CN107490582B - Assembly line workpiece detection system - Google Patents
Assembly line workpiece detection system Download PDFInfo
- Publication number
- CN107490582B CN107490582B CN201710855820.2A CN201710855820A CN107490582B CN 107490582 B CN107490582 B CN 107490582B CN 201710855820 A CN201710855820 A CN 201710855820A CN 107490582 B CN107490582 B CN 107490582B
- Authority
- CN
- China
- Prior art keywords
- crack
- image
- workpiece
- workpiece surface
- detection
- 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.)
- Active
Links
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
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides a production line workpiece detection system, which is characterized by comprising: a conveying device for conveying the workpiece to a detection area through a conveyor belt; the image acquisition module is used for shooting a surface image of the workpiece in the detection area; the image processing module is connected with the image acquisition module and is used for enhancing and detecting the shot workpiece surface image and extracting crack characteristics; the statistical analysis module is connected with the image processing module and used for analyzing cracks and obtaining corresponding workpiece surface detection results; a display module: and the statistical analysis module is connected with the workpiece surface detection module and is used for displaying the workpiece surface detection result. The invention carries out appearance detection on the processed workpieces one by one, eliminates a plurality of defects of manual detection, improves the working efficiency of product detection, and enhances the production efficiency and economic benefit of enterprises.
Description
Technical Field
The invention relates to the field of automatic workpiece detection equipment, in particular to a production line workpiece detection system.
Background
In the mechanical line production, the machined mechanical workpiece usually needs to be subjected to the last process, namely appearance detection, to see whether the production requirements are met. However, in the prior art, the appearance quality of a mechanical workpiece is generally inspected manually, a large amount of manpower is occupied, and due to the influence of factors such as individual eyesight, emotion, fatigue and light, the inspection efficiency is low, the sorting difference is large, the production efficiency and economic benefit of enterprises are reduced, and the market competitiveness of the mechanical industry is influenced. The price of the imported equipment is high, the maintenance period after the equipment is sold is long, and the normal production of enterprises can be seriously influenced once the problem of failure occurs.
Disclosure of Invention
In view of the above problems, the present invention is directed to a road crack detection device.
The purpose of the invention is realized by adopting the following technical scheme:
an in-line workpiece inspection system comprising:
a conveying device for conveying the workpiece to a detection area through a conveyor belt;
the image acquisition module is used for shooting a surface image of the workpiece in the detection area;
the image processing module is connected with the image acquisition module and is used for enhancing and detecting the shot workpiece surface image and extracting crack characteristics;
the statistical analysis module is connected with the image processing module and used for analyzing cracks and obtaining corresponding workpiece surface detection results;
a display module: and the statistical analysis module is connected with the workpiece surface detection module and is used for displaying the workpiece surface detection result.
Preferably, the image acquisition device comprises a CCD camera and a mechanical arm for bearing and adjusting the shooting position of the CCD camera.
Preferably, the image processing module includes a brightness correction unit, a denoising filter processing unit, an image enhancement unit and a crack detection segmentation unit, which are connected in sequence, wherein:
the brightness correction unit is used for carrying out light ray non-uniformity correction on the workpiece surface image, removing a shadow part in the image and acquiring the workpiece surface image after brightness correction;
the de-noising and filtering processing unit is used for carrying out de-noising and filtering processing on the workpiece surface image after the brightness correction to obtain a de-noised workpiece surface image;
the image enhancement unit is used for enhancing the denoised workpiece surface image to obtain an enhanced workpiece surface image;
and the crack detection and segmentation unit is used for carrying out crack edge detection and crack segmentation on the enhanced workpiece surface image and acquiring a segmented workpiece surface crack image.
Preferably, the statistical analysis module includes a crack identification unit and a detection result generation unit, wherein:
the crack identification unit is used for carrying out crack identification on the segmented workpiece surface crack image to obtain a crack identification result;
and the detection result generating unit is used for generating a workpiece surface detection result according to the crack identification result and sending the workpiece surface detection result to the display module.
The invention has the beneficial effects that: the invention is arranged on the last procedure of the mechanical assembly line, and performs appearance detection on the processed workpieces one by one to obtain whether the workpieces have surface defects or not, thereby eliminating a plurality of defects of manual detection, improving the working efficiency of product detection, and enhancing the production efficiency and economic benefit of enterprises.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
FIG. 1 is a block diagram of the frame of the present invention;
FIG. 2 is a block diagram of the image processing module according to the present invention;
FIG. 3 is a block diagram of a statistical analysis module according to the present invention.
Reference numerals:
the device comprises an image acquisition module 1, an image processing module 2, a statistical analysis module 3, a display module 4, a brightness correction unit 20, a denoising and filtering processing unit 21, an image enhancement unit 22, a crack detection and segmentation unit 23, a crack identification unit 30 and a detection result generation unit 31
Detailed Description
The invention is further described in connection with the following application scenarios.
Referring to fig. 1, an in-line workpiece inspection system includes:
a conveying device for conveying the workpiece to a detection area through a conveyor belt;
the image acquisition module 1 is used for shooting a surface image of a workpiece in a detection area;
the image processing module 2 is connected with the image acquisition module 1 and is used for enhancing and detecting the shot workpiece surface image and extracting crack characteristics;
the statistical analysis module 3 is connected with the image processing module 2 and used for analyzing cracks and obtaining corresponding workpiece surface detection results;
the display module 4: and the statistical analysis module 3 is connected with the workpiece surface detection device and is used for displaying the workpiece surface detection result.
Preferably, the image acquisition device 1 comprises a CCD camera and a mechanical arm for carrying and adjusting the shooting position of the CCD camera.
Preferably, referring to fig. 2, the image processing module 2 includes a brightness correction unit 20, a denoising filter processing unit 21, an image enhancement unit 22 and a crack detection segmentation unit 23 connected in sequence, wherein:
a brightness correction unit 20, configured to perform light unevenness correction on the workpiece surface image, remove a shadow portion in the image, and obtain a brightness-corrected workpiece surface image;
a denoising filter processing unit 21, configured to perform denoising filter processing on the brightness-corrected workpiece surface image to obtain a denoised workpiece surface image;
the image enhancement unit 22 is configured to perform enhancement processing on the de-noised workpiece surface image to obtain an enhanced workpiece surface image;
and the crack detection and segmentation unit 23 is used for performing crack edge detection and crack segmentation processing on the enhanced workpiece surface image to acquire a segmented workpiece surface crack image.
Preferably, referring to fig. 3, the statistical analysis module 3 includes a crack identification unit 30 and a detection result generation unit 31, wherein:
the crack identification unit 30 is used for performing crack identification on the segmented workpiece surface crack image to obtain a crack identification result;
and the detection result generating unit 31 is used for generating a workpiece surface detection result according to the crack identification result and sending the workpiece surface detection result to the display module.
According to the embodiment of the invention, the invention is arranged on the last process of the mechanical assembly line, and the appearance of the processed workpieces is detected one by one to obtain whether the workpieces have surface defects or not, so that various defects of manual detection are eliminated, the working efficiency of product detection is improved, and the production efficiency and economic benefit of enterprises are enhanced.
Preferably, the brightness correction unit is configured to perform light unevenness correction on the workpiece surface image, remove a shadow portion in the image, and obtain a brightness-corrected workpiece surface image, specifically:
(1) performing gray-scale morphological closed operation on the surface image of the workpiece, removing surface cracks in the image, and performing smoothing treatment by adopting a two-dimensional Gaussian smoothing method to obtain a smooth workpiece image;
(2) dividing the smooth workpiece image into regions with different brightness levels { Pk1,2, …, U, …, K }, so that the region P is a region PkContaining the value of the luminance Y e (T)k-1,Tk]All pixels of (2), wherein TkRepresenting a set luminance threshold, K representing the number of divided luminance levels, 0 ≦ T1≤T2≤…≤TK-1≤255，T0＝0，TK255 with different luminance thresholds TkIs set so that each luminance level region PkThe number of the contained pixel points is the same;
(3) selecting U areas C ═ C with lower brightness levelk＝PkI K1, 2, …, U as a shadow region, and the remaining K-U regions V with higher luminance levels { V ═ V-k＝PkTaking | K ═ U +1, U +2, …, K } as a non-shadow region, and corresponding the shadow region and the non-shadow region to the workpiece surface image;
(4) and performing brightness compensation on the surface image of the workpiece, wherein the adopted self-defined brightness compensation function is as follows:
in the formula, Y' (i, j) represents the brightness value of the pixel (i, j) after the brightness compensation, Y (i, j) represents the brightness value of the pixel (i, j) in the original image, and σCAnd σVThe standard deviations of the luminance values of the pixels representing the shadow area and the non-shadow area respectively,
and
respectively, the average luminance values of the shaded and unshaded regions.
In the preferred embodiment, the method is adopted to perform the light ray unevenness correction and the brightness compensation processing on the workpiece surface image, divide the workpiece surface image into different areas according to different brightness levels, accurately acquire the shadow area, and perform the brightness compensation correction on the brightness shadow area, so that the shadow part in the image can be effectively removed, the influence of the shadow part on the subsequent workpiece surface detection is eliminated, and the accuracy and the adaptability of the system are improved.
Preferably, the crack detection and segmentation unit is configured to perform crack edge detection and crack segmentation processing on the enhanced workpiece surface image, and acquire a segmented workpiece surface crack image, specifically:
(1) for the enhanced workpiece surface image EzCarrying out outline structural element corrosion operation to obtain a corroded image EfWherein
The method comprises the steps of representing an erosion operation symbol, and e representing the outline of a set structural element;
(2) for the enhanced workpiece surface image EzCarrying out contour structure element expansion operation to obtain an expanded image EpWherein
A symbol indicating an expansion operation, and e indicates the outline of the set structural element;
(3) obtaining an enhanced workpiece surface image EzAnd the mutation value of each pixel point to the background brightness, wherein the adopted mutation value acquisition function is as follows:
in the formula (I), the compound is shown in the specification,
representing the abrupt change of the pixel point (i, j) with respect to the background brightness, Ez(i, j) represents the gray value of the pixel point (i, j) of the enhanced workpiece surface image, Ef(i, j) is a graph after etchingGray value of the image pixel point (i, j), Ep(i, j) represents the gray value of the expanded image pixel point (i, j);
(4) obtaining an enhanced workpiece surface image EzAnd the distinguishable brightness difference threshold value of each pixel point is defined as follows:
in the formula, Δ ∈ (i, j) represents a threshold value of distinguishable luminance difference, Y (i, j) represents a background luminance value of the pixel point (i, j), λ, μ, θ are parameters of the set threshold model of distinguishable luminance difference, respectively, Y1And y2Luminance threshold values respectively representing low dark areas and high bright areas;
(5) and carrying out edge detection on the enhanced workpiece surface image, wherein the adopted edge detection function is as follows:
in the formula, xi (i, j) represents the edge detection result of the image pixel point (i, j),
representing the abrupt change value of the pixel point (i, j) to the background brightness, and delta epsilon (i, j) representing a resolvable brightness difference threshold model;
(6) and marking the pixel point which accords with xi (i, j) 1 as an edge pixel point, and segmenting the crack part of the workpiece according to the edge pixel point.
In the preferred embodiment, the method is adopted for inner crack segmentation, firstly, the brightness mutation value and the distinguishable brightness difference threshold value of each pixel point are obtained in the image to be processed, and are compared to obtain the crack edge point in the image, so that the crack part is accurately segmented, the accuracy is high, and a foundation is laid for the subsequent system to identify the cracks on the surface of the workpiece.
Preferably, the crack recognition unit is configured to perform crack recognition on the segmented workpiece surface crack image, and obtain a crack recognition result, specifically:
(1) performing binarization processing on the segmented workpiece surface crack image, wherein the crack part of the workpiece is represented by white pixels, namely B (i, j) is 1; the remaining background areas are represented by black pixels, i.e., B (i, j) ═ 0;
(2) counting the number of pixel points of the crack part of the workpiece in the segmented workpiece surface crack image
Wherein H × L represents the size of the image of the surface crack of the workpiece after segmentation, if kcIf the value is 0, the crack target does not exist in the workpiece surface image; otherwise, determining that the surface image of the workpiece has a crack target;
(3) identifying the type of the crack target, specifically comprising the following steps:
(31) acquiring the geometric centroid coordinate (i) of the crack target according to the crack part of the workpiecec,jc) To (i) withc,jc) Taking a square area with the side length of 2r +1 as a center, and counting the number of crack area pixel points in the square area as kz；
(32) If it is not
Calculating a crack distribution factor
Otherwise, taking r as r +10 and jumping to the step (31);
(33) factor ζ of crack distributionsJudging if the crack distribution factor is less than the first threshold value phi1Then the crack target can be considered as a strip crack; if the crack distribution factor is at a set first threshold value phi1And a second threshold value phi2In between, the crack target can be considered as a block crack; the crack distribution factor is larger than a set second threshold value phi2Then the crack target may be considered a web crack; wherein phi1<Φ2。
In the preferred embodiment, the method is adopted for crack identification, the crack distribution factor of the crack part is firstly calculated to serve as the characteristic value of crack distribution, then the type of the crack is accurately judged according to the crack distribution factor, the adaptability is strong, and the method can be suitable for real-time judgment of the crack on the surface of the workpiece by a system.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be analyzed by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (3)
1. An in-line workpiece inspection system, comprising:
a conveying device for conveying the workpiece to a detection area through a conveyor belt;
the image acquisition module is used for shooting a surface image of the workpiece in the detection area;
the image processing module is connected with the image acquisition module and is used for enhancing and detecting the shot workpiece surface image and extracting crack characteristics;
the statistical analysis module is connected with the image processing module and used for analyzing cracks and obtaining corresponding workpiece surface detection results;
a display module: the statistical analysis module is connected with the workpiece surface detection device and is used for displaying the workpiece surface detection result;
the image acquisition device comprises a CCD camera and a mechanical arm for bearing and adjusting the shooting position of the CCD camera;
the image processing module comprises a brightness correction unit, a denoising and filtering processing unit, an image enhancement unit and a crack detection and segmentation unit which are sequentially connected, wherein:
the brightness correction unit is used for carrying out light ray non-uniformity correction on the workpiece surface image, removing a shadow part in the image and acquiring the workpiece surface image after brightness correction;
the de-noising and filtering processing unit is used for carrying out de-noising and filtering processing on the workpiece surface image after the brightness correction to obtain a de-noised workpiece surface image;
the image enhancement unit is used for enhancing the denoised workpiece surface image to obtain an enhanced workpiece surface image;
the crack detection and segmentation unit is used for carrying out crack edge detection and crack segmentation on the enhanced workpiece surface image to obtain a segmented workpiece surface crack image;
wherein, the statistical analysis module comprises a crack identification unit and a detection result generation unit, wherein:
the crack identification unit is used for carrying out crack identification on the segmented workpiece surface crack image to obtain a crack identification result;
the detection result generating unit is used for generating a workpiece surface detection result according to the crack identification result and sending the workpiece surface detection result to the display module;
the brightness correction unit specifically comprises:
(1) performing gray-scale morphological closed operation on the surface image of the workpiece, removing surface cracks in the image, and performing smoothing treatment by adopting a two-dimensional Gaussian smoothing method to obtain a smooth workpiece image;
(2) dividing the smooth workpiece image into regions with different brightness levels { Pk1,2, …, U, …, K }, so that the region P is a region PkContaining the value of the luminance Y e (T)k-1,Tk]All pixels of (2), wherein TkRepresenting a set luminance threshold, K representing the number of divided luminance levels, 0 ≦ T1≤T2≤…≤TK-1≤255，T0＝0，TK255 with different luminance thresholds TkIs set so that each luminance level region PkThe number of the contained pixel points is the same;
(3) selecting U areas C ═ C with lower brightness levelk＝Pk1, 2.., U } as a shadow region, and the remaining K-U as a shadow regionRegion V ═ V with higher luminance levelk＝PkTaking | K ═ U +1, U +2, …, K } as a non-shadow region, and corresponding the shadow region and the non-shadow region to the workpiece surface image;
(4) and performing brightness compensation on the surface image of the workpiece, wherein the adopted self-defined brightness compensation function is as follows:
in the formula, Y' (i, j) represents the brightness value of the pixel (i, j) after the brightness compensation, Y (i, j) represents the brightness value of the pixel (i, j) in the original image, and σCAnd σVThe standard deviations of the luminance values of the pixels representing the shadow area and the non-shadow area respectively,
and
respectively, the average luminance values of the shaded and unshaded regions.
2. The assembly line workpiece detection system according to claim 1, wherein the crack detection and segmentation unit is configured to perform crack edge detection and crack segmentation processing on the enhanced workpiece surface image to obtain a segmented workpiece surface crack image, and specifically:
(1) for the enhanced workpiece surface image EzCarrying out outline structural element corrosion operation to obtain a corroded image EfWherein
The method comprises the steps of representing an erosion operation symbol, and e representing the outline of a set structural element;
(2) to pairEnhanced workpiece surface image EzCarrying out contour structure element expansion operation to obtain an expanded image EpWherein
A symbol indicating an expansion operation, and e indicates the outline of the set structural element;
(3) obtaining an enhanced workpiece surface image EzAnd the mutation value of each pixel point to the background brightness, wherein the adopted mutation value acquisition function is as follows:
in the formula (I), the compound is shown in the specification,
representing the abrupt change of the pixel point (i, j) with respect to the background brightness, Ez(i, j) represents the gray value of the pixel point (i, j) of the enhanced workpiece surface image, Ef(i, j) represents the gray value of the pixel point (i, j) of the image after corrosion, Ep(i, j) represents the gray value of the expanded image pixel point (i, j);
(4) obtaining an enhanced workpiece surface image EzAnd the distinguishable brightness difference threshold value of each pixel point is defined as follows:
in the formula, Δ ∈ (i, j) represents a threshold value of distinguishable luminance difference, Y (i, j) represents a background luminance value of the pixel point (i, j), λ, μ, θ are parameters of the set threshold model of distinguishable luminance difference, respectively, Y1And y2Luminance threshold values respectively representing low dark areas and high bright areas;
(5) and carrying out edge detection on the enhanced workpiece surface image, wherein the adopted edge detection function is as follows:
in the formula, xi (i, j) represents the edge detection result of the image pixel point (i, j),
representing the abrupt change value of the pixel point (i, j) to the background brightness, and delta epsilon (i, j) representing a resolvable brightness difference threshold model;
(6) and marking the pixel point which accords with xi (i, j) 1 as an edge pixel point, and segmenting the crack part of the workpiece according to the edge pixel point.
3. The assembly line workpiece detection system according to claim 2, wherein the crack recognition unit is configured to perform crack recognition on the segmented workpiece surface crack image to obtain a crack recognition result, and specifically:
(1) performing binarization processing on the segmented workpiece surface crack image, wherein the crack part of the workpiece is represented by white pixels, namely B (i, j) is 1; the remaining background areas are represented by black pixels, i.e., B (i, j) ═ 0;
(2) counting the number of pixel points of the crack part of the workpiece in the segmented workpiece surface crack image
Wherein H × L represents the size of the image of the surface crack of the workpiece after segmentation, if kcIf the value is 0, the crack target does not exist in the workpiece surface image; otherwise, determining that the surface image of the workpiece has a crack target;
(3) identifying the type of the crack target, specifically comprising the following steps:
(31) acquiring the geometric centroid coordinate (i) of the crack target according to the crack part of the workpiecec,jc) To (i) withc,jc) Taking a square area with the side length of 2r +1 as a center, and counting the number of crack area pixel points in the square area as kzWherein icAnd jcRespectively representing the abscissa and the ordinate of the geometric centroid of the crack target, and r represents a side length setting parameter;
(32) if it is not
Calculating a crack distribution factor
Otherwise, taking r as r +10 and jumping to the step (31);
(33) factor ζ of crack distributionsJudging if the crack distribution factor is less than the first threshold value phi1Then the crack target can be considered as a strip crack; if the crack distribution factor is at a set first threshold value phi1And a second threshold value phi2In between, the crack target can be considered as a block crack; the crack distribution factor is larger than a set second threshold value phi2Then the crack target may be considered a web crack; wherein phi1<Φ2。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710855820.2A CN107490582B (en) | 2017-09-20 | 2017-09-20 | Assembly line workpiece detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710855820.2A CN107490582B (en) | 2017-09-20 | 2017-09-20 | Assembly line workpiece detection system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107490582A CN107490582A (en) | 2017-12-19 |
| CN107490582B true CN107490582B (en) | 2021-03-16 |
Family
ID=60651819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710855820.2A Active CN107490582B (en) | 2017-09-20 | 2017-09-20 | Assembly line workpiece detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107490582B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108362705A (en) * | 2018-02-05 | 2018-08-03 | 中达电通股份有限公司 | A kind of toothbrush bristle quantity detection means and its detection method |
| CN108663484A (en) * | 2018-05-09 | 2018-10-16 | 安徽知之信息科技有限公司 | A kind of surface quality detection assembly line of electric vehicle covering |
| CN108764105B (en) * | 2018-05-22 | 2022-03-22 | 广东美的智能机器人有限公司 | Assembly line workpiece identification method, server and terminal |
| CN113822945A (en) * | 2021-09-28 | 2021-12-21 | 天津朗硕机器人科技有限公司 | Workpiece identification and positioning method based on binocular vision |
| CN114723701B (en) * | 2022-03-31 | 2023-04-18 | 厦门力和行自动化有限公司 | Gear defect detection method and system based on computer vision |
| CN114719749B (en) * | 2022-04-06 | 2023-07-14 | 重庆大学 | Metal surface crack detection and real size measurement method and system based on machine vision |
| CN115452844B (en) * | 2022-11-11 | 2023-02-03 | 广东海洋大学 | Injection molding part detection method and system based on machine vision |
| CN116485350B (en) * | 2023-06-20 | 2023-09-01 | 山东鲁玻玻璃科技有限公司 | Intelligent production system of medium borosilicate glass based on image recognition |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102253050A (en) * | 2011-03-14 | 2011-11-23 | 广州市盛通建设工程质量检测有限公司 | Automatic detection method and device for magnetic tile surface defect based on machine vision |
| CN202075755U (en) * | 2011-05-03 | 2011-12-14 | 西安理工大学 | Visual detection device for microcracks on surface of workpiece |
| CN103872983B (en) * | 2014-04-04 | 2016-05-25 | 天津市鑫鼎源科技发展有限公司 | Solar cell surface defect inspection method |
-
2017
- 2017-09-20 CN CN201710855820.2A patent/CN107490582B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107490582A (en) | 2017-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107490582B (en) | Assembly line workpiece detection system | |
| CN108460757B (en) | Mobile phone TFT-LCD screen Mura defect online automatic detection method | |
| CN114937055B (en) | Image self-adaptive segmentation method and system based on artificial intelligence | |
| CN109816652B (en) | Complex casting defect identification method based on gray level significance | |
| CN106780486B (en) | Steel plate surface defect image extraction method | |
| CN115222733B (en) | Metal component surface defect detection method based on image recognition | |
| CN111179243A (en) | Small-size chip crack detection method and system based on computer vision | |
| CN108876768B (en) | Shadow defect detection method for light guide plate | |
| CN112330628A (en) | Metal workpiece surface defect image detection method | |
| CN109472788B (en) | Method for detecting flaw on surface of airplane rivet | |
| CN106780526A (en) | A kind of ferrite wafer alligatoring recognition methods | |
| CN114881915A (en) | Symmetry-based mobile phone glass cover plate window area defect detection method | |
| CN109540925B (en) | Complex ceramic tile surface defect detection method based on difference method and local variance measurement operator | |
| CN109781737B (en) | Detection method and detection system for surface defects of hose | |
| Samarawickrama et al. | Matlab based automated surface defect detection system for ceremic tiles using image processing | |
| CN114549441A (en) | Sucker defect detection method based on image processing | |
| CN112258444A (en) | Elevator steel wire rope detection method | |
| CN116883408B (en) | Integrating instrument shell defect detection method based on artificial intelligence | |
| CN115684176A (en) | Online visual inspection system for film surface defects | |
| CN111539927A (en) | Detection process and algorithm of automobile plastic assembly fastening buckle lack-assembly detection device | |
| CN115272336A (en) | Metal part defect accurate detection method based on gradient vector | |
| CN114581805A (en) | Coating roller surface defect detection method adopting 3D line laser profile technology | |
| CN113298769A (en) | FPC flexible flat cable appearance defect detection method, system and medium | |
| CN114332081B (en) | Textile surface abnormity determination method based on image processing | |
| CN113487563B (en) | EL image-based self-adaptive detection method for hidden cracks of photovoltaic module |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210226 Address after: 211100 Shang Shan District, Tangshan industrial concentration area, Jiangning District, Nanjing, Jiangsu Applicant after: Nanjing Guangquan Technology Co.,Ltd. Address before: 518000 B356, 2124 Li Wan mansion, Nanhai street, Nanshan District, Shenzhen, Guangdong. Applicant before: SHENZHEN SHENGDA MACHINERY DESIGN Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |