CN112304954A - Part surface defect detection method based on line laser scanning and machine vision - Google Patents
Part surface defect detection method based on line laser scanning and machine vision Download PDFInfo
- Publication number
- CN112304954A CN112304954A CN202011125464.7A CN202011125464A CN112304954A CN 112304954 A CN112304954 A CN 112304954A CN 202011125464 A CN202011125464 A CN 202011125464A CN 112304954 A CN112304954 A CN 112304954A
- Authority
- CN
- China
- Prior art keywords
- image
- value
- camera
- difference
- machine 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
- 230000007547 defect Effects 0.000 title claims abstract description 33
- 238000001514 detection method Methods 0.000 title claims abstract description 26
- 238000001914 filtration Methods 0.000 claims abstract description 9
- 238000006243 chemical reaction Methods 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 238000009499 grossing Methods 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 37
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 5
- 101100534231 Xenopus laevis src-b gene Proteins 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000002950 deficient Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000000007 visual effect Effects 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
- G01N2021/8887—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
Abstract
The invention discloses a part surface defect detection method based on line laser scanning and machine vision, which specifically comprises the following steps: step 1, calibrating a camera, acquiring internal and external parameters of the camera, and shooting an image without laser irradiation as a reference image; step 2, collecting images by using an image collection system; step 3, sequentially carrying out Gaussian filtering, image difference, Gaussian smoothing, stripe center line extraction and coordinate conversion on the image to obtain three-dimensional point cloud data of the surface of the part to be detected; step 4, aiming at the standard part with a defect-free surface, executing the operations of the steps 1-3 to obtain a three-dimensional point cloud data image of the standard part with the defect-free surface; and 5, subtracting the data obtained in the step 3 from the data obtained in the step 4, taking the absolute value of the difference, comparing the obtained absolute value with a set threshold value, and judging whether the surface of the part to be detected has defects. The invention can accurately and efficiently detect the surface of the part.
Description
Technical Field
The invention belongs to the technical field of machine vision, and relates to a part surface defect detection method based on line laser scanning and machine vision.
Background
The detection of the surface defects of the parts is an important technical means for ensuring the use safety of the parts, when the surface defects of the parts are discovered in time, the production quality and the production efficiency of a machine are influenced, immeasurable loss is caused, and even more, the life safety of people is threatened. The traditional manual detection method is used for manually checking the defects of the parts, and has large workload and low efficiency. In the manual detection process, the technical quality and experience of detection personnel are different, so that the judgment of whether the part has defects also varies from person to person. Meanwhile, the subjectivity of manual detection is strong, and the phenomena of missing detection and false detection are easy to occur.
Machine vision is a modern detection technology which uses an industrial camera CCD to replace human eyes for detection, image processing is carried out on a detected object through the industrial camera CCD, image information is converted into digital signals, required characteristics are extracted from the digital signals, and therefore state detection of the detected object is achieved, and defect positioning and depth determination are carried out through line laser. Machine vision techniques are now widely used in many areas and play an increasingly important role therein.
Disclosure of Invention
The invention aims to provide a part surface defect detection method based on line laser scanning and machine vision, and the method can be used for accurately and efficiently detecting the surface of a part.
The invention adopts the technical scheme that a part surface defect detection method based on line laser scanning and machine vision specifically comprises the following steps:
step 1, calibrating a camera, acquiring internal and external parameters of the camera, and shooting an image without laser irradiation as a reference image;
and 5, subtracting the data obtained in the step 3 from the data obtained in the step 4, taking the absolute value of the difference, comparing the obtained absolute value with a set threshold value, and judging whether the surface of the part to be detected has defects or not according to the comparison result.
The present invention is also characterized in that,
the specific process of camera calibration in step 1 is as follows:
shooting 10-20 images of the chessboard by using a camera, detecting the number of corner points contained in each image by using a corner point detection function carried by opencv, comparing three-dimensional coordinates and pixel coordinates of the corner point coordinates, and finishing the calibration process of the camera, wherein the calibration result comprises an internal parameter matrix, a distortion coefficient and a rotation vector and a translation vector of each image of the camera.
In the step 2, the image acquisition system comprises a moving displacement platform which drives the part to move at a constant speed, the part to be detected is placed on the moving displacement platform, a CCD industrial camera is arranged right above the part to be detected, a linear laser transmitter is arranged obliquely above the part to be detected, and the CCD industrial camera is sequentially connected with a computer and a single chip microcomputer.
In step 3, the specific process of gaussian filtering is as follows:
each pixel in the image is scanned by a template, and the weighted average gray value of the pixels in the neighborhood determined by the template is used for replacing the value of the central pixel point of the template.
In step 3, the specific process of image difference is as follows:
step a, traversing pixel points of the image, and dividing R, G, B points of each pixel point in the image into
Separating out;
and b, adopting the following formula (1) to make difference between pixel points at corresponding positions of the striped image and the non-striped image:
dst(x,y,z)＝src1(x,y,z)-src2(x,y,z) (1)；
wherein dst (x, y, z) is R, G, B value of a certain pixel point of the image after the difference, src1(x, y, z) is R, G, B value of a corresponding pixel point in the image with the stripe pattern, and src2(x, y, z) is R, G, B value of a corresponding pixel point in the image without the stripe pattern
And c, repeating the step b until all the pixel points finish difference calculation, and obtaining the image dst after difference.
In step 3, the specific process of extracting the fringe center line is as follows:
step a, traversing each pixel point in the image according to columns, and finding out the brightest pixel point in each column.
And b, detecting the straight line by adopting Hough transformation.
The specific process of the step 5 is as follows:
step 5.1, taking the three-dimensional point cloud data of the surface of the part to be measured and the corresponding Z coordinate value of the three-dimensional point cloud data of the standard part under the same X, Y coordinates for difference, if the formula (2) shows that:
Hi＝Z(Xi，Yi)-Z1(Xi，Yi) (2)；
wherein, Z (X)i，Yi) Is a standard part upper point (X) with no surface defecti，Yi) Z coordinate of (A), Z1(Xi，Yi) Is the upper point (X) of the part to be measuredi，Yi) Z coordinate of (A), HiThe Z coordinate value of the standard part with the same X, Y and no defect on the lower surface of the coordinate is different from the Z coordinate value of the surface of the part to be measured;
step 5.2, adding HiAbsolute value of | HiComparing | with a set threshold value delta; if | Hi|<If the delta is within the error range determined by the threshold value, judging that the surface of the part to be measured is not defective; if | Hi|>And delta, namely, the surface of the part to be measured is out of the error range determined by the threshold value, and the surface of the part to be measured is judged to be defective.
The detection method has the advantages that the line laser generator in the image acquisition system is adopted to emit line laser to irradiate the surface of the part, and the CCD camera is used for shooting line laser stripes which are deformed due to the height modulation of the part. Because the complete surface of the part needs to be shot, the part can be driven by the speed controller to do uniform motion, and the line laser can uniformly sweep the surface of the part. The camera transmits the collected photos to the computer, the computer performs preprocessing such as median filtering and image threshold segmentation on the collected photos, and then performs operations such as fringe center line extraction and coordinate conversion on the preprocessed photos to obtain three-dimensional information of the surfaces of the parts. The height data is compared with the standard data, whether the surface of the part has defects can be found, if the defects are detected, the computer immediately sends an instruction to the singlechip through the serial port to control the on and off of a small lamp on the singlechip, and the speed controller is controlled to stop through the relay. The invention can accurately and efficiently detect the surface of the part by a visual detection technology.
Drawings
FIG. 1 is a schematic structural diagram of an image acquisition system in a part surface defect detection method based on line laser scanning and machine vision.
In the figure, 1 is a movable displacement platform, 2 is a part to be measured, 3 is a CCD industrial camera, 4 is a line laser emitter, 5 is a computer, and 6 is a single chip microcomputer.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
The invention relates to a part surface defect detection method based on line laser scanning and machine vision, which specifically comprises the following steps: step 1, calibrating a camera, acquiring internal and external parameters of the camera, and shooting an image without laser irradiation as a reference image;
in step 1, the specific process of camera calibration is as follows:
shooting 10-20 images of the chessboard by using a camera, detecting the number of corner points contained in each image by using a corner point detection function carried by opencv, comparing three-dimensional coordinates and pixel coordinates of the corner point coordinates, and finishing the calibration process of the camera, wherein the calibration result comprises an internal parameter matrix, a distortion coefficient and a rotation vector and a translation vector of each image of the camera. The result of the camera calibration can be used for correcting the shot image and subsequent coordinate conversion.
as shown in fig. 1, the image acquisition system comprises a mobile displacement platform 1 for driving the part to move at a uniform speed, a part 2 to be detected, a CCD industrial camera 3 arranged right above the part for image acquisition, a linear laser emitter 4 arranged obliquely above the part, and a computer 5 for processing a series of images, wherein the CCD industrial camera 3 is connected with the computer 5, and a 51 single chip microcomputer 6 for fault display is also arranged, and the single chip microcomputer 6 is connected with the computer 5; the type of the singlechip 6 is 89C51 singlechip.
The line laser emitted by the line laser is as narrow as possible, so that the workload of image processing of a subsequent computer can be reduced as much as possible.
The arrangement position of the CCD camera is required to be located right above the part as much as possible, and the surface appearance information of the part can be shot clearly by the CCD camera.
The working principle of the image acquisition system is as follows: the computer 5 carries on the image processing software and is compiled with VS2013+ opencv2.4.9, realize the detection to the surface defect of the part, when the surface defect of the part exists, will reveal through the turning on or off of the small light on the one-chip computer and make it stop through the relay control speed controller. Secondly, the arrangement positions of the CCD industrial camera 3 and the line laser transmitter 4 are required to ensure that the CCD camera can clearly shoot the stripe pattern which is deformed by the height modulation of the object, and meanwhile, the shot image is subjected to Gaussian filtering, image difference, Gaussian smoothing, stripe central line extraction and coordinate conversion to obtain three-dimensional point cloud data of the surface of the part.
the specific process of gaussian filtering is as follows:
each pixel in the image is scanned with a template (or convolution, mask) and the weighted average gray value of the pixels in the neighborhood determined by the template is used to replace the value of the pixel in the center of the template.
The specific process of image difference is as follows:
the image difference is obtained by subtracting the gray values or color components of the pixels corresponding to the two images.
(1) Traversing the image pixel points, and dividing R, G, B points of each pixel point in the image
Separating out;
(2) and (3) making difference between pixel points at corresponding positions of the striped image and the non-striped image:
dst(x,y,z)＝src1(x,y,z)-src2(x,y,z) (1)；
wherein dst (x, y, z) is R, G, B value of a certain pixel point of the image after the difference, src1(x, y, z) is R, G, B value of a corresponding pixel point in the image with the stripe pattern, and src2(x, y, z) is R, G, B value of a corresponding pixel point in the image without the stripe pattern;
(3) and (3) repeating the step (2) until all the pixel points complete the correlation calculation, and obtaining the differentiated image dst.
The specific process of extracting the fringe central line is as follows:
(1) traversing each pixel point in the image according to the columns, and finding out the brightest pixel point in each column.
(2) Hough transformation detection straight line
The concrete process of detecting the straight line by Hough transformation is as follows:
(a) obtaining edge information of the image;
(b) drawing a straight line in k-b space for each point in the edge image;
(c) for each point on the line, we adopt the method of "voting" (vote), i.e. adding up: there is a straight line passing through this point, the value of this point plus 1;
(d) and traversing the k-b space to find local maximum value points, wherein the coordinates (k, b) of the points are the slope and the intercept of the straight line in the original image.
The principle of coordinate transformation is a laser triangulation method;
and 5, subtracting the data obtained in the step 3 from the data obtained in the step 4, taking the absolute value of the difference, comparing the obtained absolute value with a set threshold value, and judging whether the surface of the part to be detected has defects or not according to the comparison result.
The specific process of the step 5 is as follows:
step 5.1, taking the three-dimensional point cloud data of the surface of the part to be measured and the corresponding Z coordinate value of the three-dimensional point cloud data of the standard part under the same X, Y coordinates for difference, if the formula (2) shows that:
Hi＝Z(Xi，Yi)-Z1(Xi，Yi) (2)；
wherein, Z (X)i，Yi) Is a standard part upper point (X) with no surface defecti，Yi) Z coordinate of (A), Z1(Xi，Yi) Is the upper point (X) of the part to be measuredi，Yi) Z coordinate of (A), HiThe Z coordinate value of the standard part with the same X, Y and no defect on the lower surface of the coordinate is different from the Z coordinate value of the surface of the part to be measured;
step 5.2, adding HiAbsolute value of | HiComparing | with a set threshold value delta; if | Hi|<If the delta is within the error range determined by the threshold value, judging that the surface of the part to be measured is not defective; if | Hi|>And delta, namely, the surface of the part to be measured is out of the error range determined by the threshold value, and the surface of the part to be measured is judged to be defective.
Claims (7)
1. A part surface defect detection method based on line laser scanning and machine vision is characterized in that: the method specifically comprises the following steps:
step 1, calibrating a camera, acquiring internal and external parameters of the camera, and shooting an image without laser irradiation as a reference image;
step 2, collecting images by using an image collection system;
step 3, sequentially carrying out Gaussian filtering, image difference, Gaussian smoothing, stripe center line extraction and coordinate conversion on the image to obtain three-dimensional point cloud data of the surface of the part to be detected;
step 4, aiming at the standard part with a defect-free surface, executing the operations of the steps 1-3 to obtain a three-dimensional point cloud data image of the standard part with the defect-free surface;
and 5, subtracting the data obtained in the step 3 from the data obtained in the step 4, taking the absolute value of the difference, comparing the obtained absolute value with a set threshold value, and judging whether the surface of the part to be detected has defects or not according to the comparison result.
2. The method for detecting the surface defects of the part based on the line laser scanning and the machine vision as claimed in claim 1, wherein the method comprises the following steps: the specific process of camera calibration in step 1 is as follows:
shooting 10-20 images of the chessboard by using a camera, detecting the number of corner points contained in each image by using a corner point detection function carried by opencv, comparing three-dimensional coordinates and pixel coordinates of the corner point coordinates, and finishing the calibration process of the camera, wherein the calibration result comprises an internal parameter matrix, a distortion coefficient and a rotation vector and a translation vector of each image of the camera.
3. The method for detecting the surface defects of the part based on the line laser scanning and the machine vision as claimed in claim 2, wherein the method comprises the following steps: in the step 2, the image acquisition system comprises a movable displacement platform which drives the part to move at a constant speed, the part to be detected is placed on the movable displacement platform, a CCD industrial camera is arranged right above the part to be detected, a linear laser emitter is arranged obliquely above the part to be detected, and the CCD industrial camera is sequentially connected with a computer and a single chip microcomputer.
4. The method for detecting the surface defects of the part based on the line laser scanning and the machine vision as claimed in claim 2, wherein the method comprises the following steps: in step 3, the specific process of gaussian filtering is as follows:
each pixel in the image is scanned by a template, and the weighted average gray value of the pixels in the neighborhood determined by the template is used for replacing the value of the central pixel point of the template.
5. The method for detecting the surface defects of the part based on the line laser scanning and the machine vision as claimed in claim 4, wherein the method comprises the following steps: in step 3, the specific process of image difference is as follows:
step a, traversing pixel points of an image, and separating R, G, B of each pixel point in the image;
and b, adopting the following formula (1) to make difference between pixel points at corresponding positions of the striped image and the non-striped image:
dst(x，y，z)＝src1(x，y，z)-src2(x，y，z) (1)；
wherein dst (x, y, z) is R, G, B value of a certain pixel point of the image after the difference, src1(x, y, z) is R, G, B value of a corresponding pixel point in the image with the stripe pattern, and src2(x, y, z) is R, G, B value of a corresponding pixel point in the image without the stripe pattern
And c, repeating the step b until all the pixel points finish difference calculation, and obtaining the image dst after difference.
6. The method for detecting the surface defects of the part based on the line laser scanning and the machine vision as claimed in claim 4, wherein the method comprises the following steps: in the step 3, the specific process of extracting the fringe central line is as follows:
step a, traversing each pixel point in the image according to columns, and finding out the brightest pixel point in each column.
And b, detecting the straight line by adopting Hough transformation.
7. The method for detecting the surface defects of the part based on the line laser scanning and the machine vision as claimed in claim 1, wherein the method comprises the following steps: the specific process of the step 5 is as follows:
step 5.1, taking the three-dimensional point cloud data of the surface of the part to be measured and the corresponding Z coordinate value of the three-dimensional point cloud data of the standard part under the same X, Y coordinates for difference, if the formula (2) shows that:
Hi＝Z(Xi，Yi)-Z1(Xi，Yi) (2)；
wherein, Z (X)i，Yi) Is a standard part upper point (X) with no surface defecti，Yi) Z coordinate of (A), Z1(Xi，Yi) Is the upper point (X) of the part to be measuredi，Yi) Z coordinate of (A), HiThe Z coordinate value of the standard part with the same X, Y and no defect on the lower surface of the coordinate is different from the Z coordinate value of the surface of the part to be measured;
step 5.2, adding HiAbsolute value of | HiComparing | with a set threshold value delta; if | HiIf the value is less than delta, namely the error range determined by the threshold value is within, judging that the surface of the part to be detected is free of defects; if | HiIf the value is greater than delta, namely the error range is out of the error range determined by the threshold value, the surface defect of the part to be detected is judged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011125464.7A CN112304954A (en) | 2020-10-20 | 2020-10-20 | Part surface defect detection method based on line laser scanning and machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011125464.7A CN112304954A (en) | 2020-10-20 | 2020-10-20 | Part surface defect detection method based on line laser scanning and machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112304954A true CN112304954A (en) | 2021-02-02 |
Family
ID=74328049
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011125464.7A Pending CN112304954A (en) | 2020-10-20 | 2020-10-20 | Part surface defect detection method based on line laser scanning and machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112304954A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113012119A (en) * | 2021-03-08 | 2021-06-22 | 电子科技大学 | Metal stamping part surface defect detection method and device based on fringe deflection method |
| CN113791086A (en) * | 2021-09-08 | 2021-12-14 | 天津大学 | Method and device for measuring surface defects of fan-shaped section blade based on computer vision |
| CN113793321A (en) * | 2021-09-14 | 2021-12-14 | 浙江大学滨江研究院 | Casting surface defect dynamic detection method and device based on machine vision |
| CN114384075A (en) * | 2021-12-06 | 2022-04-22 | 西安理工大学 | Track slab defect online detection system and detection method based on three-dimensional laser scanning |
| CN115908412A (en) * | 2023-01-06 | 2023-04-04 | 福建帝视智能科技有限公司 | Bamboo strip defect detection method based on line laser image and terminal |
| CN115931871A (en) * | 2022-12-01 | 2023-04-07 | 华中科技大学 | Device and method for detecting outer contour defects of permanent magnet motor rotor |
| CN116595214A (en) * | 2023-07-14 | 2023-08-15 | 中国航发北京航空材料研究院 | Component non-contact automatic shape correction system based on image processing |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020159053A1 (en) * | 2001-04-27 | 2002-10-31 | Dinesh Nair | Machine vision system and method for analyzing illumination lines in an image to determine characteristics of an object being inspected |
| CN102279190A (en) * | 2011-04-29 | 2011-12-14 | 广州有色金属研究院 | Image detection method for weld seam surface defects of laser welded plates of unequal thickness |
| CN104913737A (en) * | 2015-06-30 | 2015-09-16 | 长安大学 | Component quality checking device based on line laser three-dimensional measurement and detection method of device |
| KR20150128300A (en) * | 2014-05-09 | 2015-11-18 | 한국건설기술연구원 | method of making three dimension model and defect analysis using camera and laser scanning |
| CN106204564A (en) * | 2016-07-04 | 2016-12-07 | 南通职业大学 | A kind of laser photocentre extracting method |
| CN106338521A (en) * | 2016-09-22 | 2017-01-18 | 华中科技大学 | Additive manufacturing surface defect, internal defect and shape composite detection method and device |
| CN106990112A (en) * | 2017-03-14 | 2017-07-28 | 清华大学 | The multi-layer multi-pass welding track detection device and method merged based on multi-visual information |
| CN107578464A (en) * | 2017-06-30 | 2018-01-12 | 长沙湘计海盾科技有限公司 | A kind of conveyor belt workpieces measuring three-dimensional profile method based on line laser structured light |
| CN107907048A (en) * | 2017-06-30 | 2018-04-13 | 长沙湘计海盾科技有限公司 | A kind of binocular stereo vision method for three-dimensional measurement based on line-structured light scanning |
| CN109523505A (en) * | 2018-09-18 | 2019-03-26 | 深圳市智信精密仪器有限公司 | A kind of ceramic brick surface patterned defect detection method based on machine vision |
| CN109765240A (en) * | 2018-12-25 | 2019-05-17 | 浙江四点灵机器人股份有限公司 | A kind of detection industrial part stitch defect device and method |
| CN110306287A (en) * | 2019-06-21 | 2019-10-08 | 西安工程大学 | Hosiery machine knitting needle joint-detection device and method based on laser and machine vision |
| CN111189387A (en) * | 2020-01-02 | 2020-05-22 | 西安工程大学 | Industrial part size detection method based on machine vision |
| CN111462214A (en) * | 2020-03-19 | 2020-07-28 | 南京理工大学 | Line structure light stripe central line extraction method based on Hough transformation |
| CN111474150A (en) * | 2020-04-08 | 2020-07-31 | 华南师范大学 | STED super-resolution image background noise differential suppression method |
-
2020
- 2020-10-20 CN CN202011125464.7A patent/CN112304954A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020159053A1 (en) * | 2001-04-27 | 2002-10-31 | Dinesh Nair | Machine vision system and method for analyzing illumination lines in an image to determine characteristics of an object being inspected |
| CN102279190A (en) * | 2011-04-29 | 2011-12-14 | 广州有色金属研究院 | Image detection method for weld seam surface defects of laser welded plates of unequal thickness |
| KR20150128300A (en) * | 2014-05-09 | 2015-11-18 | 한국건설기술연구원 | method of making three dimension model and defect analysis using camera and laser scanning |
| CN104913737A (en) * | 2015-06-30 | 2015-09-16 | 长安大学 | Component quality checking device based on line laser three-dimensional measurement and detection method of device |
| CN106204564A (en) * | 2016-07-04 | 2016-12-07 | 南通职业大学 | A kind of laser photocentre extracting method |
| CN106338521A (en) * | 2016-09-22 | 2017-01-18 | 华中科技大学 | Additive manufacturing surface defect, internal defect and shape composite detection method and device |
| CN106990112A (en) * | 2017-03-14 | 2017-07-28 | 清华大学 | The multi-layer multi-pass welding track detection device and method merged based on multi-visual information |
| CN107578464A (en) * | 2017-06-30 | 2018-01-12 | 长沙湘计海盾科技有限公司 | A kind of conveyor belt workpieces measuring three-dimensional profile method based on line laser structured light |
| CN107907048A (en) * | 2017-06-30 | 2018-04-13 | 长沙湘计海盾科技有限公司 | A kind of binocular stereo vision method for three-dimensional measurement based on line-structured light scanning |
| CN109523505A (en) * | 2018-09-18 | 2019-03-26 | 深圳市智信精密仪器有限公司 | A kind of ceramic brick surface patterned defect detection method based on machine vision |
| CN109765240A (en) * | 2018-12-25 | 2019-05-17 | 浙江四点灵机器人股份有限公司 | A kind of detection industrial part stitch defect device and method |
| CN110306287A (en) * | 2019-06-21 | 2019-10-08 | 西安工程大学 | Hosiery machine knitting needle joint-detection device and method based on laser and machine vision |
| CN111189387A (en) * | 2020-01-02 | 2020-05-22 | 西安工程大学 | Industrial part size detection method based on machine vision |
| CN111462214A (en) * | 2020-03-19 | 2020-07-28 | 南京理工大学 | Line structure light stripe central line extraction method based on Hough transformation |
| CN111474150A (en) * | 2020-04-08 | 2020-07-31 | 华南师范大学 | STED super-resolution image background noise differential suppression method |
Non-Patent Citations (5)
| Title |
|---|
| XUEJUAN KANG: "A universal defect detection approach for various types of fabrics based on the Elo-rating algorithm of the integral image", 《TEXTILE RESEARCH JOURNAL》, no. 89, pages 21 - 22 * |
| 刘松: "一种激光散斑光条中心提取方法", 《计算机应用与软件》, vol. 36, no. 1, pages 272 - 274 * |
| 杨鹏程;刘洋;朱新栋;胥光申;肖渊;: "基于物体像的干涉条纹图像中散斑噪声的识别方法", 《应用光学》, vol. 38, no. 02, pages 222 - 224 * |
| 皮敏捷;徐科;: "基于多条激光线的钢板表面缺陷三维检测方法", 《机电产品开发与创新》, vol. 20, no. 02, pages 123 - 125 * |
| 龚燕萍: "轨道踏面激光三维检测的原理和方法的研究", 《佳木斯大学学报（自然科学版）》, vol. 35, no. 6, pages 2 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113012119A (en) * | 2021-03-08 | 2021-06-22 | 电子科技大学 | Metal stamping part surface defect detection method and device based on fringe deflection method |
| CN113791086A (en) * | 2021-09-08 | 2021-12-14 | 天津大学 | Method and device for measuring surface defects of fan-shaped section blade based on computer vision |
| CN113793321A (en) * | 2021-09-14 | 2021-12-14 | 浙江大学滨江研究院 | Casting surface defect dynamic detection method and device based on machine vision |
| CN113793321B (en) * | 2021-09-14 | 2024-01-23 | 浙江大学滨江研究院 | Casting surface defect dynamic detection method and device based on machine vision |
| CN114384075A (en) * | 2021-12-06 | 2022-04-22 | 西安理工大学 | Track slab defect online detection system and detection method based on three-dimensional laser scanning |
| CN115931871A (en) * | 2022-12-01 | 2023-04-07 | 华中科技大学 | Device and method for detecting outer contour defects of permanent magnet motor rotor |
| CN115908412A (en) * | 2023-01-06 | 2023-04-04 | 福建帝视智能科技有限公司 | Bamboo strip defect detection method based on line laser image and terminal |
| CN116595214A (en) * | 2023-07-14 | 2023-08-15 | 中国航发北京航空材料研究院 | Component non-contact automatic shape correction system based on image processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112304954A (en) | Part surface defect detection method based on line laser scanning and machine vision | |
| CN108562250B (en) | Keyboard keycap flatness rapid measurement method and device based on structured light imaging | |
| CN109900711A (en) | Workpiece, defect detection method based on machine vision | |
| CN111721259B (en) | Underwater robot recovery positioning method based on binocular vision | |
| CN112651968B (en) | Wood board deformation and pit detection method based on depth information | |
| CN109540925B (en) | Complex ceramic tile surface defect detection method based on difference method and local variance measurement operator | |
| CN112037203A (en) | Side surface defect detection method and system based on complex workpiece outer contour registration | |
| CN107316330B (en) | Underground hydraulic support frame group pose and verticality measuring method based on more image sequences | |
| CN109978940B (en) | Visual measurement method for SAB safety airbag size | |
| CN106651849A (en) | Area-array camera-based PCB bare board defect detection method | |
| CN109949362A (en) | A kind of material visible detection method | |
| CN111784655B (en) | Underwater robot recycling and positioning method | |
| CN116342718B (en) | Calibration method, device, storage medium and equipment of line laser 3D camera | |
| CN110807763A (en) | Method and system for detecting ceramic tile surface bulge | |
| CN112634269A (en) | Rail vehicle body detection method | |
| CN104966302B (en) | A kind of detection localization method of any angle laser cross | |
| CN114280075A (en) | Online visual inspection system and method for surface defects of pipe parts | |
| CN115384052A (en) | Intelligent laminating machine automatic control system | |
| CN114964007A (en) | Visual measurement and surface defect detection method for weld size | |
| CN110334727B (en) | Intelligent matching detection method for tunnel cracks | |
| KR100837119B1 (en) | A camera calibration method for measuring the image | |
| CN116481687A (en) | Machine vision-based finished tire stress-strain measurement device, method and program product | |
| CN115830018A (en) | Carbon block detection method and system based on deep learning and binocular vision | |
| CN113970560B (en) | Defect three-dimensional detection method based on multi-sensor fusion | |
| CN110927812A (en) | Airport pavement foreign matter monitoring method and monitoring system |
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 |