CN107228860A - A kind of gear defect detection method based on image rotation cyclophysis - Google Patents
A kind of gear defect detection method based on image rotation cyclophysis Download PDFInfo
- Publication number
- CN107228860A CN107228860A CN201710511442.6A CN201710511442A CN107228860A CN 107228860 A CN107228860 A CN 107228860A CN 201710511442 A CN201710511442 A CN 201710511442A CN 107228860 A CN107228860 A CN 107228860A
- Authority
- CN
- China
- Prior art keywords
- image
- gear
- rotation
- circle
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- 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)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of gear defect detection method based on image rotation cyclophysis, it includes detecting two stages of pretreatment stage and defects detection；Detect that pretreatment stage includes noise elimination, morphological image and operates two processes；Detection-phase comprises the following steps：J1) image binaryzation is operated；J2) image outline is extracted；J3) the determination of target region of interest；J4) image refills noise control；J5) number of gear teeth is determined；J6) gear image rotation；J7) average template image is obtained；J8) the defect location based on image difference.The present invention carries out the pretreatment of gear original image using computer vision technique, and using gear graph as twiddle operation obtains template image, defects detection is carried out with template matches.With accuracy of detection height, strong robustness and fireballing feature.
Description
Technical field
It is specifically a kind of based on image rotation periodic characteristic the present invention relates to gear open defect detection field
Gear open defect quick determination method.
Background technology
Computer integrated manufacturing system (CIM) technology is the product that Information Technology Development and industrial production are combined, and is to promote life
Unified, the integrated and efficient technology of production.In China, " research in new high-tech and the development meter come into effect for 1986
Draw " in, CIMS is an important theme, and CIMS application was being promoted at that time, and (computer/modern times collect along with CIMS
Into manufacture system) popularization, information technology starts continually to show up prominently further on industrial circle.Add for machine components
During work, due to material, technique, also or other uncontrollable factors, the appearance of defect ware is always inevitable.So on
The defect recognition of industrial products seems very necessary, can greatly improving production efficiency, while also mitigating what is manually detected
Burden, reduces the human cost of production.And human cost is often one of enterprise's capital expenditure of sustainable growth from now on.
Recently as the development of computer vision technique, its application industrially is also more extensive.For target figure
Picture, correlation computer vision technique tends to suppress its noise signal, strengthens desired signal, realizes the processing to image with entering
One step is analyzed.The existing defects detection scheme based on image information is often by picture to be detected and the progress of standard form picture
With, it is necessary to be additionally provided single standard form image.However, the standard form image additionally individually gathered in practice, it is adopted
The external environment conditions such as illumination, the focal length of collection and image to be detected are simultaneously differed, and often occur under-exposure or overexposure etc.
Situation, shooting angle also is difficult to completely the same.Even which results in intact part, the figure of its image and standard masterplate
As there is also compared with large deformation and aberration, have impact on the accuracy of defects detection.In addition, the method based on extra template matches is often
Search traveling through in yardstick, the multiple dimensions of rotation and translation needs largely to calculate the time, can not often meet industrial detection
Real-time demand.
The content of the invention
The present invention specifically addresses above mentioned problem, a kind of gear defects detection side based on image rotation cyclophysis is proposed
Method.This method includes the pretreatment of gear original image, using gear graph as twiddle operation obtains adaptive template image, utilizes
Image difference computing carries out the steps such as defects detection with template matches.Accuracy of detection of the present invention is high and speed is fast, it is not necessary to extra
Standard form, there is no excessive demand to image capture environment, the demand of large-scale production can be met.
The present invention relates to a kind of gear defect detection method based on image rotation cyclophysis, including detection pretreatment and
Two stages of defects detection；
Detect that pretreatment stage includes picture noise and eliminated and two processes of morphological operation；Original image noise is eliminated,
Refer to carrying out image processing operations using filtering methods such as gaussian filterings and based on the binarization segmentation such as threshold value method to artwork,
Morphological image operation main detection and signature analysis including edge and profile.
The defects detection stage comprises the following steps：
Step J1) binarization operation is carried out to the threshold value of image to be checked, by threshold operation carry out object in image and
The Pixel-level segmentation of background；
Image threshold binarization operation, refers to carrying out image two-value using the method for fixed threshold or adaptive threshold
Change operation.
Step J2) image outline to be checked is extracted, obtain the geometric profile of target in image-region；
Step J3) the minimum outsourcing profile obtained is combined, target region of interest is determined, the region conduct of the part center of circle is extracted
Handle the area-of-interest of target；
The determination of target region of interest, refers to the center of circle region for combining minimum outsourcing contours extract part as processing
Target region of interest, and carry out screening area point, detailed process comprises the following steps：
M1 image smoothing) is carried out to profile point set；
M2 smallest enclosing circle shape) is found, the minimum circumscribed circle shapes of all profiles in image is searched, stored；
M3 the radius data of minimum circumscribed circle) is stored；
M4) represent that the minimum of area-of-interest is represented using the maximum radius of circle in minimum circumscribed circle, choose the outer of the circle
Connect rectangular extension area-of-interest.
Step J4) image middle gear target area progress segmentation cavity is refilled, further enhance the image rotation cycle
Characteristic；
Step J5) the gear outline number of teeth is determined based on convex closure detection method, and then obtain the minimum swing circle of gear
Angle；
The determination of number of gear teeth, refers to that the method detected using convex closure is carried out to the projection of gear a certain degree of
Judge, detailed process comprises the following steps：
N1 target image) is obtained；
N2 the result of direct convex closure detection) is obtained；
N3 scaling multiple) is determined；
The determination of scaling multiple refers to reducing pixel using scaling, reduces the convex closure number detected, obtain convex closure
The functional relation of quantity and scaling multiple.
N4 the detection and analysis of convex closure) is circulated；
N5 convex closure quantity catastrophe point) is determined, concludes and determines number of gear teeth；
Determine that catastrophe point refers to obtaining the maximum catastrophe point of convex closure number change under each level of zoom, thereby determine that tooth
Tooth number.
Step J6) using the rotational periodicity of gear outward appearance, swing pinion image generates several pieces new images；
Using the rotational periodicity of gear outward appearance, swing pinion image generates several pieces new images.A specific realization
Scheme can refer to by the image rotation such as affine transformation mode come structural map as rotation function, and detailed process comprises the following steps：
L1) the acquisition of spin matrix：
The acquisition of rotational transformation matrix refers to obtaining spin matrix by the given center of circle and the anglec of rotation, and the center of circle is come
From the center of circle corresponding to the radius sequence second in profile circumscribed circle, the anglec of rotation is number of gear teeth.
L2 geometric transformation) is carried out to image using spin matrix：
L3) size of figure is corrected according to rotation results：
In step L3) in, the region after image rotation becomes big, and the size of area-of-interest immobilizes, so can go out
The problem of existing missing image, by the way that the length and width of rotation are amplified, it is corrected using the radian of rotation, after processing affine transformation
Rotate anamorphose problem.
Step J7) by using the rotational periodicity of image, rotation processing is carried out, and obtain online adaptive Prototype drawing
Picture；
The acquisition of online adaptive template image, noise spot becomes after referring to the symmetry using target part, average
It is light, then carry out threshold operation and filtered the part of light color, to obtain smoothed image.Detailed process includes the life of rotation image
Generated into the adaptive template based on rotation results.
Step J8) based on image difference computing and template matches progress defects detection, difference operation, detection are carried out to image
Defect area.
The positioning of the difference and defect of image, refers to being contrasted original image average image based on image difference,
And then determine inconsistent part.
The advantage of the invention is that：
(1) independent of additional criteria template picture, practical application succinctly facilitates very much；
(2) automatically generate matching template for each geared parts image pattern, can adaptive different photoenvironments, adjust
Try cost small；
(3) matching positioning is carried out using swing circle characteristic, search space is small, operational efficiency is high；
(4) there is no particular requirement to defect type, it is wide to various defect type relevance grades.
Brief description of the drawings
Fig. 1 is overall flow schematic diagram of the invention；
Fig. 2 is the schematic flow sheet present invention determine that target region of interest；
Fig. 3 detects the schematic flow sheet for determining number of gear teeth for the present invention using convex closure；
Fig. 4 is gear original image schematic diagram to be detected in the present invention；
Fig. 5 is gear graph to be detected in the present invention as the effect diagram of binary conversion treatment；
Fig. 6 is the Detection results schematic diagram of qualified gear.
Embodiment
Below in conjunction with drawings and examples, the present invention is described in further detail.
The present invention is a kind of gear defect detection method based on image rotation cyclophysis, as shown in figure 1, including detection
Pretreatment and two stages of defects detection.In detection pretreatment stage, image filtering, noise elimination, binaryzation, morphology are included
The pre-treatment steps such as operation.In the defects detection stage, then comprising image segmentation, contour extraction of objects, target area detection, target
Region completion, the estimation of the profile number of gears, the generation of gear image rotation, online adaptive template image and original image and acquisition
The steps such as template picture difference matching.
Detection pretreatment stage is eliminated using methods such as gaussian filtering, morphological operations to noise, and strengthens gear
Contour signal.
If Fig. 4 is gear original image schematic diagram to be detected.The present embodiment is eliminated using 2-d gaussian filterses and obeys normal state
Partition noise, its principle is to (the x in image0, y0) coordinate pixel to be filtered pixel value, be with coordinate around it
The pixel value A of (x, y) pixelX, yCumulative replacement is weighted, concrete form is as follows：
Wherein,Bandwidth parameter of the Gaussian kernel in image x-axis direction and y-axis direction is represented respectively.
After 2-d gaussian filterses operation, bilateral filtering processing is carried out to image with smooth edges.As shown in figure 5, by two-value
The result of change saves as one of stand-by image copy, and morphological operation is carried out on this basis.In the present embodiment, shape is carried out
The embodiment of state operation is as follows：K expansion, closed operation and black cap computing are carried out first, are then carried out J burn into and are opened fortune
Calculate and top cap computing.K and J determination carries out empirical selection by real data, in general, and it is 5-10 left to choose K or J
It is right.
The defects detection stage comprises the following steps：
Step J1) binarization operation is carried out to the threshold value of image to be checked, by threshold operation carry out object in image and
The Pixel-level segmentation of background；
Threshold binarization operation is to carry out the segmentation of Pixel-level, this implementation based on the object and the difference of background in image
Example carries out binarization operation using global fixed threshold method.
Step J2) image outline to be checked is extracted, obtain the geometric profile of target in image-region；
Polygon approach is carried out to the contour edge point set of extraction, obtains taking all of outside the minimum of profile or minimum outsourcing square
Shape.Detailed process is divided into lookup, storage, screening and the drafting of profile.
Step J3) the minimum outsourcing profile obtained is combined, target region of interest is determined, the region conduct of the part center of circle is extracted
Handle the area-of-interest of target；
In order to eliminate the noise outside range of gears, obtain frame with reference to minimum outsourcing profile and take the center of circle region of part as place
The target region of interest of reason, by all outsourcing circular storages extracted into array, then carries out screening differentiation, such as Fig. 2 institutes
Show, comprise the following steps that：
M1) the profile to being extracted carry out it is minimum outer take all of or minimum outsourcing rectangle before, first profile point set is carried out
Smoothly, so as to reduce error and improve efficiency；
M2) according to the shape of the similar round of part, the function of smallest enclosing circle shape is found；
M3 obtained minimum circumscribed circle radius) is stored；
M4) represent that the minimum of area-of-interest is represented using the maximum radius of circle in minimum circumscribed circle, choose the outer of the circle
Connect rectangular extension area-of-interest.
Step J4) image middle gear target area progress segmentation cavity is refilled, further enhance the image rotation cycle
Characteristic；
Segmentation cavity is carried out to image middle gear target area to refill, and further enhances image rotation cyclophysis, it is right
The geometric transformation operation to be carried out is ready afterwards.
Step J5) the gear outline number of teeth is determined based on convex closure detection method, and then obtain the minimum swing circle of gear
Angle；
The determination of number of gear teeth, the method detected using convex closure carries out a certain degree of judgement to the projection of gear,
As shown in figure 3, detailed process comprises the following steps：
N1 target image) is obtained；
N2 the result of direct convex closure detection) is obtained；
N3 scaling multiple) is determined；
The scaling that determines with of scaling multiple reduces pixel, reduces the convex closure number that detects, obtain convex closure quantity and
Scale the functional relation of multiple.
N4 the detection and analysis of convex closure) is circulated
N5 convex closure quantity catastrophe point) is determined, concludes and determines number of gear teeth；
Convex closure quantity catastrophe point is determined, concludes and determines number of gear teeth, refers to obtaining convex closure quantity under each level of zoom
Change maximum catastrophe point, thereby determine that number of gear teeth.
Step J6) using the rotational periodicity of gear outward appearance, swing pinion image generates several pieces new images；
The rotationally-varying function to construct rotation of mathematics put by affine transformation and accordingly, detailed process is included such as
Lower step：
L1) the acquisition of spin matrix：The circumscribed circle of Internal periphery in the acquisition for the back profile circumscribed circle that the center of circle comes from
The center of circle, the number of gear teeth N that the anglec of rotation is then to determine, angle be just it is counterclockwise, it is on the contrary then be spin moment clockwise, resulting
Battle array result be：
Wherein, α represents the anglec of rotation.
L2 geometric transformation) is carried out to image using spin matrix：
L3) size of figure is corrected according to rotation results：
Step J7) by using the rotational periodicity of image, rotation processing is carried out, and obtain online adaptive Prototype drawing
Picture；
It is rotational invariance using the rotational periodicity of gear target, obtains adaptive template image, is carrying out rotation figure
As noise spot is thin out after structure equalization, then carries out threshold operation and filtered the part of light color, to obtain smoothed image.
Detailed process comprises the following steps：
The storage for rotating image is obtained, and is first carried out continuously the rotation process of previous step, and the image of area-of-interest is carried out
Rotate several times, each selection result figure is stored；To the weighted accumulation of result figure and divided by rotation picture number and take
Average value or other sharpening results, obtain required template image.
Step J8) based on image difference computing and template matches progress defects detection, difference operation, detection are carried out to image
Defect area, testing result is as shown in Figure 6.
Obtain after required average template image, original image and average image are contrasted, image difference is used
Point method determines inconsistent part, takes the connected domain area region of first three to carry out frame choosing, and relative position is marked respectively and is sat
Mark, is finally marked in artwork according to obtained coordinate, it is determined that detection defect area, as shown in Figure 6.
Claims (5)
1. a kind of gear defect detection method based on image rotation cyclophysis, including detection pretreatment and defects detection two
Stage；
Detect that pretreatment stage includes picture noise and eliminated and morphological operation；
The defects detection stage comprises the following steps：
Step J1) to the threshold value progress binarization operation of image to be checked, pass through the object and background in threshold operation progress image
Pixel-level segmentation；
Step J2) image outline to be checked is extracted, obtain the geometric profile of target in image-region；
Step J3) the minimum outsourcing profile obtained is combined, target region of interest is determined, part center of circle region is extracted and is used as processing
The area-of-interest of target；
Step J4) image middle gear target area progress segmentation cavity is refilled；
Step J5) the gear outline number of teeth is determined based on convex closure detection method, and then obtain the minimum swing circle angle of gear；
Step J6) using the rotational periodicity of gear outward appearance, swing pinion image generates several pieces new images；
Step J7) using the rotational periodicity of image, rotation processing is carried out, and obtain online adaptive template image；
Step J8) based on image difference computing and template matches progress defects detection, difference operation is carried out to image, defect is detected
Region.
2. a kind of gear defect detection method based on image rotation cyclophysis according to claim 1, described inspection
Survey in pretreatment stage, picture noise, which is eliminated, is specially：Behaviour is filtered to artwork using linear filtering and threshold value binary segmentation
Make；Morphological image is operated：The detection of image border and profile and signature analysis.
3. a kind of gear defect detection method based on image rotation cyclophysis according to claim 1, described step
Rapid J3 specifically includes following steps：
M1 image smoothing) is carried out to profile point set；
M2 smallest enclosing circle shape) is found, the minimum circumscribed circle shapes of all profiles in image is searched, stored；
M3 the radius data of minimum circumscribed circle) is stored；
M4) represent that the minimum of area-of-interest is represented using the maximum radius of circle in minimum circumscribed circle, choose the external square of the circle
Shape extends area-of-interest.
4. a kind of gear defect detection method based on image rotation cyclophysis according to claim 1, described step
Rapid J5 specifically includes following steps：
N1 target image) is obtained；
N2 the result of direct convex closure detection) is obtained；
N3 scaling multiple) is determined；
Pixel is reduced using scaling, the convex closure number detected is reduced, the functional relation of convex closure quantity and scaling multiple is obtained；
N4 the detection and analysis of convex closure) is circulated；
N5 convex closure quantity catastrophe point) is determined, concludes and determines number of gear teeth；
The maximum catastrophe point of convex closure number change under each level of zoom is obtained, number of gear teeth is determined.
5. a kind of gear defect detection method based on image rotation cyclophysis according to claim 1, described step
Rapid J6 specifically includes following steps：
L1) the acquisition of spin matrix；
The acquisition of rotational transformation matrix refers to obtaining spin matrix by the given center of circle and the anglec of rotation, and the center of circle comes from
The center of circle in profile circumscribed circle corresponding to radius sequence second, the anglec of rotation is number of gear teeth；
L2 geometric transformation) is carried out to image using spin matrix；
L3) size of figure is corrected according to rotation results；
The length and width of rotation are amplified, are corrected using the radian of rotation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710511442.6A CN107228860B (en) | 2017-06-28 | 2017-06-28 | Gear defect detection method based on image rotation period characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710511442.6A CN107228860B (en) | 2017-06-28 | 2017-06-28 | Gear defect detection method based on image rotation period characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107228860A true CN107228860A (en) | 2017-10-03 |
| CN107228860B CN107228860B (en) | 2020-04-24 |
Family
ID=59935652
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710511442.6A Active CN107228860B (en) | 2017-06-28 | 2017-06-28 | Gear defect detection method based on image rotation period characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107228860B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108731606A (en) * | 2018-05-17 | 2018-11-02 | 北京化工大学 | A kind of gear parameter rapid detection method based on convexity defect key point |
| CN109064463A (en) * | 2018-08-06 | 2018-12-21 | 中车青岛四方机车车辆股份有限公司 | A kind of rippling the area ratio measurement method and system |
| CN109461141A (en) * | 2018-10-10 | 2019-03-12 | 重庆大学 | A kind of workpiece starved detection method |
| CN109472769A (en) * | 2018-09-26 | 2019-03-15 | 成都数之联科技有限公司 | A kind of bad image defect detection method and system |
| CN110084302A (en) * | 2019-04-26 | 2019-08-02 | 西安因诺航空科技有限公司 | A kind of crack detection method based on remote sensing images |
| CN110211113A (en) * | 2019-06-03 | 2019-09-06 | 湖南瑞智健科技有限公司 | A kind of detection algorithm and calculating equipment of groove exception |
| CN110322395A (en) * | 2019-06-18 | 2019-10-11 | 电子科技大学中山学院 | Part outline shape detection method and device based on image processing and affine transformation |
| CN110633886A (en) * | 2019-04-01 | 2019-12-31 | 邓继红 | Block chain-based network data sending platform, method and storage medium |
| CN111028202A (en) * | 2019-11-14 | 2020-04-17 | 苏州斯玛维科技有限公司 | X-ray bubble defect image processing method, device, storage medium and system for LED chip |
| CN111353981A (en) * | 2020-02-28 | 2020-06-30 | 广州大学 | Gear detection method and system based on machine vision and storage medium |
| WO2020248439A1 (en) * | 2019-06-11 | 2020-12-17 | 江苏农林职业技术学院 | Crown cap surface defect online inspection method employing image processing |
| CN112991338A (en) * | 2021-04-27 | 2021-06-18 | 湖南大捷智能装备有限公司 | Defect detection method and device for laser cutting part |
| CN115035107A (en) * | 2022-08-10 | 2022-09-09 | 山东正阳机械股份有限公司 | Axle gear working error detection method based on image processing |
| RU2787072C1 (en) * | 2019-06-11 | 2022-12-28 | Цзянсу Вокэйшнл Колледж Оф Агрикальче Энд Форестри | Method for promptly detecting surface defects of crown caps based on image processing |
| TWI792351B (en) * | 2021-06-15 | 2023-02-11 | 鴻海精密工業股份有限公司 | Method for detecting defects, electronic device and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1468371A (en) * | 2000-09-10 | 2004-01-14 | �²�̩������˾ | Reduction of error alarm in PCB detection |
| WO2008123459A1 (en) * | 2007-03-30 | 2008-10-16 | Shibaura Mechatronics Corporation | Apparatus and method for inspecting edge of semiconductor wafer |
| CN103578087A (en) * | 2013-11-15 | 2014-02-12 | 重庆医科大学 | Retinal image optimizing method |
| KR20140059621A (en) * | 2012-11-08 | 2014-05-16 | 주식회사 쓰리디산업영상 | A method and an apparatus for deciphering flaw of a fuse |
| CN103901044A (en) * | 2012-12-28 | 2014-07-02 | 鸿富锦精密工业（深圳）有限公司 | Detection system |
| CN105069790A (en) * | 2015-08-06 | 2015-11-18 | 潍坊学院 | Rapid imaging detection method for gear appearance defect |
| CN105841613A (en) * | 2016-03-31 | 2016-08-10 | 浙江工业大学 | Device of utilizing planar mirror set to determine qualification of shelf crossbeams |
| CN106596589A (en) * | 2016-12-24 | 2017-04-26 | 大连日佳电子有限公司 | Tray IC detection device |
-
2017
- 2017-06-28 CN CN201710511442.6A patent/CN107228860B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1468371A (en) * | 2000-09-10 | 2004-01-14 | �²�̩������˾ | Reduction of error alarm in PCB detection |
| WO2008123459A1 (en) * | 2007-03-30 | 2008-10-16 | Shibaura Mechatronics Corporation | Apparatus and method for inspecting edge of semiconductor wafer |
| KR20140059621A (en) * | 2012-11-08 | 2014-05-16 | 주식회사 쓰리디산업영상 | A method and an apparatus for deciphering flaw of a fuse |
| CN103901044A (en) * | 2012-12-28 | 2014-07-02 | 鸿富锦精密工业（深圳）有限公司 | Detection system |
| CN103578087A (en) * | 2013-11-15 | 2014-02-12 | 重庆医科大学 | Retinal image optimizing method |
| CN105069790A (en) * | 2015-08-06 | 2015-11-18 | 潍坊学院 | Rapid imaging detection method for gear appearance defect |
| CN105841613A (en) * | 2016-03-31 | 2016-08-10 | 浙江工业大学 | Device of utilizing planar mirror set to determine qualification of shelf crossbeams |
| CN106596589A (en) * | 2016-12-24 | 2017-04-26 | 大连日佳电子有限公司 | Tray IC detection device |
Non-Patent Citations (4)
| Title |
|---|
| 杨淑莹 等: ""基于机器视觉的齿轮产品外观缺陷检测"", 《天津大学学报》 * |
| 王丽: ""基于机器视觉的齿轮缺陷研究"", 《电子测试》 * |
| 范敏 等: ""基于对比度与最小凸包的显著性区域检测算法"", 《仪器仪表学报》 * |
| 蔺志敏: "基于机器视觉齿轮微观缺陷检测技术研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108731606A (en) * | 2018-05-17 | 2018-11-02 | 北京化工大学 | A kind of gear parameter rapid detection method based on convexity defect key point |
| CN109064463B (en) * | 2018-08-06 | 2020-10-20 | 中车青岛四方机车车辆股份有限公司 | Method and system for measuring tooth surface pitting area rate |
| CN109064463A (en) * | 2018-08-06 | 2018-12-21 | 中车青岛四方机车车辆股份有限公司 | A kind of rippling the area ratio measurement method and system |
| CN109472769A (en) * | 2018-09-26 | 2019-03-15 | 成都数之联科技有限公司 | A kind of bad image defect detection method and system |
| CN109461141A (en) * | 2018-10-10 | 2019-03-12 | 重庆大学 | A kind of workpiece starved detection method |
| CN110633886A (en) * | 2019-04-01 | 2019-12-31 | 邓继红 | Block chain-based network data sending platform, method and storage medium |
| CN110084302A (en) * | 2019-04-26 | 2019-08-02 | 西安因诺航空科技有限公司 | A kind of crack detection method based on remote sensing images |
| CN110084302B (en) * | 2019-04-26 | 2022-11-08 | 西安因诺航空科技有限公司 | Crack detection method based on remote sensing image |
| CN110211113A (en) * | 2019-06-03 | 2019-09-06 | 湖南瑞智健科技有限公司 | A kind of detection algorithm and calculating equipment of groove exception |
| CN110211113B (en) * | 2019-06-03 | 2021-09-07 | 湖南瑞智健科技有限公司 | Detection algorithm and calculation equipment for groove abnormity |
| RU2787072C1 (en) * | 2019-06-11 | 2022-12-28 | Цзянсу Вокэйшнл Колледж Оф Агрикальче Энд Форестри | Method for promptly detecting surface defects of crown caps based on image processing |
| WO2020248439A1 (en) * | 2019-06-11 | 2020-12-17 | 江苏农林职业技术学院 | Crown cap surface defect online inspection method employing image processing |
| CN110322395A (en) * | 2019-06-18 | 2019-10-11 | 电子科技大学中山学院 | Part outline shape detection method and device based on image processing and affine transformation |
| CN111028202B (en) * | 2019-11-14 | 2021-07-13 | 苏州斯玛维科技有限公司 | X-ray bubble defect image processing method, device, storage medium and system for LED chip |
| CN111028202A (en) * | 2019-11-14 | 2020-04-17 | 苏州斯玛维科技有限公司 | X-ray bubble defect image processing method, device, storage medium and system for LED chip |
| CN111353981A (en) * | 2020-02-28 | 2020-06-30 | 广州大学 | Gear detection method and system based on machine vision and storage medium |
| CN111353981B (en) * | 2020-02-28 | 2023-03-14 | 广州大学 | Gear detection method and system based on machine vision and storage medium |
| CN112991338B (en) * | 2021-04-27 | 2021-07-27 | 湖南大捷智能装备有限公司 | Defect detection method and device for laser cutting part |
| CN112991338A (en) * | 2021-04-27 | 2021-06-18 | 湖南大捷智能装备有限公司 | Defect detection method and device for laser cutting part |
| TWI792351B (en) * | 2021-06-15 | 2023-02-11 | 鴻海精密工業股份有限公司 | Method for detecting defects, electronic device and storage medium |
| CN115035107A (en) * | 2022-08-10 | 2022-09-09 | 山东正阳机械股份有限公司 | Axle gear working error detection method based on image processing |
| CN115035107B (en) * | 2022-08-10 | 2022-11-08 | 山东正阳机械股份有限公司 | Axle gear working error detection method based on image processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107228860B (en) | 2020-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107228860A (en) | A kind of gear defect detection method based on image rotation cyclophysis | |
| CN110826416B (en) | Bathroom ceramic surface defect detection method and device based on deep learning | |
| CN110570393B (en) | Mobile phone glass cover plate window area defect detection method based on machine vision | |
| CN108776140B (en) | Machine vision-based printed matter flaw detection method and system | |
| CN111833306B (en) | Defect detection method and model training method for defect detection | |
| CN113592845A (en) | Defect detection method and device for battery coating and storage medium | |
| CN109636772A (en) | The defect inspection method on the irregular shape intermetallic composite coating surface based on deep learning | |
| CN108898610A (en) | A kind of object contour extraction method based on mask-RCNN | |
| CN106157310A (en) | The TFT LCD mura defect inspection method being combined with multichannel based on mixed self-adapting Level Set Models | |
| CN109767445B (en) | High-precision PCB defect intelligent detection method | |
| CN105894036A (en) | Image feature template matching method being applied to detection of mobile phone screen defects | |
| CN111523540A (en) | Metal surface defect detection method based on deep learning | |
| CN108985337A (en) | A kind of product surface scratch detection method based on picture depth study | |
| CN112734761B (en) | Industrial product image boundary contour extraction method | |
| CN111754538B (en) | Threshold segmentation method for USB surface defect detection | |
| CN116109637B (en) | System and method for detecting appearance defects of turbocharger impeller based on vision | |
| CN108647706A (en) | Article identification classification based on machine vision and flaw detection method | |
| CN111027538A (en) | Container detection method based on instance segmentation model | |
| CN116664565A (en) | Hidden crack detection method and system for photovoltaic solar cell | |
| CN114255223A (en) | Deep learning-based method and equipment for detecting surface defects of two-stage bathroom ceramics | |
| CN112529893A (en) | Hub surface flaw online detection method and system based on deep neural network | |
| Dong et al. | A rapid detection method for the surface defects of mosaic ceramic tiles | |
| Yu et al. | An improved method for cloth pattern cutting based on holistically-nested edge detection | |
| CN112102189B (en) | Line structure light bar center line extraction method | |
| CN113705564A (en) | Pointer type instrument identification reading method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |