CN113847881A - Free-form surface profile tolerance detection method based on machine vision - Google Patents
Free-form surface profile tolerance detection method based on machine vision Download PDFInfo
- Publication number
- CN113847881A CN113847881A CN202110010571.3A CN202110010571A CN113847881A CN 113847881 A CN113847881 A CN 113847881A CN 202110010571 A CN202110010571 A CN 202110010571A CN 113847881 A CN113847881 A CN 113847881A
- Authority
- CN
- China
- Prior art keywords
- image
- workpiece
- free
- machine vision
- form surface
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 13
- 238000003708 edge detection Methods 0.000 claims description 12
- 238000005516 engineering process Methods 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000005520 cutting process Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 4
- 238000005286 illumination Methods 0.000 claims description 4
- 238000009434 installation Methods 0.000 claims description 4
- 238000012634 optical imaging Methods 0.000 claims description 4
- 238000004088 simulation Methods 0.000 claims description 4
- 238000013519 translation Methods 0.000 claims description 3
- 230000009897 systematic effect Effects 0.000 abstract description 2
- 238000005259 measurement Methods 0.000 description 12
- 238000004519 manufacturing process Methods 0.000 description 6
- 230000004069 differentiation Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides a method for detecting the profile tolerance of a free-form surface based on machine vision, which comprises the following steps: after the detection is started, acquiring a digital image of the workpiece; preprocessing the collected image; carrying out edge acquisition on the preprocessed image; matching the images after the process; outputting the matched camera contour data; comparing the camera image profile data with the template image profile data; and setting a threshold value to screen the final contour data so as to obtain qualified products within the threshold value range. The method can form a systematic flow, is convenient to operate, has high measuring efficiency and higher application value, and can solve the problem that the profile tolerance of the free-form surface is difficult to accurately measure and evaluate by using the detection method.
Description
Technical Field
The invention relates to the technical field of image processing and artificial intelligence, in particular to a method for detecting the profile degree of a free-form surface based on machine vision.
Background
The measurement of the profile of the free-form surface belongs to a geometric element which is difficult to define, so that the inspection of the machining precision of the free-form surface becomes more complicated. The method mainly shows that the measured curved surface can not be directly used as a measurement reference, so that the measurement result comprises systematic errors caused by the fact that a measurement coordinate system is not overlapped with a design coordinate system. The traditional surface profile error measuring method comprises the following steps: profiling device measurement, cross-section profile template measurement, optical tracking profile gauge measurement, and three-coordinate measuring device measurement, etc. when the three-coordinate measuring device is used for measurement, the template profile template is not needed, and only the CAD model of the workpiece or part is needed. Therefore, the measuring method can be applied to various occasions and the measured data is reliable.
Machine vision systems are mostly used in the fields of working condition monitoring, finished product inspection, quality control and the like in the modern automatic production process. The method is characterized by comprising the following steps: the flexibility of production is improved, and the degree of automation is ensured. In the dangerous working environment which is not suitable for manual operation or the occasion where the manual vision is difficult to meet the requirements, the common machine vision replaces the manual vision, in the process of mass industrial production, the product quality is checked by the manual vision, the efficiency is low, the precision is not high, the production efficiency and the automation degree can be greatly improved by using the machine vision detection, and the detection method based on the machine vision is easy to realize informatization integration and is a basic technology for realizing computer integration and manufacturing.
In summary, although the conventional surface profile measuring method has satisfied the basic requirements, a detection method combining machine vision is needed in consideration of the limited working environment and artificial vision, so as to further improve the production detection efficiency and the product yield.
Disclosure of Invention
The invention aims to solve the problem of combination of traditional surface profile detection and machine vision detection methods, and provides a free-form surface profile detection method based on machine vision, which comprises the following steps: the method has the advantages that the problem that the profile degree of the free-form surface is difficult to accurately measure and evaluate is solved; the problems of dangerous working environment and limited visual detection under manual operation are solved; the non-contact measurement mode is realized, and the measurement range can be flexibly expanded. And the introduction of machine vision greatly improves the quality of products put on the market and the production efficiency of workpieces.
A free-form surface profile tolerance detection method based on machine vision comprises the following steps:
step 1: after the detection is started, acquiring a digital image of the workpiece;
step 2: preprocessing the collected image;
and step 3: carrying out edge acquisition on the preprocessed image;
step 4: matching the images after the process;
and 5: outputting the matched camera contour data;
step 6: comparing the camera image profile data with the template image profile data;
and 7: and setting a threshold value to screen the final contour data so as to obtain qualified products within the threshold value range.
Further, according to the method for detecting the free-form surface profile based on machine vision, the step of acquiring the digital image of the workpiece includes the following steps:
(1) an illumination system: an LED annular light source is adopted. During image acquisition, the maximum contrast between the important features of the workpiece to be detected and the features of the background image is generated, and feature differentiation is easy to perform;
(2) an optical imaging system: an industrial CCD camera and a 13 mm lens are adopted, and the installation positions are above the workpiece and at the right side (under the front view) of the workpiece;
(3) a software system: the image acquisition software part is operated by an industrial personal computer and is configured into a Windows operating system;
(4) mechanical motion control system: a clamping device for positioning the workpiece and a conveying belt for conveying the workpiece on a simulation assembly line are adopted;
further, in the method for detecting a free-form surface profile based on machine vision as described above, the step 2 includes: carrying out distortion processing on the collected image, setting the resolution ratio of the collected image to be the same as that of the digital image by adopting a convolutional neural network technology, analyzing a possibly generated distortion form, and cutting the image to a required size according to the proportion of a detection window;
further, in the method for detecting a free-form surface profile based on machine vision as described above, the step 3 includes:
(1) edge detection: when the preprocessed image is detected, smoothing the image by adopting a Gaussian filter, so that the value of each pixel point of the image is obtained by weighting and averaging the pixel point of the image and other pixel values in the neighborhood; the Sobel operator is adopted to carry out edge detection on the gray level image, so that the target can be simply realized while noise is suppressed;
(2) edge extraction: and obtaining a binary image after edge detection, wherein the binary image is an extracted image.
Further, in the method for detecting a free-form surface profile based on machine vision, the step 4 further includes: the process of the matching algorithm is as follows: the two image outlines have the same position orientation and suitable proportion through the steps of translation, rotation, scaling and the like; calibrating 10-15 pixel points as image contour feature points; searching an optimal solution of the matching path according to dynamic planning, and performing in a circular domain within a certain range; the offsets of the feature points are calculated from the resolution of the image, the coordinates of the key points, etc.
Further, in the method for detecting a free-form surface profile based on machine vision, the step 6 includes: setting the CAD three-dimensional model as standard template image contour data, using the image after the above steps as camera image contour data, and carrying out image comparison.
Further, according to the method for detecting the free-form surface profile based on the machine vision, the image acquisition equipment photographs the workpiece, acquires 10-15 images and introduces the images into the processing system for analysis.
Advantageous effects
The invention provides a free-form surface detection method based on machine vision, which directly collects a digital image of a workpiece by using image collection equipment, the digital image is transmitted to a computer through a collection module to be subjected to image processing, edge collection, image matching, template contour comparison and other steps, data is output and screening is carried out within a set threshold value, and qualified products within an error range can be obtained. The whole process realizes the combination of traditional surface profile detection and machine vision detection, improves the detection precision, shortens the detection time, is convenient to operate, improves the measurement efficiency and has higher application value.
Drawings
FIG. 1 is a flow chart of the detection of the present invention;
FIG. 2 is a flow chart of the acquisition stage of the present invention;
FIG. 3 is a diagram of an apparatus for practicing the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention are described clearly and completely below, and it is obvious that the described embodiments are some, not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a free-form surface contour degree detection method based on machine vision, and equipment used by the method comprises the following steps: high-resolution industrial CCD camera, LED annular light source, computer, programmable controller PLC, industrial computer. Wherein industry CCD camera passes through the mounting bracket and keeps fixed, and has certain height apart from detecting the work piece, arranges perpendicular work piece top, and the camera aims and detects the work piece, and the transmission band conveying work piece reaches the collection region, and programmable controller pauses the conveyer belt operation so that carry out image acquisition and match, and the conveyer belt continues the motion after accomplishing, carries out next image acquisition.
When the system collects images, the LED annular light source sets the most suitable brightness and exposure time to generate the maximum contrast between the important characteristics of the measured object and the background image characteristics, the image of the workpiece is collected through the image collecting system, and a digital signal is output to the computer to obtain the required measuring data.
The software part of the industrial personal computer for operating the image acquisition system is based on a Windows system and is formed by programming Visual studio C + + and Open CV languages, the acquired images are processed and edge acquired, required camera image contours are extracted for image matching, and matched images are output. The image of the standard two-dimensional drawing is input into a detection system to be used as the template image contour, wherein two image contours are gray-scale images, the required image contour can be obtained only by carrying out binarization processing on the gray-scale images, the two images are compared, and data are output to screen qualified products.
Examples
The embodiment of the invention adopts an egg-shaped annular workpiece without reference requirement. And collecting the most critical annular curved surface profile as a data source of the detection method.
The embodiment of the invention provides a free-form surface profile degree detection method based on machine vision, which is characterized by comprising the following steps of:
step 1: after the detection is started, acquiring a digital image of the annular workpiece;
step 2: preprocessing the collected image;
and step 3: carrying out edge acquisition on the preprocessed image;
step 4: matching the images after the process;
and 5: outputting the matched camera contour data;
step 6: comparing the camera image profile data with the template image profile data;
and 7: and setting a threshold value to screen the final contour data so as to obtain qualified products within the threshold value range.
Wherein said acquiring a digital image of a workpiece comprises the steps of:
(1) an illumination system: an LED annular light source is adopted. During image acquisition, the maximum contrast is generated between the important features of the detected annular workpiece and the features of the background image, and feature differentiation is easy to perform;
(2) an optical imaging system: an industrial CCD camera and a 13 mm lens are adopted, and the installation positions are above the workpiece and at the right side (under the front view) of the workpiece;
(3) a software system: the image acquisition software part is operated by an industrial personal computer;
(4) mechanical motion control system: a clamping device for positioning the workpiece and a conveying belt for conveying the workpiece on a simulation assembly line are adopted;
the step 2 comprises the following steps:
carrying out distortion processing on the collected image, setting the resolution ratio of the collected image to be the same as that of the digital image by adopting a convolutional neural network technology, analyzing a possibly generated distortion form, and cutting the image to a required size according to the proportion of a detection window;
the step 3 comprises the following steps:
(1) edge detection: when the preprocessed image is detected, smoothing the image by adopting a Gaussian filter, so that the value of each pixel point of the image is obtained by weighting and averaging the pixel point of the image and other pixel values in the neighborhood; the Sobel operator is adopted to carry out edge detection on the gray level image, so that the target can be simply realized while noise is suppressed;
(2) edge extraction: and obtaining a binary image after edge detection, wherein the binary image is an extracted image.
The step 4 further comprises:
(1) the process of the matching algorithm is as follows: the two image outlines have the same position orientation and suitable proportion through the steps of translation, rotation, scaling and the like;
(2) calibrating 10-15 pixel points as image contour feature points; searching an optimal solution of the matching path according to dynamic planning, and performing in a circular domain within a certain range;
(3) the offsets of the feature points are calculated from the resolution of the image, the coordinates of the key points, etc.
The step 6 comprises the following steps: setting the CAD three-dimensional model as standard template image contour data, using the image after the above steps as camera image contour data, and carrying out image comparison.
The image acquisition equipment described in this embodiment takes a picture of the annular workpiece, acquires 10-15 images, and introduces them into the processing system for analysis.
The detection method provided by the present invention is further described below, and as shown in fig. 1, fig. 2, and fig. 3, the method includes three parts, namely, a detection process to collect a hierarchical process and an implementation manner.
Wherein, the detection process is shown in fig. 1, and comprises:
(1) an illumination system: an LED annular light source is adopted. During image acquisition, the maximum contrast is generated between the important features of the detected annular workpiece and the features of the background image, and feature differentiation is easy to perform;
(2) an optical imaging system: an industrial CCD camera and a 13 mm lens are adopted, and the installation positions are above the workpiece and at the right side (under the front view) of the workpiece;
(3) a software system: the image acquisition software part is operated by an industrial personal computer;
(4) mechanical motion control system: the clamping device for positioning the workpiece and the conveying belt for conveying the workpiece on the simulation assembly line are adopted.
The collection grading process is shown in fig. 2, and includes:
(5) carrying out distortion processing on the collected image, setting the resolution ratio of the collected image to be the same as that of the digital image by adopting a convolutional neural network technology, analyzing a possibly generated distortion form, and cutting the image to a required size according to the proportion of a detection window;
(6) edge detection: when the preprocessed image is detected, smoothing the image by adopting a Gaussian filter, so that the value of each pixel point of the image is obtained by weighting and averaging the pixel point of the image and other pixel values in the neighborhood; the Sobel operator is adopted to carry out edge detection on the gray level image, so that the target can be simply realized while noise is suppressed;
(7) edge extraction: and obtaining a binary image after edge detection, wherein the binary image is an extracted image.
The embodiment is shown in fig. 3, and comprises: the industrial CCD camera is kept fixed through the mounting frame, has a certain height from the detection workpiece and is arranged above the vertical workpiece. The camera is aimed at detecting the workpiece, the conveying belt conveys the workpiece to the acquisition area, and the programmable controller suspends the operation of the conveying belt so as to acquire and match images. When the system collects images, the LED annular light source sets the most suitable brightness and exposure time to generate the maximum contrast between the important characteristics of the measured object and the background image characteristics, the image of the workpiece is collected through the image collecting system, and a digital signal is output to the computer to obtain the required measuring data. And after the collection is finished, the conveyor belt continues to move. Processing the collected image and collecting the edge, extracting the needed camera image outline for image matching, and outputting the matched image. The image of the standard two-dimensional drawing is input into a detection system to be used as the template image contour, wherein two image contours are gray-scale images, the required image contour can be obtained only by carrying out binarization processing on the gray-scale images, the two images are compared, and data are output to screen qualified products.
In the detection method, the image acquisition equipment shoots the workpiece, acquires 10-15 images and introduces the images into the processing system for analysis.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will 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; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (7)
1. A method for detecting the profile tolerance of a free-form surface based on machine vision is characterized by comprising the following steps: step 1: after the detection is started, acquiring a digital image of the workpiece; step 2: preprocessing the collected image; and step 3: carrying out edge acquisition on the preprocessed image; step 4: matching the images after the process; and 5: outputting the matched camera contour data; step 6: comparing the camera image profile data with the template image profile data; and 7: and setting a threshold value to screen the final contour data so as to obtain qualified products within the threshold value range.
2. The method for detecting the free-form surface profile based on machine vision according to claim 1, wherein the step of acquiring the digital image of the workpiece comprises the following steps: (1) an illumination system: the LED annular light source is adopted, so that the maximum contrast is generated between the important characteristics of the detected annular workpiece and the background image characteristics during image acquisition, and characteristic distinguishing is easy to perform; (2) an optical imaging system: an industrial CCD camera and a 13 mm lens are adopted, and the installation positions are above the workpiece and at the right side (under the front view) of the workpiece; (3) a software system: the image acquisition software part is operated by an industrial personal computer; (4) mechanical motion control system: the clamping device for positioning the workpiece and the conveying belt for conveying the workpiece on the simulation assembly line are adopted.
3. The method for detecting the free-form surface profile based on the machine vision according to claim 1, wherein the step 2 comprises: and carrying out distortion processing on the acquired image, setting the resolution of the acquired image to be the same as that of the digitized image by adopting a convolutional neural network technology, analyzing a possibly generated distortion form, and cutting the acquired image to a required size according to the proportion of a detection window.
4. The method for detecting the free-form surface profile based on machine vision according to claim 1, wherein the step 3 comprises: (1) edge detection: when the preprocessed image is detected, smoothing the image by adopting a Gaussian filter, so that the value of each pixel point of the image is obtained by weighting and averaging the pixel point of the image and other pixel values in the neighborhood; the Sobel operator is adopted to carry out edge detection on the gray level image, so that the target can be simply realized while noise is suppressed; (2) edge extraction: and obtaining a binary image after edge detection, wherein the binary image is an extracted image.
5. The method for detecting the free-form surface profile based on the machine vision according to claim 1, wherein the step 4 comprises: (1) the process of the matching algorithm is as follows: the two image outlines have the same position orientation and suitable proportion through the steps of translation, rotation, scaling and the like; (2) calibrating 10-15 pixel points as image contour feature points; searching an optimal solution of the matching path according to dynamic planning, and performing in a circular domain within a certain range; (3) the offsets of the feature points are calculated from the resolution of the image, the coordinates of the key points, etc.
6. The method for detecting the free-form surface profile based on machine vision according to claim 1, wherein the step 6 comprises: setting the CAD three-dimensional model as standard template image contour data, using the image after the above steps as camera image contour data, and carrying out image comparison.
7. The method for detecting the profile degree of the free-form surface based on the machine vision as claimed in claim 2, wherein the image acquisition equipment photographs the workpiece, and the acquired image is imported into a processing system for analysis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110010571.3A CN113847881A (en) | 2021-01-06 | 2021-01-06 | Free-form surface profile tolerance detection method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110010571.3A CN113847881A (en) | 2021-01-06 | 2021-01-06 | Free-form surface profile tolerance detection method based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113847881A true CN113847881A (en) | 2021-12-28 |
Family
ID=78972178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110010571.3A Pending CN113847881A (en) | 2021-01-06 | 2021-01-06 | Free-form surface profile tolerance detection method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113847881A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114608405A (en) * | 2022-03-23 | 2022-06-10 | 深圳数码模汽车技术有限公司 | Integrated detection method for automobile part contour and hole position |
| CN114986633A (en) * | 2022-05-05 | 2022-09-02 | 四川大学 | Machine vision-based automatic selection system and method for original bamboo splitting tool |
| CN116087217A (en) * | 2023-04-10 | 2023-05-09 | 湖北工业大学 | Industrial assembly line dynamic quality detection module and method based on machine vision |
| CN116626036A (en) * | 2023-05-24 | 2023-08-22 | 北京盛和信科技股份有限公司 | Appearance quality inspection method and system based on machine vision recognition |
| CN117455221A (en) * | 2023-12-25 | 2024-01-26 | 青岛可颂食品有限公司 | Processing flow management system suitable for baking cream |
-
2021
- 2021-01-06 CN CN202110010571.3A patent/CN113847881A/en active Pending
Non-Patent Citations (2)
| Title |
|---|
| 年雷 等: "基于机器视觉的自由曲面轮廓度检测系统", 电子科技 * |
| 陈展鸿: "基于计算机视觉算法的图像处理技术", 电子世界 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114608405A (en) * | 2022-03-23 | 2022-06-10 | 深圳数码模汽车技术有限公司 | Integrated detection method for automobile part contour and hole position |
| CN114986633A (en) * | 2022-05-05 | 2022-09-02 | 四川大学 | Machine vision-based automatic selection system and method for original bamboo splitting tool |
| CN116087217A (en) * | 2023-04-10 | 2023-05-09 | 湖北工业大学 | Industrial assembly line dynamic quality detection module and method based on machine vision |
| CN116626036A (en) * | 2023-05-24 | 2023-08-22 | 北京盛和信科技股份有限公司 | Appearance quality inspection method and system based on machine vision recognition |
| CN116626036B (en) * | 2023-05-24 | 2024-04-02 | 北京盛和信科技股份有限公司 | Appearance quality inspection method and system based on machine vision recognition |
| CN117455221A (en) * | 2023-12-25 | 2024-01-26 | 青岛可颂食品有限公司 | Processing flow management system suitable for baking cream |
| CN117455221B (en) * | 2023-12-25 | 2024-03-26 | 青岛可颂食品有限公司 | Processing flow management system suitable for baking cream |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113847881A (en) | Free-form surface profile tolerance detection method based on machine vision | |
| CN109856164B (en) | Optimization device for acquiring large-range images by machine vision and detection method thereof | |
| CN107891012B (en) | Pearl size and circularity sorting device based on equivalent algorithm | |
| CN110174065B (en) | Fruit size nondestructive testing method based on orthogonal binocular machine vision | |
| CN211070921U (en) | Instrument appearance detection device based on 3D scanning method | |
| CN112001917A (en) | Machine vision-based geometric tolerance detection method for circular perforated part | |
| CN109916914B (en) | Product defect detection method and device | |
| Labudzki et al. | The essence and applications of machine vision | |
| CN112893172A (en) | Gasket size detection system and method based on machine vision, processing terminal and medium | |
| CN113822810A (en) | Method for positioning workpiece in three-dimensional space based on machine vision | |
| CN109622404B (en) | Automatic sorting system and method for micro-workpieces based on machine vision | |
| CN111815575B (en) | Bearing steel ball part detection method based on machine vision | |
| CN113205499A (en) | Bearing defect modular detection device and method based on machine vision | |
| CN111833350A (en) | Machine vision detection method and system | |
| CN114964032B (en) | Blind hole depth measurement method and device based on machine vision | |
| CN111475016A (en) | Assembly process geometric parameter self-adaptive measurement system and method based on computer vision | |
| García et al. | Rail surface inspection system using differential topographic images | |
| CN115184362A (en) | Rapid defect detection method based on structured light projection | |
| CN109632815A (en) | Surface defect on-line detecting system and method | |
| Lei et al. | Automated vision inspection system for the size measurement of workpieces | |
| CN112763495A (en) | Mobile phone battery size and appearance defect detection system and detection method | |
| Zhang et al. | Automatic optical defect inspection and dimension measurement of drill bit | |
| CN114280075B (en) | Online visual detection system and detection method for surface defects of pipe parts | |
| Charles et al. | Survey Paper on Visual Inspection of a Mechanical Part using Machine Learning | |
| Kai et al. | Cob angle recognition algorithm based on machine vision |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20211228 |