CN107084666A - Brake block dimension synthesis detection method based on machine vision - Google Patents
Brake block dimension synthesis detection method based on machine vision Download PDFInfo
- Publication number
- CN107084666A CN107084666A CN201710332039.7A CN201710332039A CN107084666A CN 107084666 A CN107084666 A CN 107084666A CN 201710332039 A CN201710332039 A CN 201710332039A CN 107084666 A CN107084666 A CN 107084666A
- Authority
- CN
- China
- Prior art keywords
- brake block
- image
- mrow
- circle
- machine vision
- 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
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/028—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by measuring lateral position of a boundary of the object
Abstract
The invention discloses a kind of brake block dimension synthesis detection method based on machine vision, comprise the following steps, the first step, according to dimensional tolerance principle and brake block layout design brake block tolerance zone figure, be used as standard form figure.Second step, picture is filtered, binary conversion treatment, rim detection, image scaling are obtained and standard form figure identical pixel size criterion for NI Vision Builder for Automated Inspection collection brake to be checked.3rd step, image progress Hough transformation obtains two central coordinate of circle and determines that the anglec of rotation makes brake block to be checked in image be horizontal after scaling, standard form figure also carries out Hough transformation and obtains two central coordinate of circle simultaneously, two equal-sized images are intercepted by interception center of two width figure central coordinate of circle line midpoints and add operation is carried out, statistics white pixel point number contrasts to obtain testing result with standard form figure white pixel point number.Detection speed of the present invention is fast, and precision is high, it is possible to detect all sizes to be checked of brake block.
Description
Technical field
The invention belongs to brake block detection field, more particularly to a kind of brake block dimension synthesis detection based on machine vision
Method.
Background technology
In the brakes of automobile, brake block is the safety component of most critical, and the quality of all braking effects is all stopped
Car piece plays a decisive role, and the quality of quality of brake pad directly affects the security of the lives and property of driver, and whether brake chip size
Qualified is to evaluate one of key factor of quality of brake pad quality.So the detection to brake block each size is particularly important.
Mainly there are artificial detection method and image procossing detection method for brake block size detecting method at present.Artificial detection side
Method relies primarily on slide measure, micrometer equidimension measuring instrument and carries out dimensional measurement, in recent years, with computer science sum
The fast development of word image processing techniques, also has using general image procossing detection brake chip size.
General manual detection efficiency is low, and testing result is big by man's activity, and precision is low, has been not suitable with modern technologies
Development, but general image procossing detected size also has limitation, general image processing method can only detect determinand
The portion size of body, such as maximum length and wide, diameter of a circle, can not detect whether other curves or arc equidimension close
Lattice.
The content of the invention
There is provided a kind of brake block dimension synthesis detection side based on machine vision for the problems of the prior art by the present invention
Method.
The technical solution adopted for the present invention to solve the technical problems is：A kind of brake block chi based on machine vision is provided
Very little method for comprehensive detection, comprises the following steps, and 1) according to dimensional tolerance principle and brake block layout design brake block dimensional tolerance
Band figure, is used as standard form figure；2) NI Vision Builder for Automated Inspection collection it is to be checked brake picture be filtered, binary conversion treatment, edge
Detection, image scaling are obtained and standard form figure identical pixel size criterion；3) image progress Hough transformation is obtained after scaling
Two central coordinate of circle determine that the anglec of rotation makes brake block to be checked in image be horizontal, while standard form figure also carries out Hough change
Get in return to two central coordinate of circle, two equal-sized images are intercepted by interception center of two width figure central coordinate of circle line midpoints and are gone forward side by side
Row add operation, statistics white pixel point number contrasts to obtain testing result with standard form figure white pixel point number.
By above-mentioned technical proposal, the step 1) in, dimensional tolerance principle mainly include hole and axle dimension limit principle,
Straight line class size allows variation principle.
By above-mentioned technical proposal, the step 1) in, brake block drawing is provided by brake block manufacturer, design brake chip size
Drawing of tolerance range is designed by CAD mapping softwares and saves as bmp picture formats, is used as standard form figure.
By above-mentioned technical proposal, the step 2) in, NI Vision Builder for Automated Inspection specifically includes the shooting of CCD high-resolution kilomega network
Head, camera lens, annular light source, computer.
By above-mentioned technical proposal, the step 2) in, binary conversion treatment is specifically included, if original image f (x, y) is utilized
OTSU Threshold segmentations find a suitable gray value as threshold value t in f (x, y), then the image after splitting is：
By above-mentioned technical proposal, the step 2) in, rim detection is realized using robert edge detection operators.
By above-mentioned technical proposal, the step 2) in, image scaling is to determine its scaling using minimum enclosed rectangle algorithm
Multiple, bianry image and standard drawing all carry out obtaining two minimum enclosed rectangle length and quant's sign after minimum enclosed rectangle, obtain
The scaling multiple of bianry image is determined to both length and width differences and is zoomed in and out so that bianry image is obtained and standard form image
Identical pixel size criterion.
By above-mentioned technical proposal, the step 3) in, image carries out Hough transformation and obtains the determination of two central coordinate of circle after scaling
The anglec of rotation makes in image brake block to be checked is horizontal to be to determine the anglec of rotation using the difference of two center of circle abscissas,
Two center of circle abscissas are equal after image rotation.
The beneficial effect comprise that：The present invention takes into full account artificial and general pattern processing detection brake block chi
The limitation of very little method have effectively achieved pair there is provided a kind of brake block dimension synthesis detection method based on machine vision
Chip size brake more rapidly, the higher detection of precision, and can detect whether all sizes to be checked are qualified.
Brief description of the drawings
Below in conjunction with drawings and Examples, the invention will be further described, in accompanying drawing：
Fig. 1 is the schematic flow sheet of brake block dimension synthesis detection method of the embodiment of the present invention；
Fig. 2 is brake block tolerance zone (standard form) figure in the embodiment of the present invention；
Fig. 3 is the image after rim detection in the embodiment of the present invention；
Fig. 4 is qualified brake block image detection result figure in the embodiment of the present invention；
Fig. 5 is unqualified brake block image detection result figure in the embodiment of the present invention.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only to explain the present invention, not
For limiting the present invention.
There is provided a kind of brake block dimension synthesis detection method based on machine vision in the embodiment of the present invention, including it is following
Step, 1) according to dimensional tolerance principle and brake block layout design brake block tolerance zone figure, it is used as standard form figure；2) machine
Picture is filtered, binary conversion treatment, rim detection, image scaling are obtained and master die for device vision system collection brake to be checked
Plate figure identical pixel size criterion；3) image progress Hough transformation obtains two central coordinate of circle and determines that the anglec of rotation makes figure after scaling
Brake block to be checked is horizontal as in, while standard form figure, which also carries out Hough transformation, obtains two central coordinate of circle, with two width figures
Central coordinate of circle line midpoint is that interception center intercepts two equal-sized images and carries out add operation, counts white pixel point
Number contrasts to obtain testing result with standard form figure white pixel point number.
Wherein, the step 1) in, dimensional tolerance principle mainly includes dimension limit principle, the straight line class size of hole and axle
Size allows variation principle.
Further, the step 1) in, brake block drawing is provided by brake block manufacturer, designs brake block tolerance zone
Figure is designed by CAD mapping softwares and saves as bmp picture formats, is used as standard form figure.
Wherein, the step 2) in, NI Vision Builder for Automated Inspection specifically includes CCD high-resolution kilomega networks camera, camera lens, ring
Shape light source, computer.
Further, the step 2) in, binary conversion treatment is specifically included, if original image f (x, y) utilizes OTSU thresholds
Value, which is segmented in f (x, y), finds a suitable gray value as threshold value t, then the image after splitting is：
Further, the step 2) in, rim detection is realized using robert edge detection operators.
Further, the step 2) in, image scaling is to determine its scaling multiple using minimum enclosed rectangle algorithm,
Bianry image and standard drawing all carry out obtaining two minimum enclosed rectangle length and quant's sign after minimum enclosed rectangle, obtain both and grow
Wide difference determines the scaling multiple of bianry image and zoomed in and out so that bianry image is obtained and standard form image identical picture
Plain dimensional standard.
Wherein, the step 3) in, image progress Hough transformation obtains two central coordinate of circle and determines that the anglec of rotation makes after scaling
It is to be determined using the difference of two center of circle abscissas after the anglec of rotation, image rotation that brake block to be checked, which is horizontal, in image
Two center of circle abscissas are equal.
In presently preferred embodiments of the present invention, as shown in figure 1, provided first according to dimensional tolerance principle and brake block business men
Brake block drawing designs brake block tolerance zone figure using CAD mapping softwares, and saves as bmp picture formats, is used as standard
Prototype drawing, such as Fig. 2 are brake block tolerance zone (standard form) figures in the embodiment of the present invention.
Secondly brake block picture to be checked is gathered using CCD high-resolution kilomega networks camera in NI Vision Builder for Automated Inspection, gone forward side by side
Row filtering, binary conversion treatment, rim detection, image scaling processing, process is to be filtered first and binary conversion treatment, if
Original image f (x, y) finds a suitable gray value as threshold value t using OTSU Threshold segmentations in f (x, y), then splits
Image afterwards is：
Wherein, threshold value t is 60 optimal in the present embodiment.
Obtain bianry image and carry out robert rim detections, obtain edge contour figure, such as Fig. 3 is side in the embodiment of the present invention
Image after edge detection.
Bianry image is desired to make money or profit with standard form simultaneously obtains minimum enclosed rectangle length and width spy with minimum enclosed rectangle algorithm
Levy, the ratio between width of the length of two figures and two figures determines the scaling multiple of bianry image, and bianry image is zoomed in and out, while edge graph
Identical multiple scaling is carried out, is all obtained and standard form figure identical pixel size criterion.
Finally, after two figures are unified pixel standard, edge graph carries out Hough transformation and obtains two central coordinate of circle, the horizontal stroke in two centers of circle
Coordinate difference determines the anglec of rotation, and the abscissa in two centers of circle is identical after rotation, meanwhile, standard form figure also carries out Hough transformation and obtained
To two central coordinate of circle, two equal-sized images are then intercepted by interception center of two width figure central coordinate of circle line midpoints and are gone forward side by side
Row add operation counts white pixel point number, the white pixel point number of image and the white picture of standard form figure after being added
Vegetarian refreshments number compares, if both are equal, i.e. the white pixel point of edge graph all in standard form figure white pixel point,
Brake block size qualification to be checked, such as Fig. 4 is qualified brake block image detection result figure in the embodiment of the present invention；If both are not
Deng that is, the white pixel point of edge graph is not all in standard form figure white pixel point, brake block off-dimension to be checked, such as
Fig. 5 is unqualified brake block image detection result figure in the embodiment of the present invention, and detection is finished.Stopping based on machine vision of the invention
Car chip size method for comprehensive detection, is realized to brake chip size more rapidly, the higher detection of precision, and can detect to be needed
Whether dipping cun is qualified.
It should be appreciated that for those of ordinary skills, can according to the above description be improved or converted, and
All these modifications and variations should all belong to scope of the appended claims of the present invention.
Claims (8)
1. a kind of brake block dimension synthesis detection method based on machine vision, it is characterised in that comprise the following steps, 1) basis
Dimensional tolerance principle and brake block layout design brake block tolerance zone figure, are used as standard form figure；2) NI Vision Builder for Automated Inspection
Picture is filtered, binary conversion treatment, rim detection, image scaling are obtained and standard form figure identical for collection brake to be checked
Pixel size criterion；3) image progress Hough transformation obtains two central coordinate of circle and determines that the anglec of rotation makes to be checked in image stop after scaling
Car piece is horizontal, while standard form figure, which also carries out Hough transformation, obtains two central coordinate of circle, is connected with two width figure central coordinate of circle
Line midpoint is that interception center intercepts two equal-sized images and carries out add operation, statistics white pixel point number and standard
Prototype drawing white pixel point number contrasts to obtain testing result.
2. the brake block dimension synthesis detection method according to claim 1 based on machine vision, it is characterised in that described
Step 1) in, dimensional tolerance principle, which mainly includes hole and dimension limit principle, the straight line class size of axle, allows variation former
Then.
3. the brake block dimension synthesis detection method according to claim 1 based on machine vision, it is characterised in that described
Step 1) in, brake block drawing is provided by brake block manufacturer, and design brake block tolerance zone figure is designed simultaneously by CAD mapping softwares
Bmp picture formats are saved as, standard form figure is used as.
4. the brake block dimension synthesis detection method according to claim 1 based on machine vision, it is characterised in that described
Step 2) in, NI Vision Builder for Automated Inspection specifically includes CCD high-resolution kilomega networks camera, camera lens, annular light source, computer.
5. the brake block dimension synthesis detection method according to claim 1 based on machine vision, it is characterised in that described
Step 2) in, binary conversion treatment is specifically included, if original image f (x, y) finds one using OTSU Threshold segmentations in f (x, y)
Individual suitable gray value is as threshold value t, then the image after splitting is：
<mrow>
<mi>g</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mn>1</mn>
</mtd>
<mtd>
<mrow>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>&GreaterEqual;</mo>
<mi>t</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>0</mn>
</mtd>
<mtd>
<mrow>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo><</mo>
<mi>t</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
6. the brake block dimension synthesis detecting method according to claim 1 based on machine vision, it is characterised in that the step
It is rapid 2) in, rim detection is realized using robert edge detection operators.
7. the brake block dimension synthesis detection method according to claim 1 based on machine vision, it is characterised in that described
Step 2) in, image scaling is to determine its scaling multiple using minimum enclosed rectangle algorithm, and bianry image and standard drawing all enter
Two minimum enclosed rectangle length and quant's sign are obtained after row minimum enclosed rectangle, both length and width differences is obtained and determines bianry image
Scaling multiple is simultaneously zoomed in and out so that bianry image is obtained and standard form image identical pixel size criterion.
8. the brake block dimension synthesis detection method according to claim 1 based on machine vision, it is characterised in that described
Step 3) in, image carries out Hough transformation and obtains two central coordinate of circle determining that the anglec of rotation makes the brake block to be checked in image be in after scaling
Horizontality is to determine that two center of circle abscissas are equal after the anglec of rotation, image rotation using the difference of two center of circle abscissas.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710332039.7A CN107084666B (en) | 2017-05-10 | 2017-05-10 | Comprehensive detection method for size of brake pad based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710332039.7A CN107084666B (en) | 2017-05-10 | 2017-05-10 | Comprehensive detection method for size of brake pad based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107084666A true CN107084666A (en) | 2017-08-22 |
| CN107084666B CN107084666B (en) | 2020-08-28 |
Family
ID=59613072
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710332039.7A Active CN107084666B (en) | 2017-05-10 | 2017-05-10 | Comprehensive detection method for size of brake pad based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107084666B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108279241A (en) * | 2017-10-20 | 2018-07-13 | 同济大学 | A kind of workpiece configurations detection method based on machine vision |
| CN108287250A (en) * | 2018-02-01 | 2018-07-17 | 中国计量大学 | Escalator step speed-measuring method based on machine vision |
| CN108460776A (en) * | 2018-04-12 | 2018-08-28 | 广东工业大学 | A kind of brake block size detecting method and device based on machine vision |
| CN109087292A (en) * | 2018-07-27 | 2018-12-25 | 广东工业大学 | A kind of thermal transfer film glue deviation detection method based on machine vision |
| CN109099818A (en) * | 2018-06-27 | 2018-12-28 | 武汉理工大学 | Portable micron order high definition range-measurement system |
| CN109174674A (en) * | 2018-07-26 | 2019-01-11 | 昆山睿力得软件技术有限公司 | A kind of detection device for automotive brake pads |
| CN109211110A (en) * | 2018-09-18 | 2019-01-15 | 佛山科学技术学院 | A kind of flat-type workpiece size detection system and method based on machine vision |
| CN110008955A (en) * | 2019-04-01 | 2019-07-12 | 中国计量大学 | A kind of automotive brake pads face character coining quality inspection method |
| CN110230978A (en) * | 2018-03-14 | 2019-09-13 | 浙江大学山东工业技术研究院 | A kind of refractory brick geometric dimension measurement method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000161921A (en) * | 1998-12-01 | 2000-06-16 | Dainippon Printing Co Ltd | Dimension measuring device |
| CN101751572A (en) * | 2008-12-05 | 2010-06-23 | 比亚迪股份有限公司 | Pattern detection method, device, equipment and system |
| CN103793712A (en) * | 2014-02-19 | 2014-05-14 | 华中科技大学 | Image recognition method and system based on edge geometric features |
| CN103914827A (en) * | 2013-09-06 | 2014-07-09 | 贵州大学 | Method for visual inspection of shortages of automobile sealing strip profile |
| CN104298993A (en) * | 2014-01-09 | 2015-01-21 | 郑州金惠计算机系统工程有限公司 | Pole number positioning and identification method suitable for railway line in complex scene |
| CN104711784A (en) * | 2015-04-01 | 2015-06-17 | 华中科技大学 | Method for obtaining sewing path of cut pieces |
| CN105381961A (en) * | 2015-12-23 | 2016-03-09 | 胡琳丽 | Comprehensive detection device for brake blocks |
| CN106568385A (en) * | 2016-01-29 | 2017-04-19 | 中国计量学院 | Automobile brake pad dimension machine vision automatic measuring system based on dual cameras |
-
2017
- 2017-05-10 CN CN201710332039.7A patent/CN107084666B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000161921A (en) * | 1998-12-01 | 2000-06-16 | Dainippon Printing Co Ltd | Dimension measuring device |
| CN101751572A (en) * | 2008-12-05 | 2010-06-23 | 比亚迪股份有限公司 | Pattern detection method, device, equipment and system |
| CN103914827A (en) * | 2013-09-06 | 2014-07-09 | 贵州大学 | Method for visual inspection of shortages of automobile sealing strip profile |
| CN104298993A (en) * | 2014-01-09 | 2015-01-21 | 郑州金惠计算机系统工程有限公司 | Pole number positioning and identification method suitable for railway line in complex scene |
| CN103793712A (en) * | 2014-02-19 | 2014-05-14 | 华中科技大学 | Image recognition method and system based on edge geometric features |
| CN104711784A (en) * | 2015-04-01 | 2015-06-17 | 华中科技大学 | Method for obtaining sewing path of cut pieces |
| CN105381961A (en) * | 2015-12-23 | 2016-03-09 | 胡琳丽 | Comprehensive detection device for brake blocks |
| CN106568385A (en) * | 2016-01-29 | 2017-04-19 | 中国计量学院 | Automobile brake pad dimension machine vision automatic measuring system based on dual cameras |
Non-Patent Citations (4)
| Title |
|---|
| WANJI LIU 等: "《Precision size measurement instrument for irregular objects》", 《2015 INTERNATIONAL CONFERENCE ON ADVANCED MECHATRONIC SYSTEMS》 * |
| 宾鸿赞 等: "《先进加工过程技术》", 30 September 2009, 华中科技大学出版社 * |
| 牟洪波 等: "《基于BP和RBF神经网络的木材缺陷检测研究》", 31 May 2011, 哈尔滨工程大学出版社 * |
| 胡琳丽 等: "《刹车片尺寸自动检测装置设计》", 《中国计量大学学报》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108279241A (en) * | 2017-10-20 | 2018-07-13 | 同济大学 | A kind of workpiece configurations detection method based on machine vision |
| CN108287250A (en) * | 2018-02-01 | 2018-07-17 | 中国计量大学 | Escalator step speed-measuring method based on machine vision |
| CN110230978A (en) * | 2018-03-14 | 2019-09-13 | 浙江大学山东工业技术研究院 | A kind of refractory brick geometric dimension measurement method |
| CN108460776A (en) * | 2018-04-12 | 2018-08-28 | 广东工业大学 | A kind of brake block size detecting method and device based on machine vision |
| CN108460776B (en) * | 2018-04-12 | 2022-03-25 | 广东工业大学 | Brake pad size detection method and device based on machine vision |
| CN109099818A (en) * | 2018-06-27 | 2018-12-28 | 武汉理工大学 | Portable micron order high definition range-measurement system |
| CN109174674A (en) * | 2018-07-26 | 2019-01-11 | 昆山睿力得软件技术有限公司 | A kind of detection device for automotive brake pads |
| CN109087292A (en) * | 2018-07-27 | 2018-12-25 | 广东工业大学 | A kind of thermal transfer film glue deviation detection method based on machine vision |
| CN109211110A (en) * | 2018-09-18 | 2019-01-15 | 佛山科学技术学院 | A kind of flat-type workpiece size detection system and method based on machine vision |
| CN110008955A (en) * | 2019-04-01 | 2019-07-12 | 中国计量大学 | A kind of automotive brake pads face character coining quality inspection method |
| CN110008955B (en) * | 2019-04-01 | 2020-12-15 | 中国计量大学 | Method for testing character imprinting quality of surface of automobile brake pad |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107084666B (en) | 2020-08-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107084666A (en) | Brake block dimension synthesis detection method based on machine vision | |
| CN106952250B (en) | Metal plate strip surface defect detection method and device based on fast R-CNN network | |
| CN101634551B (en) | Method and system for detecting surface roughness | |
| CN106407981B (en) | A kind of licence plate recognition method, apparatus and system | |
| CN107180416B (en) | Train wheel tread image deformity correction method and system | |
| CN101799434B (en) | Printing image defect detection method | |
| CN102496161B (en) | Method for extracting contour of image of printed circuit board (PCB) | |
| CN107014819A (en) | A kind of solar panel surface defects detection system and method | |
| CN106372667A (en) | Method for detecting adverse state of inclined sleeve part screws of high-speed train overhead line system | |
| CN112001917A (en) | Machine vision-based geometric tolerance detection method for circular perforated part | |
| CN103034850A (en) | Trouble of moving freight car detection system (TFDS) block key loss fault automatic identification method | |
| CN103439348A (en) | Remote controller key defect detection method based on difference image method | |
| CN107622277A (en) | A kind of complex-curved defect classification method based on Bayes classifier | |
| JP2019027826A (en) | Defect inspection method and defect inspection device | |
| CN102880859A (en) | Method for recognizing number plate | |
| CN107240086A (en) | A kind of fabric defects detection method based on integration nomography | |
| TWI512284B (en) | Bubble inspection system for glass | |
| CN110987954B (en) | Method and system for eliminating leather surface defect detection blind area | |
| Wang et al. | License plate location algorithm based on edge detection and morphology | |
| CN106989672A (en) | A kind of workpiece measuring based on machine vision | |
| CN111415348B (en) | Method for extracting bubble characteristics in automobile brake pipeline | |
| CN109614868A (en) | Automobile tire decorative pattern graph line identifying system | |
| CN104616281A (en) | Distance online detection method applied to double-filament bulb | |
| Li et al. | Detection of small size defects in belt layer of radial tire based on improved faster r-cnn | |
| Zhao et al. | Research on road traffic sign recognition based on video image |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Xu Zhiling Inventor after: Hu Linli Inventor before: Hu Linli Inventor before: Xu Zhiling |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |