CN114862790A - Vision-based steel ball front side surface flaw correction method - Google Patents
Vision-based steel ball front side surface flaw correction method Download PDFInfo
- Publication number
- CN114862790A CN114862790A CN202210481952.4A CN202210481952A CN114862790A CN 114862790 A CN114862790 A CN 114862790A CN 202210481952 A CN202210481952 A CN 202210481952A CN 114862790 A CN114862790 A CN 114862790A
- Authority
- CN
- China
- Prior art keywords
- steel ball
- area
- flaw
- defect
- vision
- 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.)
- Pending
Links
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 93
- 239000010959 steel Substances 0.000 title claims abstract description 93
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000007547 defect Effects 0.000 claims abstract description 29
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000000605 extraction Methods 0.000 claims abstract description 4
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000011426 transformation method Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 14
- 230000002950 deficient Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 125000001475 halogen functional group Chemical group 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
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
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/168—Segmentation; Edge detection involving transform domain methods
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to a vision-based steel ball front side flaw correction method, which comprises the following steps: 1) shooting the steel ball by using a camera, and extracting a steel ball area from a camera image; 2) preprocessing the extracted steel ball image to remove noise interference; 3) extracting a flaw part in the image by using a difference method, and determining an effective area; 4) dividing the surface flaw of the steel ball in the effective area to obtain the surface flaw area and the area of the steel ball; 5) obtaining the correction coefficient of the positive side surface of the steel ball surface flaw area according to the following relational expression; 6) and multiplying the area of the plane defect area obtained by extraction by the correction coefficient of the positive side surface to obtain the corrected defect area. The method can correct the plane flaw area of the steel ball surface obtained by the camera into the flaw area of the three-dimensional sphere surface, and greatly improves the accuracy and stability of steel ball flaw area detection.
Description
Technical Field
The invention relates to a detection technology, in particular to a steel ball flaw detection technology, and specifically relates to a vision-based steel ball front side flaw correction method.
Background
The surface flaws of the steel ball are important indexes for measuring the quality of the steel ball, so that the area size of the surface flaws of the steel ball needs to be accurately measured when the quality of the steel ball is judged. However, the general steel ball surface flaw detection mostly depends on manual visual inspection, and the reliability of manual detection is reduced under high-intensity work. In order to solve the problem that manual detection excessively depends on the mental state of detection staff, some devices for detecting flaws on the surface of a steel ball based on image acquisition are available at present, but a common-grade steel ball surface detection device only uses an industrial camera to shoot the surface of the steel ball and directly calculates the detected flaw area, but the method does not take the problem that the two-dimensional image obtained by the camera is different from the actual surface of a three-dimensional ball into consideration, so that the flaw area detected by the same flaw in an area close to the edge is smaller than the actual area, the quality of the steel ball is difficult to judge correctly, and the accuracy of the detection device is reduced.
Disclosure of Invention
The invention aims to provide a visual-based steel ball front side flaw correction method aiming at the defects of the prior art, which can correct the plane flaw area of the steel ball surface obtained by a camera into the flaw area of the three-dimensional sphere surface, and greatly improves the accuracy and stability of steel ball flaw area detection.
The technical scheme of the invention is as follows:
a vision-based steel ball front side flaw correction method comprises the following steps:
1) shooting the steel ball by using a camera, and extracting a steel ball area from a camera image;
2) preprocessing the extracted steel ball image to remove noise interference;
3) extracting a flaw part in the image by using a difference method, and determining an effective area;
4) dividing the surface flaw of the steel ball in the effective area to obtain the surface flaw area and the area of the steel ball;
5) the correction coefficient of the front side surface of the steel ball surface flaw area is obtained according to the following relational expression
Wherein, Δ S ball The surface elements are spherical surface elements, and spherical defect areas are formed; delta S XOY The image is projected to a plane surface element of XOY and forms a plane flaw area extracted by a camera;
the included angle between the connecting line of the spherical surface element to the original point and the Z axis in the XYZ coordinate system is formed;
6) and multiplying the area of the plane defect area obtained by extraction by the correction coefficient of the positive side surface to obtain the corrected defect area.
Further, in the step 1), the steel ball is placed on an unfolding mechanism, a camera is used for shooting images of partial devices including the steel ball, and the largest circular part in the images is extracted by adopting a Hough circle transformation method, namely the area where the steel ball is located; then, the part except the circle is covered by white pixels, and the steel ball area image is obtained.
Further, in the step 2), a gaussian filtering method is adopted to perform filtering processing on the surface of the steel ball, so as to eliminate noise.
Further, in the step 3), the radius R of the steel ball is calculated according to hough transform, and an annulus with a radius between [ a × R, b × R ] is defined as an effective region, where 0< a < b < 1.
Further, in the step 4), an OSTU Otsu method is adopted to perform threshold segmentation to obtain a segmentation result of the surface defects.
Further, in the step 5), for each extracted flaw, a point p closest to the center of the circle on the plane flaw area is taken min And the point p farthest from the center of the circle max A handle p min And p max The included angle between the connecting line and the Z axis is
Then the process of the first step is carried out,
further, the defect correction coefficient is obtained
A value of (d); wherein,
h x is p min And p max The distance between them.
The invention has the beneficial effects that:
(1) the invention realizes the correction of the positive side surface of the steel ball surface flaw area, and can correct the plane steel ball flaw area obtained in the camera image into the size of the spherical surface flaw area, so that the quality judgment of the steel ball is more stable and reliable.
(2) The method is suitable for detecting the defects of various spherical parts and has wide application in the detection field.
Drawings
FIG. 1 is a schematic flow diagram of the present invention.
Figure 2 is a schematic representation of the principle of the invention for positive lateral correction.
Fig. 3 is a top view of fig. 2, consistent with the camera view.
Fig. 4 is a front view of fig. 2.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and embodiments, so that how to apply the technical means to solve the technical problems and achieve the technical effects can be fully understood and implemented. It should be noted that, as long as there is no conflict, the embodiments and the features of the embodiments of the present invention may be combined with each other, and the technical solutions formed are within the scope of the present invention.
Additionally, the steps illustrated in the flow charts of the figures may be performed in a computer system such as a set of computer-executable instructions and, although a logical order is illustrated in the flow charts, in some cases, the steps illustrated or described may be performed in an order different than here.
As shown in fig. 1, a method for correcting a flaw on a front side of a steel ball based on vision includes the following steps: :
step S110 is to extract a steel ball region from the camera image. The steel balls are unfolded on the disc type full-surface unfolding mechanism according to a meridian unfolding method, in the unfolding process of each steel ball, a camera shoots 60 images of each steel ball, and each steel ball can be completely unfolded at least once in the time of shooting 60 images. And then, the wheel disc with the steel balls puts the next batch of steel balls to be detected into the visual field of the camera for the next round of image acquisition. The camera captures images of a portion of the device including the steel ball. Therefore, the largest circular part in the image, namely the area where the steel ball is located, is extracted by adopting a Hough circle transformation method, and the parts except the circular part are covered by white pixels, so that the image only on the surface of the steel ball can be obtained.
And step S120, preprocessing the extracted steel ball image. The method for preprocessing the obtained steel ball image comprises the following steps: in the image acquisition process, some external noise interference is inevitably generated in the acquired image, and subsequent steps of flaw detection, area calculation and the like are influenced, so that a Gaussian filtering method can be adopted to filter the surface of the steel ball, and the method specifically comprises the following steps: each pixel in the image is scanned by using a template with the size of 3 x 3, the value of all pixels in the template is weighted and averaged by using a Gaussian template coefficient matrix with the size of 3 x 3, and then the value obtained by weighted averaging is used for replacing the value of the central pixel point of the template, so that the noise can be inhibited, and the detailed characteristics of a non-noise part are not damaged.
In step S130, a difference method is used to extract a defective portion in the image. In the steel ball flaw detection process, the steel ball to be detected rotates and expands on the expansion system, and the camera shoots the steel ball in the state. 60 images can be acquired for the same steel ball, and the whole surface of the steel ball can be covered. As the steel ball rotates on the unfolding system continuously, the position of the surface flaws of the steel ball in the two adjacent frames of images can change. Meanwhile, the color of the flaw area on the surface of the steel ball is dark, so that the difference image is obtained by subtracting the adjacent collected images, wherein the pixel position larger than 0 is the extracted flaw part, and the pixel position smaller than 0 after subtraction is set to be 0. And the differential image is the extracted defective area.
And step S140, dividing the flaws on the surface of the steel ball in the effective area. The steel ball image that the camera was gathered has obvious blur and shadow at the outermost edge, has a little black circle region at the positive center of steel ball, can produce the halo around it simultaneously, has covered original steel ball surface. Therefore, the radius R of the steel ball can be obtained by Hough transform calculation when the steel ball is detected, and the radius is defined to be [ a R, b R [ ]]The zone in between is the active area. Wherein, 0<a<b<1, the numerical values of a and b can be adjusted according to the specific situation of the steel ball, and a reasonable effective area is obtained. And covering the other areas with white pixel points, and performing threshold segmentation on the effective area by adopting an OSTU Otsu method to obtain a defective area. Since the following small outliers may be segmented after the threshold segmentation, the outliers can be eliminated by an on operation in the image processing. Specifically, the segmentation result seg is firstly etched by using a template m with the size of 7 x 7 to obtain an etching result
Where p represents each pixel in seg, (m) p Representing the range of m of the template centered on pAll of the pixels of (1). Then, the corroded result is expanded by a template m with the size of 7 x 7, and the final flaw result is obtained
Wherein p represents seg 1 Each pixel in (m) p Representing all pixels within the range of template m centered on p. Therefore, small and fine miscellaneous points can be eliminated while the large defect area is ensured to be unchanged, and interference of the miscellaneous points in the subsequent defect area calculation process is avoided. And finally obtaining a planar steel ball surface flaw area after opening operation, and calculating to obtain the area of the planar flaw area.
And step S150, solving a positive lateral correction coefficient for the acquired plane defect area. The extracted plane flaw area is the projection area of the flaw on the surface of the sphere rather than the real flaw area on the surface of the sphere. When the same flaw is on the front surface and the side surface of the sphere, the areas projected on the photosensitive surface of the camera are different, but the flaw area of the real spherical surface is not changed, so that the plane flaw area extracted by the camera needs to be corrected into the spherical surface flaw area. Specifically, the correction coefficient of each defect is obtained by the following formula
Wherein, Delta S ball The surface elements are spherical surface elements and form spherical defect areas; delta S XOY Projected onto an XOY plane bin and constitutes a plane defect region extracted by a camera.
The included angle between the connecting line of the spherical surface element to the origin and the Z axis in the XYZ coordinate system is shown. Therefore, the correction coefficient of the plane flaw can be obtained by obtaining the included angle between the surface where the spherical flaw is located and the Z axis, and the size of the area of the spherical flaw can be obtained. As shown in fig. 2-4, for each extracted flaw, the point p closest to the center of the circle on the plane flaw is taken min And the point p farthest from the center of the circle max P corresponding to the spherical surface flaw min And p max The included angle between the connecting line and the Z axis is used as the defect correction coefficient
Thus, p can be derived directly from the pixel position in the image min And p max Distance h between two points x While obtaining p min And p max The distances between the two points and the circle center O are respectively d min And d max . Then, can be according to d min 、d max And the radius R of the steel ball is calculated to obtain p min And p max Height difference of two points in front view
Thus, p can be obtained min And p max Is at an angle to the Z axis
Further obtain the defect correction coefficient
The value of (c).
And step S160, multiplying the area of the plane defect area obtained by extraction by the correction coefficient of the front side surface to obtain the corrected defect area. Moreover, when the same flaw is in different positions of the camera, the corrected flaw area is similar.
The method can efficiently and accurately correct the flaw area of the plane image of the steel ball surface obtained by the camera into the flaw area of the three-dimensional sphere surface, and improve the accuracy and stability of steel ball flaw area detection.
The parts not involved in the present invention are the same as or can be implemented using the prior art.
Claims (6)
1. A vision-based steel ball front side flaw correction method is characterized by comprising the following steps:
1) shooting the steel ball by using a camera, and extracting a steel ball area from a camera image;
2) preprocessing the extracted steel ball image to remove noise interference;
3) extracting a flaw part in the image by using a difference method, and determining an effective area;
4) dividing the surface flaw of the steel ball in the effective area to obtain the surface flaw area and the area of the steel ball;
5) the correction coefficient of the positive side surface of the steel ball surface flaw area is obtained according to the following relational expression
Wherein, Δ S ball The surface elements are spherical surface elements, and spherical defect areas are formed; delta S XOY Projecting the plane surface element to XOY, and forming a plane defect area extracted by a camera;
the included angle between the connecting line of the spherical surface element to the original point and the Z axis in the XYZ coordinate system is formed;
6) and multiplying the area of the plane defect area obtained by extraction by the correction coefficient of the positive side surface to obtain the corrected defect area.
2. The vision-based steel ball front side surface defect correcting method according to claim 1, wherein in the step 1), the steel ball is placed on a spreading mechanism, a machine is used for shooting images of partial devices including the steel ball, and a Hough circle transformation method is adopted to extract the largest circular part in the images, namely the area where the steel ball is located; then, the part except the circle is covered by white pixels, and the steel ball area image is obtained.
3. The vision-based steel ball front side surface flaw correction method according to claim 1, wherein in the step 2), a gaussian filtering method is adopted to filter the surface of the steel ball to eliminate noise.
4. The vision-based steel ball front side surface defect correction method according to claim 1, wherein in the step 3), a radius R of the steel ball is obtained according to hough transform calculation, and an annulus with a radius between [ a x R, b x R ] is defined as an effective area, wherein 0< a < b < 1.
5. The vision-based method for correcting the flaws on the front and side surfaces of the steel ball as claimed in claim 1, wherein in the step 4), the OSTU algorithm is used for threshold segmentation to obtain the segmentation result of the surface flaws.
6. The vision-based steel ball front side surface defect correcting method for the steel ball according to claim 1, wherein in the step 5), for each extracted defect, a point p closest to the center of the circle on a plane defect area is taken min And the point p farthest from the center of the circle max A handle p min And p max The included angle between the connecting line and the Z axis is
Then the process of the first step is carried out,
further, the defect correction coefficient is obtained
A value of (d); wherein,
h x is p min And p max The distance between them.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210481952.4A CN114862790A (en) | 2022-05-05 | 2022-05-05 | Vision-based steel ball front side surface flaw correction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210481952.4A CN114862790A (en) | 2022-05-05 | 2022-05-05 | Vision-based steel ball front side surface flaw correction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114862790A true CN114862790A (en) | 2022-08-05 |
Family
ID=82635343
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210481952.4A Pending CN114862790A (en) | 2022-05-05 | 2022-05-05 | Vision-based steel ball front side surface flaw correction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114862790A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06282659A (en) * | 1993-03-25 | 1994-10-07 | Daikin Ind Ltd | Method and device for polygon projection on semisphere, polygon projection area calculation, and form factor calculation |
| DE102012109105A1 (en) * | 2012-03-28 | 2013-10-02 | BAM Bundesanstalt für Materialforschung und -prüfung | Method for determining planar projection of property and data projected on virtual spherical surface, involves providing value distribution on spherical surface or hemisphere surface, where value distribution is relevant to property |
| CN106914428A (en) * | 2017-01-16 | 2017-07-04 | 哈尔滨理工大学 | A kind of New Algorithm of the steel ball surface defect Differential Detection based on machine vision |
| JP2018072252A (en) * | 2016-11-01 | 2018-05-10 | 倉敷紡績株式会社 | Device and method for inspecting surface of spherical object |
| CN111986158A (en) * | 2020-07-23 | 2020-11-24 | 佛山市承安铜业有限公司 | High-precision measuring method and system for copper balls with same specification |
| CN112033974A (en) * | 2020-09-25 | 2020-12-04 | 常州光电技术研究所 | Air-suction type sphere surface flaw detection system based on machine vision |
-
2022
- 2022-05-05 CN CN202210481952.4A patent/CN114862790A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06282659A (en) * | 1993-03-25 | 1994-10-07 | Daikin Ind Ltd | Method and device for polygon projection on semisphere, polygon projection area calculation, and form factor calculation |
| DE102012109105A1 (en) * | 2012-03-28 | 2013-10-02 | BAM Bundesanstalt für Materialforschung und -prüfung | Method for determining planar projection of property and data projected on virtual spherical surface, involves providing value distribution on spherical surface or hemisphere surface, where value distribution is relevant to property |
| JP2018072252A (en) * | 2016-11-01 | 2018-05-10 | 倉敷紡績株式会社 | Device and method for inspecting surface of spherical object |
| CN106914428A (en) * | 2017-01-16 | 2017-07-04 | 哈尔滨理工大学 | A kind of New Algorithm of the steel ball surface defect Differential Detection based on machine vision |
| CN111986158A (en) * | 2020-07-23 | 2020-11-24 | 佛山市承安铜业有限公司 | High-precision measuring method and system for copper balls with same specification |
| CN112033974A (en) * | 2020-09-25 | 2020-12-04 | 常州光电技术研究所 | Air-suction type sphere surface flaw detection system based on machine vision |
Non-Patent Citations (3)
| Title |
|---|
| 北京大学 等: "高等数学 第三册", 30 June 1982, 化学工业出版社, pages: 260 * |
| 王义文 等: "钢球表面缺陷的图像差分检测算法", 《计算机辅助设计与图形学学报》, vol. 28, no. 10, 31 October 2016 (2016-10-31), pages 1699 - 1704 * |
| 高纪青;云挺;薛联凤;: "基于鱼目摄像和地面激光雷达的真实叶面积指数计算", 南京师大学报(自然科学版), no. 04, 20 December 2014 (2014-12-20), pages 143 - 150 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108776140B (en) | Machine vision-based printed matter flaw detection method and system | |
| US12094152B2 (en) | Method for fully automatically detecting chessboard corner points | |
| CN108460757B (en) | Mobile phone TFT-LCD screen Mura defect online automatic detection method | |
| CN117237368B (en) | Bridge crack detection method and system | |
| CN109190628A (en) | A kind of plate camber detection method based on machine vision | |
| CN109540925B (en) | Complex ceramic tile surface defect detection method based on difference method and local variance measurement operator | |
| CN102156996B (en) | Image edge detection method | |
| CN109900711A (en) | Workpiece, defect detection method based on machine vision | |
| CN104568986A (en) | Method for automatically detecting printing defects of remote controller panel based on SURF (Speed-Up Robust Feature) algorithm | |
| CN113592955B (en) | Round workpiece plane coordinate high-precision positioning method based on machine vision | |
| CN107561087A (en) | A kind of mouse logo positioning and defect inspection method based on machine vision | |
| CN110596116B (en) | Vehicle surface flaw detection method and system | |
| CN108447070B (en) | Industrial part defect detection algorithm based on pixel vector invariant relation features | |
| CN112304954B (en) | Part surface defect detection method based on line laser scanning and machine vision | |
| CN112037203A (en) | Side surface defect detection method and system based on complex workpiece outer contour registration | |
| CN115096206B (en) | High-precision part size measurement method based on machine vision | |
| CN109815822B (en) | Patrol diagram part target identification method based on generalized Hough transformation | |
| CN110933926A (en) | Automatic correction method for angle of suction nozzle element of chip mounter based on angular point detection | |
| CN114627080B (en) | Vehicle stamping accessory defect detection method based on computer vision | |
| CN105741281B (en) | Method for detecting image edge based on neighborhood dispersion | |
| CN108492306A (en) | A kind of X-type Angular Point Extracting Method based on image outline | |
| CN112419225B (en) | SOP type chip detection method and system based on pin segmentation | |
| CN114862790A (en) | Vision-based steel ball front side surface flaw correction method | |
| CN117911419A (en) | Method and device for detecting steel rotation angle enhancement of medium plate, medium and equipment | |
| KR102383577B1 (en) | A method for inspecting a skeleton wafer |
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 |