CN102680478A - Detection method and device of surface defect of mechanical part based on machine vision - Google Patents
Detection method and device of surface defect of mechanical part based on machine vision Download PDFInfo
- Publication number
- CN102680478A CN102680478A CN2012101241769A CN201210124176A CN102680478A CN 102680478 A CN102680478 A CN 102680478A CN 2012101241769 A CN2012101241769 A CN 2012101241769A CN 201210124176 A CN201210124176 A CN 201210124176A CN 102680478 A CN102680478 A CN 102680478A
- Authority
- CN
- China
- Prior art keywords
- image
- machine
- detection
- drive axle
- component
- Prior art date
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 16
- 230000005540 biological transmission Effects 0.000 claims abstract description 14
- 238000001914 filtration Methods 0.000 claims abstract description 5
- 238000000034 methods Methods 0.000 claims description 8
- 241000270322 Lepidosauria Species 0.000 claims description 6
- 230000002950 deficient Effects 0.000 claims description 6
- 241001157067 Leucoagaricus meleagris Species 0.000 claims description 3
- 238000006243 chemical reactions Methods 0.000 claims description 3
- 230000002708 enhancing Effects 0.000 claims description 3
- 230000001429 stepping Effects 0.000 claims description 3
- 230000005347 demagnetization Effects 0.000 abstract description 3
- 230000001788 irregular Effects 0.000 abstract description 2
- 238000000605 extraction Methods 0.000 abstract 1
- 230000000877 morphologic Effects 0.000 abstract 1
- 238000005070 sampling Methods 0.000 description 3
- 238000002604 ultrasonography Methods 0.000 description 3
- 238000010586 diagrams Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering processes Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006011 modification reactions Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Abstract
Description
Technical field
The present invention relates to the surface and detect research field, particularly a kind of component of machine detection method of surface flaw and device based on machine vision.
Background technology
In component of machine processing process; Often need detect, measure it; Because mostly component of machine is to be used to bear certain pressure or to carry out a large amount of to-and-fro movements; Therefore in case the component of machine of producing occurs unusually, then might cause the total system collapse, even cause catastrophic consequence.For example bent axle is the main rotary gadget of engine, load onto connecting rod after, can make accept connecting rod about (back and forth) motion become circulation (rotation) and move, be important parts on the engine.As the dynamic connector of all kinds of engines, if unusual, then possibly cause serious consequence, so the roughness on bent axle surface has been detected as the very important outpost of the tax office together.Detect for component of machine, comprise dual mode at present substantially, a kind of is ultrasound detection; Another kind is the magnetic carrying out flaw detection; But because ultrasound detection is applicable to the tubular member that detects comparison rule, though and the speed that the magnetic flaw detection detects can reach requirement, demagnetization fully basically; This might cause tremendous influence to the performance of engine, and the operation more complicated.Traditional detection method is also normally artificial at present comes the bent axle surface imperfection is judged that not only inefficiency, and cost of labor is high according to its experience and naked-eye observation, personnel labor intensity is big, is prone to make mistakes, and can not satisfy the needs of current high-speed production.
Therefore, component of machine detection method of surface flaw and the device that a kind of automaticity is high, recognition speed is fast, accuracy of identification is high need be provided.
Summary of the invention
The shortcoming that fundamental purpose of the present invention is to overcome prior art is with not enough; A kind of component of machine detection method of surface flaw based on machine vision is provided; This method is to utilize machine vision that component of machine is detected, and accuracy of detection is high, recognition speed is fast, and automaticity is high.The present invention also provides a kind of component of machine surface defect detection apparatus based on machine vision of realizing said method, and this device accuracy of detection is high, detection efficiency is high.
One object of the present invention realizes through following technical scheme: a kind of component of machine detection method of surface flaw based on machine vision may further comprise the steps:
(1) parts to be detected is fixed on the anchor clamps, anchor clamps is moved to the place ahead of video camera; Video camera is gathered the surface image of parts to be measured, sends images to then in the host computer;
(2) after the image processing module in the host computer receives the image of collection, operate as follows:
(2-1) image is carried out zone location, intercepting goes out parts to be detected place image-region;
The parts to be detected place image-region that (2-2) step (2-1) is obtained carries out filtering and enhancing;
(2-3) image is carried out binary conversion treatment, use the morphology algorithm to remove impurity then;
(2-4) boundary tracking is carried out in the target area in the resultant image in the step (2-3);
(2-5) according to the boundary tracking result, obtain the number of pixels in each zone to be detected, if this area pixel number greater than certain limit value, then there is defective in the parts of current detection, externally send alerting signal, withdraw from detection; Otherwise, then get into step (3);
(3) judge whether the overall situation is taken completion to parts to be detected, if then withdraw from detection; Otherwise video camera is taken the surface image of next parts to be detected successively, gets into step (2) then, repeats aforesaid operations.
Preferably, adopt average or median filter method in the said step (2-2), histogram equalization is adopted in the figure image intensifying.Adopt average or this spatial domain method of intermediate value to have the counting yield height, a plurality of pixel parallel processings of ability realize advantage such as processing and fast processing in real time.Adopt histogram equalization can improve the visual effect of image, the sharpness of raising iconic element makes the probability of all gray level appearance identical, and at this moment the entropy of image is maximum, and information content of image is maximum.
Preferably, utilization morphology removal impurity specifically is meant in the said step (2-3): the image after the binaryzation is carried out the several times opening operation, and the structural element that opening operation adopted, number of times are confirmed according to actual photographed picture quality and shooting environmental.The morphology opening operation can effectively be removed some smaller noise spots, do not influence the area size of defect part simultaneously again, so eyefidelity is higher, is beneficial to the accuracy that behindness parameter is analyzed as far as possible.
Preferably; Boundary tracking is to adopt worm with method, specifically in the said step (2-4): the image target area of establishing after the processing representes that with 1 the background area is represented with 0; Given reptile starting point is that P0, tracking value are 1, follow the trail of direction for clockwise; P0 adopts following principle to confirm: to image from left to right, scan from top to bottom, first gray-scale value that scans is that 1 pixel is for following the tracks of starting point; The tracking principle is exactly: if the current point pixel value is 1, then turns left and advance a pixel; If the current pixel point value is 0 just to turn right and the pixel of advancing, until reptile climbs to till the starting point.Adopt said method can realize the target area profile is followed the tracks of, use the summation of (comprising borderline) pixel count in the zone to represent area then, represent girth with the boundary pixel summation in zone.Said method can calculate the number of those suspected defects rapidly, comes through the judgement to the area size whether further judgement should the zone be defective then.
Another object of the present invention realizes through following technical scheme: a kind of component of machine surface defect detection apparatus based on machine vision; Comprise position transmission module, position control module, anchor clamps, image capture module, be used for Flame Image Process and send the host computer of position control instruction; Said position transmission module comprises the Z through-drive axle that moves on the Y through-drive axle that moves on the X through-drive axle that moves on framework platform, the directions X, the Y direction, the Z direction; Said X through-drive axle is arranged on the X axis rail; The X axis rail is arranged on the framework platform, and said Y through-drive axle is arranged on the Y axis rail, and the Y axis rail is fixedly installed on the slide block on the X through-drive axle; Said Z through-drive axle is arranged on the Z axis rail; Z axis rail one end is fixedly installed on the slide block on the Y through-drive axle, and the anchor clamps that are used for fixing component of machine to be detected are arranged on the slide block of Z through-drive axle, and the anchor clamps two ends are provided with and are used to drive the rotating disk that component of machine to be detected vertically rotates; Said X through-drive axle, Y through-drive axle, Z through-drive axle and rotating disk link to each other with electric rotating machine with X spindle motor, y-axis motor, Z spindle motor respectively; Above-mentioned four motors all link to each other with position control module, and image capture module comprises video camera and light source, and video camera and light source position are fixed; Light source links to each other with external power source, and video camera links to each other with host computer respectively with position control module.
Preferably, said position control module is a single-chip microcomputer.Adopt single-chip microcomputer speed fast, and can save cost.
Preferably, said X spindle motor, y-axis motor, Z spindle motor and electric rotating machine are stepper motor or servomotor.Adopt the motor of this form, accurately the precision that moves of control position.
Further, said X spindle motor, y-axis motor, Z spindle motor and electric rotating machine are two-phase hybrid stepping motor, and each motor all links to each other with single-chip microcomputer through stepper motor driver.
Preferably, said video camera adopts CCD, and pixel is at 500～1200dpi, and electronic shutter speed was not less than 1/50 second; Light source adopts the annular LED light source.
Preferably, said position transmission module, position control module, anchor clamps, image capture module all are arranged in the airtight casing.Adopt this structure can avoid of the interference of extraneous light, guarantee the stability of image processing algorithm, relatively be applicable to small-scale sampling Detection IMAQ.
The present invention compared with prior art has following advantage and beneficial effect:
1, the present invention has realized lossless detection.In process, cause the enchancement factor of roughness difference many, be difficult to set up precise math model, and obtain indirectly can assess product quality effectively with the relevant parameter of roughness through machine vision technique.
2, the present invention adopts image process method to detect, and compared to ultrasound detection, can detect irregular part, compared to the magnetic flaw detection, does not have the problem of demagnetization, detect compared to the conventional artificial naked eyes, and accuracy of detection, efficient height, and cost of labor is low.
3, adopted three-dimensional position gear train in apparatus of the present invention, can in practical application, be connected with the streamline of producing parts, the parts of for example accomplishing are placed in the anchor clamps automatically; Device according to the invention then starts; After detection finished, according to testing result, the position gear train was put into appointed area etc. with parts automatically; Parts can also rotate simultaneously, realize the comprehensive scanning of parts.
Description of drawings
Fig. 1 is the Facad structure synoptic diagram of apparatus of the present invention;
Fig. 2 is the side structure synoptic diagram of apparatus of the present invention;
Fig. 3 is the schematic flow sheet of the inventive method.
Among Fig. 1-2: 1-bent axle to be detected; The 2-electric rotating machine; The 3-X spindle motor; 4-X through-drive axle; The 5-X axis rail; The 6-Y spindle motor; 7-Y through-drive axle; The 8-Y axis rail; The 9-Z spindle motor; 10-Z through-drive axle; The 11-Z axis rail; The 12-rotating disk; The 13-anchor clamps; The 14-framework platform.
Embodiment
Below in conjunction with embodiment and accompanying drawing the present invention is described in further detail, but embodiment of the present invention is not limited thereto.
Embodiment 1
Bent axle is the main rotary gadget of engine, load onto connecting rod after, can make accept connecting rod about (back and forth) motion become circulation (rotation) and move, be important parts on the engine.Along with the demand of development of science and technology and bent axle increases day by day, the working (machining) efficiency of bent axle also is greatly improved in recent years; While is as the dynamic connector of all kinds of engines; Quality requirements to bent axle also becomes increasingly high; And plant equipment is in operational process, and its inner mechanical component processs bad mechanical component and occurred easily unusually owing to receive the effect of various stress; Cause system crash, even catastrophic accident occurs.Therefore the roughness on bent axle surface has been detected as the very important outpost of the tax office together.
In the present embodiment, detecting with the bent axle surface is example, and particular content of the present invention is described.As illustrated in fig. 1 and 2; A kind of bent axle surface defect detection apparatus based on machine vision; Comprise position transmission module, position control module, anchor clamps 13, image capture module, be used for Flame Image Process and send the host computer of position control instruction; Said position transmission module comprises the Z through-drive axle 10 that moves on the Y through-drive axle 7 that moves on the X through-drive axle 4 that moves on framework platform 14, the directions X, the Y direction, the Z direction, and said X through-drive axle 4 is arranged on the X axis rail 5, and X axis rail 5 is arranged on the framework platform 14; Said Y through-drive axle 7 is arranged on the Y axis rail 8; Y axis rail 8 is fixedly installed on the slide block on the X through-drive axle 4, and said Z through-drive axle 10 is arranged on the Z axis rail 11, and Z axis rail 11 1 ends are fixedly installed on the slide block on the Y through-drive axle 7; The anchor clamps 13 that are used for fixing bent axle to be detected are arranged on the slide block of Z through-drive axle 10; Anchor clamps 13 two ends are provided with and are used to drive the rotating disk 12 that bent axle to be detected vertically rotates, and said X through-drive axle 4, Y through-drive axle 7, Z through-drive axle 10 link to each other with X spindle motor 3, y-axis motor 6, Z spindle motor 9 and electric rotating machine 2 respectively with rotating disk 12, and above-mentioned four motors all link to each other with position control module; Image capture module comprises video camera and light source; Video camera and light source position are fixed, and light source links to each other with external power source, and video camera links to each other with host computer respectively with position control module.
In the present embodiment, said position control module is a single-chip microcomputer.Said X spindle motor 3, y-axis motor 6, Z spindle motor 9 and electric rotating machine 2 are two-phase hybrid stepping motor, and each motor all links to each other with single-chip microcomputer through stepper motor driver.Also available servomotor replaces in practical application.Said video camera adopts CCD, and pixel is at 500～1200dpi, and electronic shutter speed was not less than 1/50 second, and concrete parameter is confirmed according to the actual photographed environment.Light source adopts the annular LED light source.
For fear of of the interference of extraneous light to IMAQ, guarantee the stability of image processing algorithm, position transmission module, position control module, anchor clamps 13, image capture module all are arranged in the airtight casing in the present embodiment.Adopt this texture ratio to be applicable to small-scale sampling Detection.
In practical application, this device also can be connected with the streamline of producing bent axle, and the bent axle of for example accomplishing is placed in the anchor clamps automatically; Device according to the invention then starts, and position control module activation point transmission module is transported to the desired location of video camera front with bent axle, carries out IMAQ, detection; Behind to be detected the finishing, according to testing result, the position gear train is put into the appointed area with parts automatically; For example; If there is defective in the bent axle that detects then bent axle is placed on the defect ware district,, just be placed on another driving-belt and export if no problem.Therefore no matter be that online detection or sampling Detection can realize.
As shown in Figure 3, may further comprise the steps based on the detection method of surface flaw of said apparatus:
(1) bent axle 1 to be detected is fixed on the anchor clamps 13, anchor clamps 13 is moved to the place ahead of video camera; Video camera is gathered the surface image of bent axle to be measured, sends images in the host computer then.Because will detect defective, so the sharpness of image is had relatively high expectations, the image that photographs here is the local surfaces image of bent axle.
(2) after the image processing module in the host computer receives the image of collection, operate as follows:
(2-1) comprise crankshaft region and background area in the captured topography,, accelerate the speed of data processing, at first image is carried out zone location, the intercepting bent axle place image-region in the picture of publishing picture in order to reduce data processing amount; The zone location here both can be the manual interceptings of operating personnel, also can be according to experiment, confirm the position relation of video camera, position transmission module after, carry out automatic intercepting according to the relationship of the two.
The bent axle place image-region that (2-2) step (2-1) is obtained carries out filtering and enhancing;
(2-3) further image is carried out binary conversion treatment, use the morphology algorithm to remove impurity then;
(2-4) to the target area in the resultant image in the step (2-3), promptly the white portion after the binaryzation carries out boundary tracking;
(2-5) according to the boundary tracking result, obtain the number of pixels in each zone to be detected, if this area pixel number greater than certain limit value, then there is defective in the bent axle of current detection, externally sends alerting signal, withdraws from detection; Otherwise, then get into step (3);
(3) judge whether it is last of bent axle; Be bent axle whether the overall situation all through and shooting and detect, if not, then position control module control position transmission module moves; Bent axle is carried out up and down or rotatablely moves; Video camera is taken the surface image of next bent axle successively then, gets into step (2) then, repeats aforesaid operations; If then withdraw from detection.Here judge whether it is last of current bent axle to be detected 1, both can pass through manual control, also can control automatically.For example, set when beginning to detect, begin to take from the top of bent axle, and bent axle is parked in Z axle top, then in one week of crankshaft rotating, and bent axle can think to detect and accomplish when moving to Z axle bottom, withdraws from detection automatically.
In the present embodiment, adopt the mean filter method in the said step (2-2), histogram equalization is adopted in the figure image intensifying.Certainly other known filtering method also is general here, just adopts above-mentioned algorithm, realizes that simply processing speed is fast.
Utilization morphology removal impurity specifically is meant in the said step (2-3): the image after the binaryzation is carried out the several times opening operation, and the structural element that opening operation adopted, number of times are confirmed according to actual photographed picture quality and shooting environmental.
Boundary tracking is to adopt worm with method in the said step (2-4); Specifically: the image target area of establishing after the processing is represented with 1; The background area representes that with 0 given reptile starting point is that P0, tracking value are 1, follow the trail of direction for clockwise, and P0 adopts following principle to confirm: to image from left to right; Scan from top to bottom, first gray-scale value that scans is that 1 pixel is for following the tracks of starting point; The tracking principle is exactly: if the current point pixel value is 1, then turns left and advance a pixel; If the current pixel point value is 0 just to turn right and the pixel of advancing, until reptile climbs to till the starting point.
The foregoing description is a preferred implementation of the present invention; But embodiment of the present invention is not restricted to the described embodiments; Other any do not deviate from change, the modification done under spirit of the present invention and the principle, substitutes, combination, simplify; All should be the substitute mode of equivalence, be included within protection scope of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101241769A CN102680478A (en) | 2012-04-25 | 2012-04-25 | Detection method and device of surface defect of mechanical part based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101241769A CN102680478A (en) | 2012-04-25 | 2012-04-25 | Detection method and device of surface defect of mechanical part based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102680478A true CN102680478A (en) | 2012-09-19 |
Family
ID=46812738
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012101241769A CN102680478A (en) | 2012-04-25 | 2012-04-25 | Detection method and device of surface defect of mechanical part based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102680478A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103056727A (en) * | 2013-01-14 | 2013-04-24 | 南京格蕾飞信息技术有限公司 | Machine vision cutter of CNC (computerized numeral control) machine tool |
| CN103196918A (en) * | 2013-03-22 | 2013-07-10 | 上海理工大学 | Key assembling detection method for vehicle air conditioner control panel |
| CN103456021A (en) * | 2013-09-24 | 2013-12-18 | 苏州大学 | Piece goods blemish detecting method based on morphological analysis |
| CN103454283A (en) * | 2013-09-12 | 2013-12-18 | 电子科技大学 | Line detection system and method |
| CN104089586A (en) * | 2014-07-16 | 2014-10-08 | 浙江大学宁波理工学院 | Image detection device and method of engine crankshaft journal shape errors |
| CN104677839A (en) * | 2015-01-22 | 2015-06-03 | 浙江大学 | Rotary scanning hyperspectral crop stem information acquisition system |
| CN104698145A (en) * | 2013-12-05 | 2015-06-10 | 珠海格力电器股份有限公司 | Flaw detection device for U-shaped pipe |
| CN105139400A (en) * | 2015-08-27 | 2015-12-09 | 任红霞 | Workpiece defect positioning system based on image processing |
| CN105629321A (en) * | 2016-02-24 | 2016-06-01 | 广州市华颉电子科技有限公司 | Integrated device achieving image collection, and automatic optical detection method for three planes |
| CN106770331A (en) * | 2017-02-10 | 2017-05-31 | 南京航空航天大学 | A kind of workpiece, defect detecting system based on machine vision |
| CN106767659A (en) * | 2016-12-20 | 2017-05-31 | 武汉钢铁股份有限公司 | Automatic coarseness measuring apparatus |
| CN107561095A (en) * | 2017-10-10 | 2018-01-09 | 东睦（天津）粉末冶金有限公司 | A kind of vision-based detection auto parts and components equipment or system |
| CN107749058A (en) * | 2017-10-23 | 2018-03-02 | 中南大学 | A kind of machine vision detection method and system of boiler tubing surface defect |
| CN107991314A (en) * | 2017-11-23 | 2018-05-04 | 苏州艺力鼎丰智能技术有限公司 | A kind of carbon fiber surface of automobile part printed matter defect intelligent detection equipment |
| CN108279241A (en) * | 2017-10-20 | 2018-07-13 | 同济大学 | A kind of workpiece configurations detection method based on machine vision |
| CN108776143A (en) * | 2018-05-28 | 2018-11-09 | 湖北工业大学 | A kind of online vision inspection apparatus and method of the small stain of egg eggshell surface |
| CN108982543A (en) * | 2017-11-23 | 2018-12-11 | 苏州艺力鼎丰智能技术有限公司 | A kind of carbon fiber surface of automobile part printing volume defect intelligent detection equipment |
| CN110009618A (en) * | 2019-04-02 | 2019-07-12 | 浙江大学 | A kind of Axle Surface quality determining method and device |
| CN111260646A (en) * | 2020-03-11 | 2020-06-09 | 顾志军 | Digital ray detection method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101509878A (en) * | 2009-03-09 | 2009-08-19 | 北京航空航天大学 | Part vision detection device |
| CN102221556A (en) * | 2011-03-15 | 2011-10-19 | 中国计量学院 | Device and method for online detection on appearance defect of minitype connecting part based on machine vision |
-
2012
- 2012-04-25 CN CN2012101241769A patent/CN102680478A/en not_active Application Discontinuation
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101509878A (en) * | 2009-03-09 | 2009-08-19 | 北京航空航天大学 | Part vision detection device |
| CN102221556A (en) * | 2011-03-15 | 2011-10-19 | 中国计量学院 | Device and method for online detection on appearance defect of minitype connecting part based on machine vision |
Non-Patent Citations (1)
| Title |
|---|
| 李杏华等: "基于机器视觉的加工误差在线检测系统设计", 《计算机工程与应用》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103056727A (en) * | 2013-01-14 | 2013-04-24 | 南京格蕾飞信息技术有限公司 | Machine vision cutter of CNC (computerized numeral control) machine tool |
| CN103196918A (en) * | 2013-03-22 | 2013-07-10 | 上海理工大学 | Key assembling detection method for vehicle air conditioner control panel |
| CN103454283A (en) * | 2013-09-12 | 2013-12-18 | 电子科技大学 | Line detection system and method |
| CN103456021A (en) * | 2013-09-24 | 2013-12-18 | 苏州大学 | Piece goods blemish detecting method based on morphological analysis |
| CN103456021B (en) * | 2013-09-24 | 2016-05-18 | 苏州大学 | A kind of Fabric Defect detection method based on morphological analysis |
| CN104698145A (en) * | 2013-12-05 | 2015-06-10 | 珠海格力电器股份有限公司 | Flaw detection device for U-shaped pipe |
| CN104089586A (en) * | 2014-07-16 | 2014-10-08 | 浙江大学宁波理工学院 | Image detection device and method of engine crankshaft journal shape errors |
| CN104677839A (en) * | 2015-01-22 | 2015-06-03 | 浙江大学 | Rotary scanning hyperspectral crop stem information acquisition system |
| CN105139400A (en) * | 2015-08-27 | 2015-12-09 | 任红霞 | Workpiece defect positioning system based on image processing |
| CN105629321A (en) * | 2016-02-24 | 2016-06-01 | 广州市华颉电子科技有限公司 | Integrated device achieving image collection, and automatic optical detection method for three planes |
| CN106767659A (en) * | 2016-12-20 | 2017-05-31 | 武汉钢铁股份有限公司 | Automatic coarseness measuring apparatus |
| CN106770331A (en) * | 2017-02-10 | 2017-05-31 | 南京航空航天大学 | A kind of workpiece, defect detecting system based on machine vision |
| CN106770331B (en) * | 2017-02-10 | 2020-03-10 | 南京航空航天大学 | Workpiece defect detection system based on machine vision |
| CN107561095A (en) * | 2017-10-10 | 2018-01-09 | 东睦（天津）粉末冶金有限公司 | A kind of vision-based detection auto parts and components equipment or system |
| CN108279241A (en) * | 2017-10-20 | 2018-07-13 | 同济大学 | A kind of workpiece configurations detection method based on machine vision |
| CN107749058A (en) * | 2017-10-23 | 2018-03-02 | 中南大学 | A kind of machine vision detection method and system of boiler tubing surface defect |
| CN107991314A (en) * | 2017-11-23 | 2018-05-04 | 苏州艺力鼎丰智能技术有限公司 | A kind of carbon fiber surface of automobile part printed matter defect intelligent detection equipment |
| CN108982543A (en) * | 2017-11-23 | 2018-12-11 | 苏州艺力鼎丰智能技术有限公司 | A kind of carbon fiber surface of automobile part printing volume defect intelligent detection equipment |
| CN108776143A (en) * | 2018-05-28 | 2018-11-09 | 湖北工业大学 | A kind of online vision inspection apparatus and method of the small stain of egg eggshell surface |
| CN110009618A (en) * | 2019-04-02 | 2019-07-12 | 浙江大学 | A kind of Axle Surface quality determining method and device |
| CN111260646A (en) * | 2020-03-11 | 2020-06-09 | 顾志军 | Digital ray detection method |
| CN111260646B (en) * | 2020-03-11 | 2020-10-02 | 顾志军 | Digital ray detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104749184B (en) | Automatic optical detection method and system | |
| EP1995553B1 (en) | System and method for identifying a feature of a workpiece | |
| CN103090804B (en) | Automatic detection system and detection method of finished product magnet ring image | |
| CN100582657C (en) | Three-dimensional microcosmic appearance inclined scanning method and apparatus | |
| CN101487838B (en) | Extraction method for dimension shape characteristics of profiled fiber | |
| CN102601061B (en) | Automatic sorting device for defective products of pole pieces of timers | |
| CN100342207C (en) | Detector for three-dimensional appearance of micro-member through-hole inner surface and its marking and using method | |
| US20130113915A1 (en) | Method and System for Position Control Based on Automated Defect Detection Feedback | |
| KR20170069178A (en) | Multiple optics vision inspection system | |
| CN203124215U (en) | Frame sealant coating machine | |
| CN103759648B (en) | A kind of complicated angle welding method for detecting position based on Binocular stereo vision with laser | |
| CN102735695B (en) | Rapid lens flaw detection method and apparatus thereof | |
| CN202330294U (en) | Surface defect detection device based on machine vision | |
| CN102854191A (en) | Real-time visual detection and identification method for high speed rail surface defect | |
| WO2009097494A1 (en) | High resolution edge inspection | |
| CN102175700B (en) | Method for detecting welding seam segmentation and defects of digital X-ray images | |
| CN104076042B (en) | Cylindrical bar outward appearance automatic detection device | |
| CN102759347B (en) | Online in-process quality control device and method for high-speed rail contact networks and composed high-speed rail contact network detection system thereof | |
| CN102323274B (en) | Omnidirectional imaging-based method and system for detecting inner wall of steel pipe | |
| CN103454285A (en) | Transmission chain quality detection system based on machine vision | |
| CN102253050A (en) | Automatic detection method and device for magnetic tile surface defect based on machine vision | |
| CN105160652A (en) | Handset casing testing apparatus and method based on computer vision | |
| CN202916213U (en) | Gear defect detecting system based on computer vision | |
| CN102636490A (en) | Method for detecting surface defects of dustproof cover of bearing based on machine vision | |
| KR101716817B1 (en) | Image creation method, substrate inspection method, storage medium for storing program for executing image creation method and substrate inspection method, and substrate inspection apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| C06 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| C10 | Entry into substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120919 |
|
| C12 | Rejection of a patent application after its publication |