination pixel point group, and the other is an illumination pixel point group.
(5-2) determining an illumination pixel group and an unreceived illumination pixel group in the two pixel groups according to the gray levels of the pixels in the two pixel groups corresponding to each parallel light related line segment in each mapping crack region under different incidence angles, so as to obtain the number of the illumination pixels and the number of the unreceived illumination pixels corresponding to each parallel light related line segment in each mapping crack region under different incidence angles.
On the basis of the step (5-1), because gray values of pixels in the illumination pixel group and the non-illumination pixel group are obviously different, and gray values of pixels in the illumination pixel group are obviously larger, two pixel groups can be divided into the illumination pixel group and the non-illumination pixel group, and the number of illumination pixels in the illumination pixel group is recorded as m a The number of non-illuminated pixels in the non-illuminated pixel group is m b ，m a +m b ＝m。
(6) And determining the maximum depth value and the crack volume value of each mapping crack area according to the number of illumination pixel points and the number of non-illumination pixel points corresponding to each parallel light related line segment in each mapping crack area under different incidence included angles, the length of each parallel light related line segment and the corresponding different incidence included angles.
On the basis of the step (5), the number of illumination pixel points and the number of non-illumination pixel points of each parallel light related line segment in each mapping crack area under different incidence included angles and the length of each parallel light related line segment can be obtained, and the maximum depth value of each mapping crack area can be determined by combining the corresponding incidence included angles, and the specific implementation steps comprise:
(6-1) determining the corresponding depth value of each parallel light related line segment in each mapping crack area under different incidence included angles according to the number of illumination pixel points and the number of non-illumination pixel points of each parallel light related line segment in each mapping crack area under different incidence included angles, the length of each parallel light related line segment and the corresponding different incidence included angles, wherein the corresponding calculation formula is as follows:
h is the depth value corresponding to each parallel light related line segment in each mapping crack area under the incident included angle theta, and m is b The number of the non-illuminated pixel points m corresponding to each parallel light related line segment in each mapping crack area under the incident included angle theta a And the number of illumination pixel points corresponding to each parallel light related line segment in each mapping crack area under the incident included angle theta is represented by Z, and the length of each parallel light related line segment in each mapping crack area is represented by Z.
And (6-2) determining the maximum depth value of each mapping crack area according to the corresponding depth value of each parallel light related line segment in each mapping crack area under different incidence included angles.
For each crack mapping area, through the step (6-1), the depth value h corresponding to each parallel light related line segment under different incident angles θ e [0 °, 90 ° ] can be determined, and the maximum depth value among all the depth values h corresponding to each parallel light related line segment is found, where the maximum depth value is the deepest depth of the crack corresponding to the parallel light related line segment. And then determining the maximum value of the maximum depth values corresponding to all the parallel light related line segments, and taking the maximum value as the maximum depth value of the mapping crack area.
On the basis of the steps (5) and (6-1), the crack volume value of each mapping crack region can be determined, and the specific implementation steps comprise:
(6-3) determining the lengths of the illumination line segments corresponding to each parallel light related line segment in each mapping crack region under different incidence angles according to the number of illumination pixel points, the number of non-illumination pixel points and the length of each parallel light related line segment in each mapping crack region under different incidence angles, wherein the corresponding calculation formula is as follows:
wherein, x is the length of the illumination line segment corresponding to each parallel light related line segment in each mapping crack region under different incidence included angles, m b The number of non-illuminated pixel points m corresponding to each parallel light related line segment in each mapping crack region under different incidence included angles a And the number of corresponding illumination pixel points of each parallel light related line segment in each mapping crack area under different incidence included angles is Z, and the length of each parallel light related line segment in each mapping crack area is Z.
And (6-4) determining a crack function expression corresponding to each parallel light related line segment in each mapping crack area according to the length and the depth value of the illumination line segment corresponding to each parallel light related line segment in each mapping crack area under different incidence included angles.
For each parallel light related line segment in each crack mapping area, under an incident angle theta epsilon [0 DEG, 90 DEG ], each theta corresponds to a depth value h and an illumination line segment length x, namely, a point (x, h) on a crack curve corresponding to the parallel light related line segment can be obtained under each theta, and the points are fitted, so that a crack function expression corresponding to the parallel light related line segment can be obtained, namely h is F (x).
And (6-5) determining a crack volume value corresponding to each parallel light-related line segment in each crack mapping region according to the crack function expression corresponding to each parallel light-related line segment in each crack mapping region.
In this embodiment, a three-dimensional crack region is divided into a small three-dimensional regions, and each small three-dimensional region is defined by a crack curve corresponding to a corresponding parallel light-related line segment, so that on the basis of knowing a crack function expression corresponding to each parallel light-related line segment, a volume value corresponding to each small three-dimensional region, that is, a crack volume value corresponding to each parallel light-related line segment, can be obtained:
the crack volume value of each parallel light related line segment in each crack mapping region is S, a is the actual length represented by the width of each parallel light related line segment in each crack mapping region, F (x) is a crack function expression corresponding to each parallel light related line segment in each crack mapping region, and Z is the length of each parallel light related line segment in each crack mapping region.
(6-6) accumulating the crack volume values corresponding to each parallel light related line segment in each mapping crack area to obtain the crack volume value of each mapping crack area, wherein the corresponding calculation formula is as follows:
wherein V is the crack volume value of each of the mapped crack regions, S i And A is the number of the parallel light related line segments in each mapped crack region, and when A is larger, the crack volume value V of each corresponding mapped crack region is more accurate.
(7) And determining the overall crack damage degree value of the precision standard part to be detected according to the edge length value, the width value, the maximum depth value and the volume value of each mapping crack area and the size value of the precision standard part to be detected, and further determining the crack damage grade of the precision standard part to be detected.
Through the steps, the edge length value, the width value, the maximum depth value and the volume value of each mapping crack area can be determined, and the overall crack hazard level value of the precision standard part to be detected can be determined by combining the size value of the precision standard part to be detected, namely the length, the width and the height a, b and c of the standard part, and the implementation steps comprise:
and (7-1) determining the crack hazard degree of each mapping crack area according to the edge length value, the width value, the maximum depth value and the size value of the precision standard component to be detected of each mapping crack area.
In this embodiment, the shape of the precision standard component to be detected is a standard cuboid, the size of the precision standard component to be detected includes length, width and height, and the ratio of the edge length value of each mapping crack region to the length of the precision standard component to be detected, the ratio of the width value of each mapping crack region to the width of the precision standard component to be detected, and the ratio of the maximum depth value of each mapping crack region to the height of the precision standard component to be detected are calculated respectively; accumulating the three ratios corresponding to each mapping crack area to obtain the crack hazard degree of each mapping crack area, wherein the corresponding calculation formula is as follows:
wherein y is the crack hazard degree of each mapping crack region, R is the edge length value of each mapping crack region, D is the width value of each mapping crack region, and h max And (c) respectively representing the length, the width and the height of the precision standard component to be detected as the maximum depth value of each mapping crack area.
And (7-2) determining the crack hazard weight value of each mapping crack area according to the volume value of each mapping crack area and the size value of the precision standard component to be detected.
Because different crack regions may exist on the surface of the same part, different weights are given to the cracks according to the size of the crack regions, and then the cracks are evaluated, wherein the larger the size is, the larger the crack degree is, and the larger the weight is set, so that the overall crack damage degree value of the precision standard part to be detected can be conveniently and accurately determined in the follow-up process. Specifically, the calculation formula corresponding to the crack hazard weight value of each crack mapping region is as follows:
wherein alpha is i A crack hazard weight value, V, for the ith mapped crack region i And (b) respectively representing the length, the width and the height of the precise standard component to be detected, namely the size value of the precise standard component to be detected.
(7-3) determining the overall crack hazard degree value of the precision standard component to be detected according to the crack hazard degree and the crack hazard weight value of each mapping crack area, wherein the corresponding calculation formula is as follows:
wherein Y is the overall crack damage degree value of the precision standard component to be detected, V i Mapping the volume value, y, of the crack region for the ith i And the damage degree of the crack of the ith mapping crack region is U, the number of the mapping crack regions is U, and the U is K-1, a, b and c are the length, the width and the height of the precision standard part to be detected, namely the size value of the precision standard part to be detected.
After the overall crack damage degree value Y of the precision standard component to be detected is obtained, the cracks on the surface of the precision standard component to be detected can be evaluated based on the overall crack damage degree value Y. Specifically, a first threshold Y of the overall crack damage degree may be preset 1 And a second threshold Y for overall crack hazard level 2 ，Y 1 Less than Y 2 When the damage degree value Y of the whole cracks is smaller than the first threshold value Y of the damage degree of the whole cracks 1 When the damage degree of the whole cracks on the surface of the precision standard part to be detected is relatively light, the normal use is not influenced, and at the moment, the precision standard part to be detected is judged to be in a first-grade whole crack damage grade; when the damage degree value Y of the whole cracks is not less than the first threshold value Y of the damage degree of the whole cracks 1 And is not more than the second threshold value Y of the overall crack hazard level 2 In the process, the surface overall crack hazard degree of the precision standard part to be detected is moderate, whether the precision standard part to be detected can be normally used needs to be further confirmed, and at the moment, the precision standard part to be detected is judgedThe grade is a second-grade overall crack hazard grade; when the overall crack damage degree value Y is larger than the second threshold value Y of the overall crack damage degree 2 And judging that the surface overall crack damage degree of the precision standard component to be detected is heavier and affects normal use, and judging that the precision standard component to be detected is in a three-level overall crack damage grade.
In addition, the overall crack damage degree value Y based on the precision standard component to be detected is used for judging the overall crack damage grade of the precision standard component to be detected. However, considering that even though the overall crack damage degree value Y is small, the use condition of the precision standard component to be detected is still affected when the crack damage degree of the individual mapping crack region is large, the present embodiment also determines the crack damage degree of the single mapping crack region based on the consideration.
Specifically, according to the calculation formula of the crack hazard degree y, the value range of y is [0,3], when the value of y is in the range of [0,0.1], the crack which appears is a slight crack and does not affect the performance, and at the moment, the crack hazard level of the mapping crack area is judged to be first grade; when the value of y is in the range of [0.1,0.5], the cracks are considered to be large, the performance is reduced, and at the moment, the crack hazard level of the mapping crack area is judged to be two levels; and when the value of y is in the range of [0.5,3], determining that the cracks are too large and the standard component cannot be used, and determining that the damage level of the cracks in the mapping crack area is three levels.
The method and the device utilize visible light to obtain the divergent light surface image and the parallel light surface image of the precision standard part to be detected, perform material analysis and test based on the images, can detect the comprehensive characteristics of the crack such as length, width, depth, volume and the like, realize the precision analysis of the crack on the surface of the precision standard part, and effectively improve the precision of crack detection of the standard part.
It should be noted that: the above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. A method for detecting surface cracks of a precision standard component is characterized by comprising the following steps:
acquiring a divergent light surface image of a precision standard component to be detected, and further acquiring a divergent light surface gray image;
judging whether cracks exist on the surface of the precision standard part to be detected or not according to the gray value of pixel points in the gray image of the surface of the divergent light, and if the cracks exist, determining each crack area;
acquiring parallel light surface images corresponding to different incidence included angles of each crack area according to the position of each crack area, and further acquiring parallel light surface gray level images corresponding to different incidence included angles of each crack area;
determining each mapping crack area corresponding to each crack area in the parallel light surface gray level image corresponding to different incidence included angles according to the position of each crack area, and determining the edge length value and the width value of each mapping crack area;
determining the number of illumination pixel points and the number of non-illumination pixel points of each parallel light related line segment in each mapping crack region under different incidence angles and the length of each parallel light related line segment according to the gray values of the pixel points in each mapping crack region in the parallel light surface gray images corresponding to different incidence angles;
determining the maximum depth value and the crack volume value of each mapping crack area according to the number of illumination pixel points and the number of non-illumination pixel points corresponding to each parallel light related line segment in each mapping crack area under different incidence included angles, the length of each parallel light related line segment and the corresponding different incidence included angles;
and determining the overall crack damage degree value of the precision standard part to be detected according to the edge length value, the width value, the maximum depth value and the volume value of each mapping crack area and the size value of the precision standard part to be detected, and further determining the crack damage grade of the precision standard part to be detected.
2. The method for detecting the surface crack of the precision standard component as claimed in claim 1, wherein the step of determining the maximum depth value of each mapping crack area comprises the following steps:
determining the depth value corresponding to each parallel light related line segment in each mapping crack area under different incidence included angles according to the number of illumination pixel points and the number of non-illumination pixel points corresponding to each parallel light related line segment in each mapping crack area under different incidence included angles, the length of each parallel light related line segment and the corresponding different incidence included angles;
and determining the maximum depth value of each mapping crack area according to the corresponding depth value of each parallel light related line segment in each mapping crack area under different incidence included angles.
3. The method for detecting the surface crack of the precision standard component according to claim 2, wherein the calculation formula for determining the corresponding depth value of each parallel light related line segment in each mapping crack area under different incidence included angles is as follows:
h is a depth value corresponding to each parallel light related line segment in each mapping crack area under an incident included angle theta, and m is a depth value corresponding to each parallel light related line segment in each mapping crack area under an incident included angle theta b The number of the non-illuminated pixel points m corresponding to each parallel light related line segment in each mapping crack area under the incident included angle theta a And the number of illumination pixel points corresponding to each parallel light related line segment in each mapping crack area under the incident included angle theta is represented by Z, and the length of each parallel light related line segment in each mapping crack area is represented by Z.
4. The method for detecting the surface cracks of the precision standard component according to claim 2 or 3, wherein the step of determining the volume value of each mapping crack area comprises the following steps:
determining the lengths of the illumination line segments corresponding to each parallel light related line segment in each mapping crack region under different incidence angles according to the number of illumination pixel points, the number of non-illumination pixel points and the length of each parallel light related line segment in each mapping crack region under different incidence angles;
determining a crack function expression corresponding to each parallel light related line segment in each mapping crack area according to the length and the depth value of the illumination line segment corresponding to each parallel light related line segment in each mapping crack area under different incidence included angles;
determining a crack volume value corresponding to each parallel light related line segment in each mapping crack area according to a crack function expression corresponding to each parallel light related line segment in each mapping crack area;
and accumulating the crack volume values corresponding to each parallel light related line segment in each mapping crack area so as to obtain the crack volume value of each mapping crack area.
5. The method for detecting the surface cracks of the precision standard component according to claim 1, wherein the step of determining the number of the illumination pixel points and the number of the non-illumination pixel points of each parallel light related line segment in each mapping crack area under different incidence included angles comprises the following steps:
clustering each pixel point corresponding to each parallel light related line segment in each mapping crack region according to the pixel point gray value in each mapping crack region in the parallel light surface gray image corresponding to different incidence included angles, thereby obtaining two pixel point groups corresponding to each parallel light related line segment in each mapping crack region under different incidence included angles;
and determining an illumination pixel group and an un-illumination pixel group in the two pixel groups according to the gray levels of the pixel points in the two pixel groups corresponding to each parallel light related line segment in each mapping crack region under different incidence included angles, thereby obtaining the number of the illumination pixel points and the number of the un-illumination pixel points corresponding to each parallel light related line segment in each mapping crack region under different incidence included angles.
6. The method for detecting the surface cracks of the precision standard component according to claim 1, wherein the step of determining the overall crack damage degree value of the precision standard component to be detected comprises the following steps:
determining the crack hazard degree of each mapping crack area according to the edge length value, the width value, the maximum depth value and the size value of the precision standard component to be detected of each mapping crack area;
determining a crack hazard weighted value of each mapping crack area according to the volume value of each mapping crack area and the size value of the precision standard component to be detected;
and determining the overall crack hazard degree value of the precision standard component to be detected according to the crack hazard degree and the crack hazard weighted value of each mapping crack area.
7. The method for detecting the surface cracks of the precision standard component according to claim 6, wherein the step of determining the degree of damage of the cracks of each mapping crack area comprises the following steps:
the shape of the precision standard part to be detected is a cuboid, the size of the precision standard part to be detected comprises length, width and height, and the ratio of the edge length value of each mapping crack area to the length of the precision standard part to be detected, the ratio of the width value of each mapping crack area to the width of the precision standard part to be detected and the ratio of the maximum depth value of each mapping crack area to the height of the precision standard part to be detected are respectively calculated;
and accumulating the three ratios corresponding to each mapping crack area to obtain the crack hazard degree of each mapping crack area.
8. The method for detecting the surface cracks of the precision standard component according to claim 1, wherein the step of judging whether the surface of the precision standard component to be detected has the cracks comprises the following steps:
performing superpixel segmentation on the divergent light surface gray image according to the gray value of a pixel point in the divergent light surface gray image to obtain each superpixel block;
counting the gray values of the pixel points in each super pixel block to obtain a gray histogram corresponding to each super pixel block;
determining a first characteristic index between any two superpixel blocks according to the gray histogram corresponding to each superpixel block;
determining the number of value intervals corresponding to the first characteristic indexes between any one superpixel block and other superpixel blocks, further determining the target number of the value intervals, judging that no crack exists on the surface of the precision standard component to be detected if the target number is 1, and otherwise judging that a crack exists on the surface of the precision standard component to be detected.
9. The method for detecting the surface crack of the precision standard component according to claim 8, wherein if the crack exists, the step of determining each crack area comprises the following steps:
determining a second characteristic index between any two superpixel blocks according to the position coordinates of the seed points corresponding to the superpixel blocks;
dividing each super pixel block into K super pixel block groups according to a first characteristic index and a second characteristic index between any two super pixel blocks, wherein K is the target number of a value interval;
determining K-1 crack superpixel block groups in the K superpixel block groups according to the gray levels of pixel points in the K superpixel block groups;
and determining K-1 crack regions corresponding to the K-1 crack superpixel groups according to the gray value of the pixel points in the K-1 crack superpixel groups.
10. The method for detecting the surface crack of the precision standard component according to claim 8, wherein the calculation formula for determining the first characteristic index between any two superpixel blocks is as follows:
wherein Q is a first characteristic index between any two superpixel blocks, p 1i For the frequency value, p, corresponding to the ith gray level in the gray histogram corresponding to the first of any two superpixel blocks 2i The frequency value corresponding to the ith gray level in the gray histogram corresponding to the second super-pixel block in any two super-pixel blocks.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210432068.1A CN114894804B (en) | 2022-04-22 | Surface crack detection method for precision standard part |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210432068.1A CN114894804B (en) | 2022-04-22 | Surface crack detection method for precision standard part |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114894804A true CN114894804A (en) | 2022-08-12 |
| CN114894804B CN114894804B (en) | 2024-06-21 |
Family
ID=
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115170572A (en) * | 2022-09-08 | 2022-10-11 | 山东瑞峰新材料科技有限公司 | BOPP composite film surface gluing quality monitoring method |
| 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 |
| CN115880304A (en) * | 2023-03-08 | 2023-03-31 | 曲阜市巨力铁路轨道工程股份有限公司 | Method for identifying defects of sleeper based on complex scene |
| CN117455870A (en) * | 2023-10-30 | 2024-01-26 | 太康精密（中山）有限公司 | Connecting wire and connector quality visual detection method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010121992A (en) * | 2008-11-18 | 2010-06-03 | Taisei Corp | Crack detecting method |
| JP2011058939A (en) * | 2009-09-09 | 2011-03-24 | Panasonic Electric Works Co Ltd | Apparatus and method for visual inspection |
| WO2017057363A1 (en) * | 2015-10-01 | 2017-04-06 | 富士フイルム株式会社 | Crack detection apparatus, crack detection method, and program |
| CN109727244A (en) * | 2019-01-18 | 2019-05-07 | 深圳至汉装备科技有限公司 | A kind of magnetic shoe surface crack testing method |
| 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 (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010121992A (en) * | 2008-11-18 | 2010-06-03 | Taisei Corp | Crack detecting method |
| JP2011058939A (en) * | 2009-09-09 | 2011-03-24 | Panasonic Electric Works Co Ltd | Apparatus and method for visual inspection |
| WO2017057363A1 (en) * | 2015-10-01 | 2017-04-06 | 富士フイルム株式会社 | Crack detection apparatus, crack detection method, and program |
| CN109727244A (en) * | 2019-01-18 | 2019-05-07 | 深圳至汉装备科技有限公司 | A kind of magnetic shoe surface crack testing method |
| 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 |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115170572A (en) * | 2022-09-08 | 2022-10-11 | 山东瑞峰新材料科技有限公司 | BOPP composite film surface gluing quality monitoring method |
| 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 |
| 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 |
| CN115880304A (en) * | 2023-03-08 | 2023-03-31 | 曲阜市巨力铁路轨道工程股份有限公司 | Method for identifying defects of sleeper based on complex scene |
| CN117455870A (en) * | 2023-10-30 | 2024-01-26 | 太康精密（中山）有限公司 | Connecting wire and connector quality visual detection method |
| CN117455870B (en) * | 2023-10-30 | 2024-04-16 | 太康精密（中山）有限公司 | Connecting wire and connector quality visual detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115311292B (en) | Strip steel surface defect detection method and system based on image processing | |
| CN113689428B (en) | Mechanical part stress corrosion detection method and system based on image processing | |
| CN106778734B (en) | Sparse representation-based insulator string-falling defect detection method | |
| WO2022016884A1 (en) | Method for extracting sea surface wind speed on basis of k-means clustering algorithm | |
| CN106529559A (en) | Pointer-type circular multi-dashboard real-time reading identification method | |
| CN102176228B (en) | Machine vision method for identifying dial plate information of multi-pointer instrument | |
| CN115351598A (en) | Numerical control machine tool bearing detection method | |
| CN110286124A (en) | Refractory brick measuring system based on machine vision | |
| CN115249246B (en) | Optical glass surface defect detection method | |
| CN107392929B (en) | Intelligent target detection and size measurement method based on human eye vision model | |
| CN107564017B (en) | Method for detecting and segmenting urban high-resolution remote sensing image shadow | |
| CN114998852A (en) | Intelligent detection method for road pavement diseases based on deep learning | |
| CN106127205A (en) | A kind of recognition methods of the digital instrument image being applicable to indoor track machine people | |
| CN109726649B (en) | Remote sensing image cloud detection method and system and electronic equipment | |
| CN115018844A (en) | Plastic film quality evaluation method based on artificial intelligence | |
| CN109359604B (en) | Method for identifying instrument under shadow interference facing inspection robot | |
| CN116385450A (en) | PS sheet wear resistance detection method based on image processing | |
| CN105069395A (en) | Road marking automatic identification method based on terrestrial three-dimensional laser scanning technology | |
| CN115841488A (en) | Hole checking method of PCB (printed Circuit Board) based on computer vision | |
| CN117372436A (en) | Wind power blade fault detection method based on image data | |
| CN116188468A (en) | HDMI cable transmission letter sorting intelligent control system | |
| CN116309577A (en) | Intelligent detection method and system for high-strength conveyor belt materials | |
| CN107818341A (en) | A kind of color extraction method based on improvement K means algorithms | |
| CN112699824B (en) | Method and device for detecting constant of electric energy meter and storage medium | |
| CN114155226A (en) | Micro defect edge calculation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240531 Address after: No.13 Wensu Street, Hunnan District, Shenyang City, Liaoning Province, 110000 Applicant after: Liaoning zhongkeliler Testing Technology Service Co.,Ltd. Country or region after: China Address before: 226000 No. 998, Renmin South Road, Yudong Town, Haimen City, Nantong City, Jiangsu Province Applicant before: Jiangsu mingou Precision Machinery Co.,Ltd. Country or region before: China |
|
| GR01 | Patent grant |