CN103499590B - Ring-shaped work pieces end face defect detection and screening technique and system - Google Patents
Ring-shaped work pieces end face defect detection and screening technique and system Download PDFInfo
- Publication number
- CN103499590B CN103499590B CN201310486574.XA CN201310486574A CN103499590B CN 103499590 B CN103499590 B CN 103499590B CN 201310486574 A CN201310486574 A CN 201310486574A CN 103499590 B CN103499590 B CN 103499590B
- Authority
- CN
- China
- Prior art keywords
- ring
- work pieces
- shaped work
- image
- circle
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The present invention relates to ring-shaped work pieces end face defect detection and screening technique and system, this system comprises optical amplification device, computer for controlling, controller, spray nozzle of atmospheric pressure device, stepper motor and travelling belt, the method comprises the following steps: 1, taken ring-shaped work pieces to be checked by an optical amplification device, obtains the optical amplifier image of ring-shaped work pieces end face to be checked; 2, by a computer for controlling, image procossing and defect identification are carried out to optical amplifier image, then judge that whether ring-shaped work pieces is qualified according to defect situation; 3) by a controller, receive the order of computer for controlling, control the work of spray nozzle of atmospheric pressure device, underproof part is rejected, control travelling belt simultaneously and next part is sent to detection position.The present invention truly can reflect the end face defect information of ring-shaped work pieces, and accurately can judge that whether detected object is qualified, and automaticity is high, provides detection efficiency.
Description
Technical field
The present invention relates to technical field of image processing, particularly a kind of method and system can carrying out end face defect detection and screening to small-size annular part.
Background technology
Being less than the small-size annular part of 5 millimeters for outer annular diameter, in order to ensure product quality, must detecting micro-defect of its end face (as fine crack, micro-breakage).The surface damage of such part detects main dependence human eye visual detection at present, due to impacts such as examinate person's technology, experience, working environment and asthenopias, be easy to occur flase drop and undetected, and artificial visually examine's efficiency is low, lack accuracy and standardization, stability and Reliability comparotive poor.The difficult problem that artificial visually examine's work difficulty is large, efficiency is low in order to solve, loss is high, needs to introduce a kind of Automatic Measurement Technique, not only reduces human cost but also can realize the strict control to product quality.
Current computer vision technique relative maturity, there is the plurality of advantages such as noncontact, speed is fast, precision is high, antijamming capability is strong, if computer vision technique is introduced in small-size annular part end face defect detection, its requirement to reliability and sensitivity can be met well, and easy to maintenance.
Summary of the invention
The object of the invention is to overcome the deficiencies in the prior art, provide a kind of ring-shaped work pieces end face defect detection and screening technique and system, the method and system not only detection accuracy are high, and automaticity is high, provide detection efficiency.
For achieving the above object, technical scheme of the present invention is: a kind of ring-shaped work pieces end face defect detection and screening technique, comprise the following steps:
(1) by an optical amplification device, ring-shaped work pieces to be checked is taken, obtain the optical amplifier image of ring-shaped work pieces end face to be checked;
(2) described optical amplifier image is read by a computer for controlling, image procossing and defect identification are carried out to described optical amplifier image, then judge that whether ring-shaped work pieces is qualified according to defect situation, and result of determination is sent to the communication port of described computer for controlling with command forms;
(3) by a controller, receive the order of the communication port of described computer for controlling, if ring-shaped work pieces is defective, described controller controls the work of spray nozzle of atmospheric pressure device, blow off this ring-shaped work pieces travelling belt, then ring-shaped work pieces to be checked for the next one is sent to the detection position of optical amplification device by control step motor drag travelling belt, enters next round and detects and screening process.
Further, in step (1), described optical amplification device adopt industrial camera and stereomicroscope combined, to need to obtain the optical amplifier image of ring-shaped work pieces different multiples to be checked particularly large multiple according to scene.
Further, in step (2), image procossing is carried out to described optical amplifier image and defect identification comprises the following steps:
(2.1) construct linear smoothing filter and filtering is carried out to described optical amplifier image, remove the sharpen detail in radio-frequency component and image; Described linear smoothing filter adopts local mean value computing, and each grey scale pixel value weights of all values in its local neighborhood are replaced, and computing formula is:
Wherein, M is the pixel sum in neighborhood N, and h [i, j] is the gray-scale value of Filtered Picture vegetarian refreshments [i, j], and f [k, l] is the gray-scale value of the neighborhood territory pixel point of filtering preceding pixel point [k, l];
(2.2) adopt threshold value process of iteration to carry out image binaryzation first to filtered image, combining image morphology operations wiping out background information, obtains the circular profile of desirable ring-shaped work pieces; Described threshold value process of iteration is as follows:
(2.2.1) the estimated value T(of an initial approximation threshold value is selected can to adopt gradation of image average as initial value);
(2.2.2) utilize estimated value T that image is divided into two groups of region R according to gray-scale value
1and R
2;
(2.2.3) zoning R
1and R
2gray average μ
1and μ
2;
(2.2.4) according to formula T=(μ
1+ μ
2)/2 calculate and select new estimated value T;
(2.2.5) repeat step (2.2.2)-(2.2.4), continuous iterative computation estimated value T, until (μ
1+ μ
2the value of)/2 no longer changes;
In order to obtain desirable circular profile, threshold value can be selected to be that image is converted into bianry image by (0.5 ~ 1) T according to field condition, namely be partitioned into doughnut picture;
(2.3) adopt boundary scan method to obtain the cylindrical border dot information of ring-shaped work pieces, and pass through central coordinate of circle and the radius of least square fitting cylindrical; Described boundary scan method is as follows:
(2.3.1) select outside circle a bit as scan start point, by horizontal and vertical scanning, until obtain first point on cylindrical border, judge that whether this point is the point on cylindrical simultaneously;
(2.3.2) use this as the initial point of boundary tracking, according to boundary connected in certain direction pointwise obtain cylindrical border dot information and preserve in the matrix form;
Described least square fitting cylindrical is specially:
Read the cylindrical border dot information (circular arc or circle) scanned, calculate corresponding parameter by the equation of circle, the equation of circle is:
(x-x
c)
2+(y–y
c)
2=radius
2
Wherein, (x
c, y
c) be the center of circle, radius is radius of a circle, launches to obtain:
x
2+y
2+ax+by+c=0
Wherein, a=-2x
c, b=-2y
c, c=x
c 2+ y
c 2-radius
2, adopt least square method calculating parameter a, b, c of curve, according to formula:
Calculate data a, b, c, thus try to achieve round central coordinate of circle (x
c, y
c), radius r adius is:
x
c=-a/2；
y
c=-b/2；
；
(2.4) select the center of circle as scan start point, adopt the boundary scan method as described in step (2.3) to obtain the inner circle border dot information of ring-shaped work pieces, and by radius of a circle in least square fitting;
(2.5) read step (2.1) filtered image again, the central coordinate of circle of the ring-shaped work pieces obtained according to step (2.3), (2.4), exradius and inner circle radius, remove the cylindrical border of background and ring-shaped work pieces, inner circle boundary information, full segmentation goes out the defect of annulus inside;
(2.6) image that step (2.5) is partitioned into is processed, step (2.2) described threshold value process of iteration is adopted to carry out second time image binaryzation, after obtaining binary image, take suitable structural element to carry out morphology operations for different defect feature, finally defect area is filled and zone marker;
(2.7) calculate defect area pixel point areas, the several regions choosing defect larger judge, the size calculating the minimum enclosed rectangle of zones of different respectively and the size calculating zones of different are to judge that whether ring-shaped work pieces to be checked is qualified.
Present invention also offers a kind of ring-shaped work pieces end face defect detection and screening system, comprise optical amplification device, computer for controlling, controller, spray nozzle of atmospheric pressure device, stepper motor and can travelling belt driven by stepper motors, described computer for controlling is connected with controller with described optical amplification device respectively, described optical amplification device is placed in directly over travelling belt, and described controller is connected with air pressure spray nozzle device with described stepper motor respectively.
Further, described optical amplification device comprises industrial camera and stereomicroscope, and described stereomicroscope is equipped with LED circular lamp.
Further, if ring-shaped work pieces is defective, described computer for controlling sends product and rejects order, and after described controller receives order, control spray nozzle of atmospheric pressure device and start, blow off ring-shaped work pieces travelling belt, if ring-shaped work pieces is qualified, then spray nozzle of atmospheric pressure device does not start; Then, described controller control step motor runs, and by travelling belt, ring-shaped work pieces to be checked for the next one is sent to detection position, enters next round and detects and screening process.
Compared to prior art, the invention has the beneficial effects as follows: adopt the mode that computer vision and micro-vision technology combine, achieve end face defect detection and the screening of small-size annular part, solve small size ring-shape accessory (diameter is less than 5mm) end face defect detection difficulty, and the problem such as algorithm calculated amount is large, detection speed is slow, truly can reflect the end face defect information of ring-shaped work pieces, and accurately can judge that whether detected object is qualified, and data volume is little, detection efficiency is high, has very strong practicality and wide application prospect.
Below in conjunction with drawings and the specific embodiments, the present invention is described in further detail.
Accompanying drawing explanation
Fig. 1 is the workflow diagram in the embodiment of the present invention, optical amplifier image being carried out to image procossing and defect identification.
Fig. 2 is the system architecture schematic diagram of the embodiment of the present invention.
Embodiment
The invention provides a kind of ring-shaped work pieces end face defect detection and screening technique, comprise the following steps:
(1) by an optical amplification device, ring-shaped work pieces to be checked is taken, obtain the optical amplifier image of ring-shaped work pieces end face to be checked;
(2) described optical amplifier image is read by a computer for controlling, image procossing and defect identification are carried out to described optical amplifier image, comprise image filtering, threshold value iteration, image binaryzation, morphology operations, Iamge Segmentation, defect identification etc., then judge that whether ring-shaped work pieces is qualified according to defect situation, and result of determination is sent to the communication port of described computer for controlling with command forms;
(3) by a controller, receive the order of the communication port of described computer for controlling, if ring-shaped work pieces is defective, described controller controls the work of spray nozzle of atmospheric pressure device, blow off this ring-shaped work pieces travelling belt, then ring-shaped work pieces to be checked for the next one is sent to the detection position of optical amplification device by control step motor drag travelling belt, enters next round and detects and screening process.
In step (1), described optical amplification device adopt industrial camera and stereomicroscope combined, to need to obtain the optical amplifier image (7 ~ 90 times) of ring-shaped work pieces different multiples to be checked particularly large multiple according to scene, the end face defect information of miniature toroidal part can be obtained authentic and validly, be convenient to observe and differentiate, drastically increase measuring accuracy.
As shown in Figure 1, in step (2), image procossing is carried out to described optical amplifier image and defect identification comprises the following steps:
(2.1) construct linear smoothing filter and filtering is carried out to described optical amplifier image, remove the sharpen detail in radio-frequency component and image; Described linear smoothing filter adopts local mean value computing, and each grey scale pixel value weights of all values in its local neighborhood are replaced, and computing formula is:
Wherein, M is the pixel sum in neighborhood N, and h [i, j] is the gray-scale value of Filtered Picture vegetarian refreshments [i, j], and f [k, l] is the gray-scale value of the neighborhood territory pixel point of filtering preceding pixel point [k, l]; Such as, get 3 × 3 neighborhoods at pixel [i, j] place, obtain:
Linear smoothing filter can remove the sharpen detail in radio-frequency component and image, and the present invention adopts the smoothing filter of 3 × 3, and its Weight template is as follows:
(2.2) adopt threshold value process of iteration to carry out image binaryzation first to filtered image, combining image morphology operations wiping out background information, obtains the circular profile of desirable ring-shaped work pieces; Described threshold value process of iteration is as follows:
(2.2.1) the estimated value T(of an initial approximation threshold value is selected can to adopt gradation of image average as initial value);
(2.2.2) utilize estimated value T whether image is greater than T according to gray-scale value and be divided into two groups of region R
1and R
2;
(2.2.3) zoning R
1and R
2gray average μ
1and μ
2;
(2.2.4) according to formula T=(μ
1+ μ
2)/2 calculate and select new estimated value T;
(2.2.5) repeat step (2.2.2)-(2.2.4), continuous iterative computation estimated value T, until (μ
1+ μ
2the value of)/2 no longer changes;
In order to obtain desirable circular profile, threshold value can be selected to be that image is converted into bianry image by (0.5 ~ 1) T according to field condition, namely be partitioned into doughnut picture;
(2.3) adopt boundary scan method to obtain the cylindrical border dot information of ring-shaped work pieces, and pass through central coordinate of circle and the radius of least square fitting cylindrical; Described boundary scan method is as follows:
(2.3.1) select outside circle a bit as scan start point, by horizontal and vertical scanning, until obtain first point on cylindrical border, judge that whether this point is the point on cylindrical simultaneously;
(2.3.2) use this as the initial point of boundary tracking, according to boundary connected in certain direction pointwise obtain cylindrical border dot information and preserve in the matrix form; In this program, arranging connected relation is 8 connected relations, and boundary tracking path is 8 paths, in order to the result making acquisition is accurate as far as possible, point as much as possible should be utilized as frontier point, and the number of frontier point is by the number of experimental selection optimum;
Described least square fitting cylindrical is specially:
Read the cylindrical border dot information scanned, calculate corresponding parameter by the equation of circle, the equation of circle is:
(x-x
c)
2+(y–y
c)
2=radius
2
Wherein, (x
c, y
c) be the center of circle, radius is radius of a circle, launches to obtain:
x
2+y
2+ax+by+c=0
Wherein, a=-2x
c, b=-2y
c, c=x
c 2+ y
c 2-radius
2, adopt least square method calculating parameter a, b, c of curve, according to formula:
Calculate data a, b, c, thus try to achieve round central coordinate of circle (x
c, y
c), radius r adius is:
x
c=-a/2；
y
c=-b/2；
；
The algorithm of the scanning fitting circle that the present invention adopts is less to annulus position limitation, only requires that annulus position can complete round matching in the orientation, visual field of micro-vision;
(2.4) select the center of circle as scan start point, adopt the boundary scan method as described in step (2.3) to obtain the inner circle border dot information of ring-shaped work pieces, and by radius of a circle in least square fitting;
(2.5) read step (2.1) filtered image again, the central coordinate of circle of the ring-shaped work pieces obtained according to step (2.3), (2.4), exradius and inner circle radius, remove the cylindrical border of background (background refers to the region of other than ring type part) and ring-shaped work pieces, inner circle boundary information, full segmentation goes out the defect of annulus inside, namely the border of annulus cylindrical and inner circle is also removed, only leave the part region between inside and outside circle;
(2.6) image that step (2.5) is partitioned into is processed, step (2.2) described threshold value process of iteration is adopted to carry out second time image binaryzation, after obtaining binary image, take suitable structural element (as planar rectangular structural element, circular planar disk-like structural element) to carry out morphology operations for different defect feature, finally defect area is filled and zone marker;
(2.7) calculate defect area pixel point areas, the several regions choosing defect larger judge, the size calculating the minimum enclosed rectangle of zones of different respectively and the size calculating zones of different are to judge that whether ring-shaped work pieces to be checked is qualified.
As shown in Figure 2, the present invention also provides a kind of ring-shaped work pieces end face defect detection and screening system, the travelling belt 6 comprising optical amplification device, computer for controlling 1, controller 9, spray nozzle of atmospheric pressure device 8, stepper motor 5 and can be driven by stepper motor 5, described computer for controlling 1 is connected with controller 9 with described optical amplification device respectively, described optical amplification device is placed in directly over travelling belt 6 and ring-shaped work pieces 7 to be checked, and described controller 9 is connected with air pressure spray nozzle device 8 with described stepper motor 5 respectively.
In the present embodiment, described optical amplification device comprises industrial camera 2 and stereomicroscope 3, described stereomicroscope 3 is equipped with LED circular lamp 4, the enlargement factor of stereomicroscope is 7 ~ 90 times, utilize this device effectively can obtain the end face defect information of miniature toroidal part, be convenient to observe and differentiate, drastically increase measuring accuracy.
If ring-shaped work pieces is defective, described computer for controlling sends product and rejects order, and after described controller receives order, control spray nozzle of atmospheric pressure device and start, blow off ring-shaped work pieces travelling belt, if ring-shaped work pieces is qualified, then spray nozzle of atmospheric pressure device does not start; Then, described controller control step motor runs, and by travelling belt, ring-shaped work pieces to be checked for the next one is sent to detection position, enters next round and detects and screening process.
Be more than preferred embodiment of the present invention, all changes done according to technical solution of the present invention, when the function produced does not exceed the scope of technical solution of the present invention, all belong to protection scope of the present invention.
Claims (5)
1. ring-shaped work pieces end face defect detection and a screening technique, is characterized in that, comprises the following steps:
(1) by an optical amplification device, ring-shaped work pieces to be checked is taken, obtain the optical amplifier image of ring-shaped work pieces end face to be checked;
(2) described optical amplifier image is read by a computer for controlling, image procossing and defect identification are carried out to described optical amplifier image, then judge that whether ring-shaped work pieces is qualified according to defect situation, and result of determination is sent to the communication port of described computer for controlling with command forms;
(3) by a controller, receive the order of the communication port of described computer for controlling, if ring-shaped work pieces is defective, described controller controls the work of spray nozzle of atmospheric pressure device, blow off this ring-shaped work pieces travelling belt, then ring-shaped work pieces to be checked for the next one is sent to the detection position of optical amplification device by control step motor drag travelling belt, enters next round and detects and screening process;
In step (2), image procossing is carried out to described optical amplifier image and defect identification comprises the following steps:
(2.1) construct linear smoothing filter and filtering is carried out to described optical amplifier image, remove the sharpen detail in radio-frequency component and image; Described linear smoothing filter adopts local mean value computing, and each grey scale pixel value weights of all values in its local neighborhood are replaced, and computing formula is:
Wherein, M is the pixel sum in neighborhood N, and h [i, j] is the gray-scale value of Filtered Picture vegetarian refreshments [i, j], and f [k, l] is the gray-scale value of the neighborhood territory pixel point of filtering preceding pixel point [k, l];
(2.2) adopt threshold value process of iteration to carry out image binaryzation first to filtered image, combining image morphology operations wiping out background information, obtains the circular profile of ring-shaped work pieces accurately; Described threshold value process of iteration is as follows:
(2.2.1) the estimated value T of an initial approximation threshold value is selected;
(2.2.2) utilize estimated value T whether image is greater than T according to gray-scale value and be divided into two groups of region R
1and R
2;
(2.2.3) zoning R
1and R
2gray average μ
1and μ
2;
(2.2.4) according to formula T=(μ
1+ μ
2)/2 calculate and select new estimated value T;
(2.2.5) repeat step (2.2.2)-(2.2.4), continuous iterative computation estimated value T, until (μ
1+ μ
2the value of)/2 no longer changes;
In order to obtain circular profile accurately, selecting threshold value image to be converted into bianry image for (0.5 ~ 1) T, being namely partitioned into doughnut picture;
(2.3) adopt boundary scan method to obtain the cylindrical border dot information of ring-shaped work pieces, and pass through central coordinate of circle and the radius of least square fitting cylindrical; Described boundary scan method is as follows:
(2.3.1) select outside circle a bit as scan start point, by horizontal and vertical scanning, until obtain first point on cylindrical border, judge that whether this point is the point on cylindrical simultaneously;
(2.3.2) use this as the initial point of boundary tracking, according to boundary connected in certain direction pointwise obtain cylindrical border dot information and preserve in the matrix form;
Described least square fitting cylindrical is specially:
Read the cylindrical border dot information scanned, calculate corresponding parameter by the equation of circle, the equation of circle is:
(x-x
c)
2+(y–y
c)
2=radius
2
Wherein, (x
c, y
c) be the center of circle, radius is radius of a circle, launches to obtain:
x
2+y
2+ax+by+c=0
Wherein, a=-2x
c, b=-2y
c, c=x
c 2+ y
c 2-radius
2, adopt least square method calculating parameter a, b, c of curve, according to formula:
Calculate data a, b, c, thus try to achieve round central coordinate of circle (x
c, y
c), radius r adius is:
x
c=-a/2；
y
c=-b/2；
；
(2.4) select the center of circle as scan start point, adopt the boundary scan method as described in step (2.3) to obtain the inner circle border dot information of ring-shaped work pieces, and by radius of a circle in least square fitting;
(2.5) read step (2.1) filtered image again, the central coordinate of circle of the ring-shaped work pieces obtained according to step (2.3), (2.4), exradius and inner circle radius, remove the cylindrical border of background and ring-shaped work pieces, inner circle boundary information, full segmentation goes out the defect of annulus inside;
(2.6) image that step (2.5) is partitioned into is processed, step (2.2) described threshold value process of iteration is adopted to carry out second time image binaryzation, after obtaining binary image, take suitable structural element to carry out morphology operations for different defect feature, finally defect area is filled and zone marker;
(2.7) calculate defect area pixel point areas, the several regions choosing defect larger judge, the size calculating the minimum enclosed rectangle of zones of different respectively and the size calculating zones of different are to judge that whether ring-shaped work pieces to be checked is qualified.
2. ring-shaped work pieces end face defect detection according to claim 1 and screening technique, it is characterized in that, in step (1), described optical amplification device adopt industrial camera and stereomicroscope combined, to need the optical amplifier image obtaining ring-shaped work pieces different multiples to be checked according to scene.
3. one kind adopts ring-shaped work pieces end face defect detection and the screening system of method as claimed in claim 1, it is characterized in that, comprise optical amplification device, computer for controlling, controller, spray nozzle of atmospheric pressure device, stepper motor and can travelling belt driven by stepper motors, described computer for controlling is connected with controller with described optical amplification device respectively, described optical amplification device is placed in directly over travelling belt, and described controller is connected with air pressure spray nozzle device with described stepper motor respectively.
4. ring-shaped work pieces end face defect detection according to claim 3 and screening system, is characterized in that, described optical amplification device comprises industrial camera and stereomicroscope, and described stereomicroscope is equipped with LED circular lamp.
5. ring-shaped work pieces end face defect detection according to claim 3 and screening system, it is characterized in that, if ring-shaped work pieces is defective, described computer for controlling sends product and rejects order, after described controller receives order, control spray nozzle of atmospheric pressure device and start, blow off ring-shaped work pieces travelling belt, if ring-shaped work pieces is qualified, then spray nozzle of atmospheric pressure device does not start; Then, described controller control step motor runs, and by travelling belt, ring-shaped work pieces to be checked for the next one is sent to detection position, enters next round and detects and screening process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310486574.XA CN103499590B (en) | 2013-10-17 | 2013-10-17 | Ring-shaped work pieces end face defect detection and screening technique and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310486574.XA CN103499590B (en) | 2013-10-17 | 2013-10-17 | Ring-shaped work pieces end face defect detection and screening technique and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103499590A CN103499590A (en) | 2014-01-08 |
| CN103499590B true CN103499590B (en) | 2015-11-18 |
Family
ID=49864819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310486574.XA Active CN103499590B (en) | 2013-10-17 | 2013-10-17 | Ring-shaped work pieces end face defect detection and screening technique and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103499590B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104390589B (en) * | 2014-11-20 | 2017-02-22 | 景德镇陶瓷大学 | Anti-dazzle circular daily ceramic device applique out-of-bound detection method |
| CN105092577B (en) * | 2015-05-15 | 2017-08-01 | 浙江工业大学 | A kind of retainer positive and negative discriminating gear |
| CN105548192B (en) * | 2016-02-15 | 2018-03-06 | 无锡速博威迅科技有限公司 | A kind of automatic detection system of direct current shutter |
| CN107315012B (en) * | 2017-06-22 | 2019-10-18 | 福建省万龙新材料科技有限公司 | Composite polycrystal-diamond end face collapses the intelligent detecting method at angle |
| CN107703150B (en) * | 2017-11-01 | 2020-04-14 | 南昌航空大学 | Detection method and detection system for defects of valve head |
| CN108596909A (en) * | 2018-05-09 | 2018-09-28 | 芜湖哈特机器人产业技术研究院有限公司 | Hollow cylinder Surface Flaw Detection system and method |
| CN109187581A (en) * | 2018-07-12 | 2019-01-11 | 中国科学院自动化研究所 | The bearing finished products plate defects detection method of view-based access control model |
| CN109325930B (en) * | 2018-09-12 | 2021-09-28 | 苏州优纳科技有限公司 | Boundary defect detection method, device and detection equipment |
| CN110989587B (en) * | 2019-11-29 | 2023-11-17 | 龙铁纵横（北京）轨道交通科技股份有限公司 | Intelligent fastening control system and method for robot |
| CN111337510A (en) * | 2020-04-20 | 2020-06-26 | 南通大学 | Detection device for lack of fastening buckle of automobile plastic assembly and working method |
| CN113139943B (en) * | 2021-04-22 | 2022-08-12 | 苏州华兴源创科技股份有限公司 | Method and system for detecting appearance defects of open circular ring workpiece and computer storage medium |
| CN114998311A (en) * | 2022-07-11 | 2022-09-02 | 江苏名欧精密机械有限公司 | Part precision detection method based on homomorphic filtering |
| CN115861315B (en) * | 2023-02-27 | 2023-05-30 | 常州微亿智造科技有限公司 | Defect detection method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09210656A (en) * | 1995-11-28 | 1997-08-12 | Nikon Corp | Inspection system |
| CN102411007A (en) * | 2011-08-08 | 2012-04-11 | 长春理工大学 | Surface defect detection system for tiny circular or circular ring-shaped parts |
-
2013
- 2013-10-17 CN CN201310486574.XA patent/CN103499590B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09210656A (en) * | 1995-11-28 | 1997-08-12 | Nikon Corp | Inspection system |
| CN102411007A (en) * | 2011-08-08 | 2012-04-11 | 长春理工大学 | Surface defect detection system for tiny circular or circular ring-shaped parts |
Non-Patent Citations (3)
| Title |
|---|
| 基于机器视觉的圆环形零件形位尺寸自动测量;刘科文等;《工业控制计算机》;20101231;第23卷(第7期);第1-3页 * |
| 基于计算机视觉技术的小尺寸机械零件的尺寸测量***研究;何学科，龙赛琼;《湘潭师范学院学报》;20070930;第29卷(第3期);第35-37页，图3-4 * |
| 机械零件二维几何特征视觉检测***研究与开发;朱晓林等;《中国工程机械学报》;20100630;第8卷(第2期);第199-203页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103499590A (en) | 2014-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103499590B (en) | Ring-shaped work pieces end face defect detection and screening technique and system | |
| CN107255641B (en) | A method of Machine Vision Detection is carried out for self-focusing lens surface defect | |
| CN107705288B (en) | Infrared video detection method for dangerous gas leakage under strong interference of pseudo-target motion | |
| KR102664258B1 (en) | Colony contrast collection | |
| CN109900711A (en) | Workpiece, defect detection method based on machine vision | |
| CN110570393A (en) | mobile phone glass cover plate window area defect detection method based on machine vision | |
| CN102297660B (en) | Measuring method of shield tunnel lining segment seam open width and apparatus thereof | |
| CN105046700B (en) | Fruit surface defect detection method and system based on gamma correction and color classification | |
| CN105046697B (en) | A kind of beer bottleneck localization method assessed based on multiple random loop truss and degree of fitting | |
| CN104297255B (en) | A kind of dixie cup defective vision detection method and system and device | |
| CN109900706A (en) | A kind of weld seam and weld defect detection method based on deep learning | |
| CN109685760B (en) | MATLAB-based SLM powder bed powder laying image convex hull depression defect detection method | |
| CN107014819A (en) | A kind of solar panel surface defects detection system and method | |
| CN107203990A (en) | A kind of labeling damage testing method based on template matches and image quality measure | |
| CN115937199B (en) | Spraying quality detection method for insulating layer of power distribution cabinet | |
| CN106780473B (en) | A kind of magnet ring defect multi-vision visual detection method and system | |
| CN110286124A (en) | Refractory brick measuring system based on machine vision | |
| CN101105459A (en) | Empty bottle mouth defect inspection method and device | |
| CN108596873A (en) | The recognition methods of refractory brick deep defects based on height histogram divion | |
| CN105606619B (en) | Detection and optimized grinding method of casting blank grinding machine | |
| CN110108712A (en) | Multifunctional visual sense defect detecting system | |
| CN106780526A (en) | A kind of ferrite wafer alligatoring recognition methods | |
| CN109146859A (en) | A kind of pavement crack detection system based on machine vision | |
| CN108844961A (en) | A kind of temperature controller case vision detection system and method | |
| CN110763700A (en) | Method and equipment for detecting defects of semiconductor component |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |