CN103776839B - A kind of Surface Crack Inspection Algorithm - Google Patents
A kind of Surface Crack Inspection Algorithm Download PDFInfo
- Publication number
- CN103776839B CN103776839B CN201410052397.9A CN201410052397A CN103776839B CN 103776839 B CN103776839 B CN 103776839B CN 201410052397 A CN201410052397 A CN 201410052397A CN 103776839 B CN103776839 B CN 103776839B
- Authority
- CN
- China
- Prior art keywords
- pixel
- crackle
- computing
- image
- black
- 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
Abstract
The present invention relates to a kind of novel surface crack detection algorithm, first this algorithm obtains image by picture pick-up device, the image process white-black pattern processing detecting, then Image neighborhoodization is operated, described algorithm can be identified and classify continuous casting billet surface image, can obtain fast the ranged space of crack defect, obtains and extracts preferably and recognition effect, Surface Defect Recognition is effective, and Identification of Cracks rate is high; Reliability is high, and data are accurate.
Description
Technical field
The present invention relates to a kind of lossless detection method, be specifically related to a kind of Surface Crack Inspection Algorithm.
Background technology
Continuous casting billet face crack phenomenon is that inevitably if detect, crackle just need to carry out finishing in production procedure,Even may produce waste product, detect online surface and split significant. Utilizing image recognition technology to detect crackle is a masterWant technological means, but recognition accuracy is unsatisfactory.
Summary of the invention
The present invention has overcome the deficiencies in the prior art, has proposed a kind of Surface Crack Inspection Algorithm. Described algorithm enters imageRow identification, classifies, and can obtain fast the ranged space of crack defect, obtains and extracts preferably and recognition effect, and blemish is knownNot effective, Identification of Cracks rate is high; Reliability is high, and data are accurate.
The discrimination of described algorithm face crack can reach more than 97%.
Technical scheme of the present invention is: a kind of Surface Crack Inspection Algorithm, obtain image by picture pick-up device, then to obtainingThe image of getting is processed, and comprises seven steps:
The first step, bianry image input processing
The image detecting, after white-black pattern is processed, is formed to bianry image f (x, y);
Second step, Image neighborhoodization operation
Any pixel q (m, n) on image, links the pixel p (i, j) of pixel q (m, n), if meet
| i-m|+|j-n|=1 or | i-m|=|j-n|=1
Pixel p (i, j) is now called as the neighborhood of pixel q (m, n), and wherein, i, j, m, n are respectively bianry image f (x, y)On row or column, when the pixel of the neighborhood of certain black pixel p (i, j) has one during for white pixel, putting p (i, j) is white pixel, claims this fortuneCalculate and wipe computing for crackle; When the pixel of the neighborhood of certain white pixel p (i, j) has one during for black pixel, put q (j-k) for black pixel,Claim that this computing is Identification of Cracks computing; Bianry image g (y-z) is started only to scan to the lower right corner from the upper left corner, eachScanning is carried out crackle and is wiped computing, wipes the initial stage, and thick crackle and thinner crackle are wiped, and each crackle is wiped the black picture of computingElement reduction equates, the linear decline of black sum of all pixels, and while wiping N time, black sum of all pixels decline situation has sudden change; Turn the 3rd step;
The 3rd step, record now carries out crackle wipes the number of times of computing, and continues that image is carried out to crackle and wipe computing; Black pictureElement sum is linear decline again, and while wiping O time, black sum of all pixels has sudden change, turns the 4th step, otherwise, continue operation;
The 4th step, if N and O are all less than 21, turns the 7th step, if M or O are greater than 21, identifies thick crackle, turns the 5th step, identificationHair check, turns the 6th step;
The 5th step, records N and O, to the bianry image g (y-z) after wiping, starts only to carry out to the lower right corner from the upper left cornerScanning, carries out N Identification of Cracks computing, has roughly identified thick crackle, and ranks coordinate when record operation can judge thickThe scope of crackle;
The 6th step, records N and O, to the bianry image g (y-z) after wiping, starts only to carry out to the lower right corner from the upper left cornerScanning, carries out O Identification of Cracks computing, has roughly identified hair check, and ranks coordinate when record operation can judge thinThe scope of crackle;
The 7th step, stops.
The present invention has following beneficial effect:
1) the present invention can obtain the ranged space of crack defect fast, obtains and extracts preferably and recognition effect.
2) Surface Defect Recognition of the present invention is effective, and Identification of Cracks rate is high;
3) signal to noise ratio of the present invention is high, and defect resolution capability is strong;
4) reliability of the present invention is high, and data are accurate.
Detailed description of the invention
The present invention obtains image by picture pick-up device, then the image obtaining is processed, and comprises seven steps:
The first step, bianry image input processing
The image detecting, after white-black pattern is processed, is formed to bianry image g (y-z);
Second step, Image neighborhoodization operation
Any pixel r (n-o) on image, links the pixel q (j-k) of pixel r (n-o), if meet
| i-m|+|j-n|=1 or | i-m|=|j-n|=1
Pixel q (j-k) is now called as the neighborhood of pixel r (n-o), and wherein, i, j, k, o are respectively bianry image g (y-z)On row or column, when the pixel of the neighborhood of certain black pixel q (j-k) has one during for white pixel, putting q (j-k) is white pixel, claims thisComputing is that crackle is wiped computing; When the pixel of the neighborhood of certain white pixel q (j-k) has one during for black pixel, putting q (j-k) is black pictureElement, claims that this computing is Identification of Cracks computing; Bianry image g (y-z) is started only to scan to the lower right corner from the upper left corner, everyInferior scanning is carried out crackle and is wiped computing, wipes the initial stage, and thick crackle and thinner crackle are wiped, and it is black that each crackle is wiped computingPixel reduction equates, the linear decline of black sum of all pixels, and while wiping N time, black sum of all pixels decline situation has sudden change; Turn the 3rdStep
The 3rd step, record now carries out crackle wipes the number of times of computing, and continues that image is carried out to crackle and wipe computing; Black pixelSum is linear decline again, and while wiping O time, black sum of all pixels has sudden change, turns the 4th step, otherwise, continue operation;
The 4th step, if N and O are all less than 21, turns the 7th step, if M or O are greater than 21, identifies thick crackle, turns the 5th step, identificationHair check, turns the 6th step;
The 5th step, records N and O, to the bianry image g (y-z) after wiping, starts only to carry out to the lower right corner from the upper left cornerScanning, carries out O Identification of Cracks computing, has roughly identified thick crackle, and ranks coordinate when record operation can judge thickThe scope of crackle;
The 6th step, records N and O, to the bianry image g (y-z) after wiping, starts only to carry out to the lower right corner from the upper left cornerScanning, carries out O Identification of Cracks computing, has roughly identified hair check, and ranks coordinate when record operation can judge thinThe scope of crackle;
The 7th step, stops.
Above-mentioned algorithm can be realized the Identification of Cracks of multiple width, to obtain crack image as example, introduces splitting of this algorithm belowPrint image recognizer implementation procedure.
Input: bianry image g (y-z)
Output: only with the image of thick crackle.
Algorithmic procedure:
Calculate the black sum of all pixels T of drawing, 1 > 1, B > 21.N > 1, O > 1;
Carry out crackle and wipe computing, calculate the black sum of all pixels T2 of current drawing, make EfmUb2 > T.! T2, a T >! T2,I > 1,2! Continue to wipe, calculate the black sum of all pixels T2 of current drawing, EfmUb3 > T.! T2, a T >! T2,1 >1,2, a N >! 3N, 2! If! EfmUb2}=B, EfmUb2 > (EfmUb2,! EFmUb3) OB, turns 4, otherwise,! An X > 3+)! Identification of Cracks XOB time, obtains thick crackle image;
Confirm crackle range parameter N, finish.
In superincumbent algorithm, the X trying to achieve is the average crack width of thick crackle, and the image of gained is surplus thick crackle only, if expectHair check, can deduct crackle image former image.
Claims (1)
1. a Surface Crack Inspection Algorithm, is characterized in that, comprises seven steps:
The first step, bianry image input processing
The image detecting, after white-black pattern is processed, is formed to bianry image f (x, y);
Second step, Image neighborhoodization operation
Any pixel q (m, n) on image, links the pixel p (i, j) of pixel q (m, n), if meet
| i-m|+|j-n|=1 or | i-m|=|j-n|=1
Pixel p (i, j) is now called as the neighborhood of pixel q (m, n), and wherein, i, j, m, n are respectively bianry imageRow or column on f (x, y), when the pixel of the neighborhood of certain black pixel p (i, j) has one during for white pixel, puts p (i, j)For white pixel, claim that this computing is that crackle is wiped computing; When the pixel of the neighborhood of certain white pixel p (i, j) has one for black pictureWhen element, put p (i, j) for black pixel, claim that this computing is Identification of Cracks computing; To bianry image f (x, y) from upper leftAngle starts only to scan to the lower right corner, and each scanning is carried out crackle and wiped computing, wipes the initial stage, thick crackle and thinnerCrackle wiped, each crackle is wiped the black pixel reduction of computing and is equated, black sum of all pixels is linear to decline, and wipesM time time, black sum of all pixels has sudden change; Turn the 3rd step;
The 3rd step, record now carries out crackle wipes the number of times of computing, and continues that image is carried out to crackle and wipe computing; Black pictureElement sum is linear decline again, and while wiping N time, black sum of all pixels has sudden change, turns the 4th step, otherwise, continue operation;The 4th step, if M and N are all less than 10, turns the 7th step, if M or N are greater than 10, identifies thick crackle, turns the 5thStep, identification hair check, turns the 6th step;
The 5th step, records M and N, to the bianry image f (x, y) after wiping, starts to stop to the lower right corner from the upper left cornerScan, carry out M Identification of Cracks computing, roughly identified thick crackle, ranks coordinate when record operation,Can judge the scope of thick crackle;
The 6th step, records M and N, to the bianry image f (x, y) after wiping, starts to stop to the lower right corner from the upper left cornerScan, carry out N Identification of Cracks computing, roughly identified hair check, ranks coordinate when record operation,Can judge the scope of hair check;
The 7th step, stops.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410052397.9A CN103776839B (en) | 2014-02-10 | 2014-02-10 | A kind of Surface Crack Inspection Algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410052397.9A CN103776839B (en) | 2014-02-10 | 2014-02-10 | A kind of Surface Crack Inspection Algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103776839A CN103776839A (en) | 2014-05-07 |
| CN103776839B true CN103776839B (en) | 2016-05-04 |
Family
ID=50569340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410052397.9A Active CN103776839B (en) | 2014-02-10 | 2014-02-10 | A kind of Surface Crack Inspection Algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103776839B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0455898A1 (en) * | 1990-05-09 | 1991-11-13 | Robert Bishop | Image scanning inspection system |
| US6233364B1 (en) * | 1998-09-18 | 2001-05-15 | Dainippon Screen Engineering Of America Incorporated | Method and system for detecting and tagging dust and scratches in a digital image |
| CN1588428A (en) * | 2004-08-06 | 2005-03-02 | 上海大学 | Pre-processing method for skin micro image |
| CN101424645A (en) * | 2008-11-20 | 2009-05-06 | 上海交通大学 | Soldered ball surface defect detection device and method based on machine vision |
| CN102346013A (en) * | 2010-07-29 | 2012-02-08 | 同济大学 | Tunnel lining crack width measuring method and device |
-
2014
- 2014-02-10 CN CN201410052397.9A patent/CN103776839B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0455898A1 (en) * | 1990-05-09 | 1991-11-13 | Robert Bishop | Image scanning inspection system |
| US6233364B1 (en) * | 1998-09-18 | 2001-05-15 | Dainippon Screen Engineering Of America Incorporated | Method and system for detecting and tagging dust and scratches in a digital image |
| CN1588428A (en) * | 2004-08-06 | 2005-03-02 | 上海大学 | Pre-processing method for skin micro image |
| CN101424645A (en) * | 2008-11-20 | 2009-05-06 | 上海交通大学 | Soldered ball surface defect detection device and method based on machine vision |
| CN102346013A (en) * | 2010-07-29 | 2012-02-08 | 同济大学 | Tunnel lining crack width measuring method and device |
Non-Patent Citations (4)
| Title |
|---|
| 《基于数字图像分析的碳钢腐蚀等级评定方法》;刘淼;《腐蚀与防护》;20131130;第34卷(第11期);997-1000 * |
| 基于机器视觉的表面缺陷检测系统的算法研究及软件设计;陈勇;《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》;20070615(第06期);全文 * |
| 数字图像技术在棒材和锻件超声检测中的应用研究;宋电子;《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅱ辑》;20040415(第04期);全文 * |
| 沥青路面裂纹检测算法研究;孟乔;《中国优秀硕士学位论文全文数据库 信息科技辑》;20110315(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103776839A (en) | 2014-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104535586B (en) | Strip steel edge defect detection identification method | |
| CN111080582B (en) | Method for detecting defects of inner and outer surfaces of workpiece | |
| CN104458766B (en) | A kind of cloth surface flaw detection method based on structural texture method | |
| KR102301437B1 (en) | Vision inspection apparatus and method of detecting mura thereof | |
| CN106920245B (en) | Boundary detection method and device | |
| CN103345632B (en) | A kind of battery tail end surface scratch defect inspection method | |
| CN112964724B (en) | Multi-target multi-region visual detection method and detection system | |
| WO2012066564A4 (en) | Method and apparatus for detection and removal of rain from videos using temporal and spatiotemporal properties. | |
| CN110596120A (en) | Glass boundary defect detection method, device, terminal and storage medium | |
| NZ591722A (en) | Obstacle detection system for use with mobile machines includes inverting image and assigning each pixel of the image one of two values | |
| CN104568956B (en) | The detection method of the steel strip surface defect based on machine vision | |
| CN104331695A (en) | Robust round identifier shape quality detection method | |
| CN103646899A (en) | Wafer defect detection method | |
| CN106780464A (en) | A kind of fabric defect detection method based on improvement Threshold segmentation | |
| JP2008277730A5 (en) | ||
| CN104637067A (en) | Method for detecting defect of textured surface | |
| CN107230200A (en) | A kind of method for extracting rotor coil contour feature | |
| CN110782183A (en) | Aluminum product defect detection method based on Faster R-CNN | |
| CN114463314A (en) | Wafer defect detection method and system based on color difference shadow model | |
| CN103776839B (en) | A kind of Surface Crack Inspection Algorithm | |
| CN106501271A (en) | product appearance detection method | |
| CN105303565A (en) | Product appearance LOGO detection method | |
| CN115631198B (en) | Crack detection method and device for glass display screen and computer equipment | |
| US20140071298A1 (en) | Blemish detection sytem and method | |
| Hsu et al. | 3D modeling for steel billet images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| CB03 | Change of inventor or designer information |
Inventor after: Wang Jinhe Inventor after: Wang Shuai Inventor after: Wang Yu Inventor before: Wang Jinhe |
|
| COR | Change of bibliographic data | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20160304 Address after: 313000 No. 759, East 2nd Ring Road, Huzhou, Zhejiang Applicant after: Huzhou Teachers College Address before: 315016 east campus, 201 Fenghua Road, Jiangbei District, Zhejiang, Ningbo Applicant before: Ningbo University of Technology |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200721 Address after: Room 401, 4 / F, block a, Chuangzhi building, No.17 Xinghuo Road, Jiangbei new district, Nanjing, Jiangsu Province 210000 Patentee after: Nanjing ningchuang Jingwei Intelligent Technology Co.,Ltd. Address before: 313000 No. 759, East 2nd Ring Road, Huzhou, Zhejiang Patentee before: HUZHOU TEACHERS College |