CN108872252A - A kind of girder steel flaw detection system - Google Patents

A kind of girder steel flaw detection system Download PDF

Info

Publication number
CN108872252A
CN108872252A CN201810882961.8A CN201810882961A CN108872252A CN 108872252 A CN108872252 A CN 108872252A CN 201810882961 A CN201810882961 A CN 201810882961A CN 108872252 A CN108872252 A CN 108872252A
Authority
CN
China
Prior art keywords
girder steel
detected
image
pixel
module
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.)
Pending
Application number
CN201810882961.8A
Other languages
Chinese (zh)
Inventor
韦玥
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Yixin Intelligent Technology Co Ltd
Original Assignee
Shenzhen Yixin Intelligent Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Yixin Intelligent Technology Co Ltd filed Critical Shenzhen Yixin Intelligent Technology Co Ltd
Priority to CN201810882961.8A priority Critical patent/CN108872252A/en
Publication of CN108872252A publication Critical patent/CN108872252A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/8851Scan 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
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/8851Scan 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
    • G01N2021/8887Scan 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 present invention provides a kind of girder steel flaw detection system, which includes:Girder steel image capture module, for acquiring the original image of girder steel to be detected;Girder steel image processing module, for being denoised to the original image of acquisition, edge detection and enhancing processing, obtain the target image of girder steel to be detected;Girder steel extracting thermal crack module, for extracting the characteristic of girder steel to be detected from target image;Girder steel crack identification module judges girder steel to be detected with the presence or absence of crackle for matching the characteristic of the girder steel for the flawless being pre-stored in the characteristic of girder steel to be detected and database.The present invention can quickly and accurately extract the characteristic of girder steel to be detected, and identify girder steel to be detected with the presence or absence of crackle, in favor of rapidly and accurately being excluded to failure, improve the economic benefit of factory and the personal safety of safeguard work personnel.

Description

A kind of girder steel flaw detection system
Technical field
The present invention relates to fault diagnosis technologies and information process analysis technical field, and in particular to a kind of girder steel crack detection System.
Background technique
The girder steel that industry and enterprise use is once cracked on surface, will produce to it and cause great economic loss With cause serious human safety issues, the guide rail at top especially in production line, in by the operation of hanger idler wheel upwards or Downward extruding component, stress accumulation will lead to destruction fracture and occur again and again.And shop personnel are only capable of at present by visual Change and check crackle, detection heavy workload, low efficiency, time-consuming.Therefore, there is an urgent need to a kind of effective automatic checkout systems can Steel beam surface is accurately detected.
Summary of the invention
In view of the above-mentioned problems, the present invention provides a kind of girder steel flaw detection system
The purpose of the present invention is realized using following technical scheme:
A kind of girder steel flaw detection system, the girder steel flaw detection system include girder steel image capture module, girder steel image Processing module, girder steel crack extraction module and girder steel crack identification module.Girder steel image capture module, for acquiring The original image of girder steel to be detected;Girder steel image processing module, for being denoised to the original image of acquisition, edge detection and Enhancing processing, obtains the target image of girder steel to be detected;Girder steel extracting thermal crack module, it is to be detected for being extracted from target image The characteristic of girder steel;Girder steel crack identification module, for will be prestored in the characteristic of girder steel to be detected and database The characteristic of the girder steel of the flawless of storage is matched, and judges girder steel to be detected with the presence or absence of crackle.
Beneficial effects of the present invention are:The present invention can quickly and accurately extract the characteristic of girder steel to be detected, and know Not Chu girder steel to be detected with the presence or absence of crackle in favor of rapidly and accurately being excluded to failure improve the economic benefit of factory And the personal safety of safeguard work personnel.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings Other attached drawings.
Fig. 1 is the structure chart of girder steel flaw detection system;
Fig. 2 is the frame construction drawing of girder steel image processing module.
Appended drawing reference:Girder steel image capture module 1;Girder steel image processing module 2;Girder steel crack extraction module 3;Steel Beam crack identification module 4;Warning module 5;Denoise unit 6;Edge detection unit 7;Enhancement unit 8.
Specific embodiment
The invention will be further described with the following Examples.
Referring to Fig. 1, a kind of girder steel flaw detection system, the girder steel flaw detection system include girder steel image capture module 1, Girder steel image processing module 2, girder steel crack extraction module 3 and girder steel crack identification module 4.Girder steel Image Acquisition mould Block 1, for acquiring the original image of girder steel to be detected;Girder steel image processing module 2, for being gone to the original image of acquisition It makes an uproar, edge detection and enhancing processing, obtains the target image of girder steel to be detected;Girder steel extracting thermal crack module 3 is used for from target figure The characteristic of girder steel to be detected is extracted as in;Girder steel crack identification module 4, for by the characteristic of girder steel to be detected It is matched with the characteristic of the girder steel for the flawless being pre-stored in database, judges girder steel to be detected with the presence or absence of crackle.
Beneficial effect:The present invention can quickly and accurately extract the characteristic of girder steel to be detected, and identify to be detected Girder steel whether there is crackle, in favor of rapidly and accurately being excluded to failure, improve the economic benefit and safeguard work of factory The personal safety of personnel.
Preferably, which further includes warning module 5, and warning module 5 and girder steel crack identify Module 4 is connected, for show girder steel to be detected there are when crackle, by warning module 5 to service personnel's sending when matching result Warning information.
Preferably, girder steel image capture module 1 is industrial camera.
Preferably, referring to fig. 2, girder steel image processing module 2 includes denoising unit 6, edge detection unit 7 and enhancement unit 8.Denoising unit 6 is used to remove the random noise in the original image;Edge detection unit 7 is used for the original graph after denoising As carrying out edge detection, the benchmark image of girder steel to be detected is obtained;Enhancement unit 8 is used to carry out enhancing processing to benchmark image, Obtain the target image of girder steel to be detected.
Preferably, the random noise in the removal original image, specifically:The original image is carried out at gray processing Reason, and successively the original image after gray processing is denoised point by point, obtain the denoising of each pixel in the original image Estimated value, and using denoising estimated value as new gray value, the set that all pixels point is constituted at this time is original after denoising Image;Wherein, the denoising estimated value of pixel p (i, j) is calculated using following formula in the original image:
In formula,For the denoising estimated value of pixel p (i, j), be pixel p denoising after gray value, i, j points Not Wei pixel p abscissa and ordinate, Z is regularization parameter, W be centered on pixel p (i, j), size be M × M Search window, q is any pixel point in search window,Europe is weighted for the Gauss of pixel p and pixel q Formula distance, α are the standard deviation of Gaussian function, and h is smoothing parameter, and G (q) is the gray value of pixel q, and G (p) is pixel p's Gray value,For the average gray value of all pixels point in search window.
Beneficial effect:The denoising estimated value of each pixel in above-mentioned solution original image, the solution procedure are mainly benefit It is denoised with the redundancy in original image, by searching for pixel similar with target pixel points in a search window Point, and then replace with the gray value of these similar pixel points the gray value of current pixel point.The denoising method is simple, denoising is fast Degree is fast, not only allow for the Gauss weighted euclidean distance information between pixel, it is also contemplated that residual pixel point in search window It is improved with the relationship of target pixel points gray value to farthest remain the edge and minutia of original image Effect is denoised, while being also beneficial to accurate detection of the subsequent acquisition to girder steel to be detected, improves detection accuracy.
Preferably, the original image after described pair of denoising carries out edge detection, obtains the benchmark image of girder steel to be detected, has Body is:
(1) taking the central pixel point in the sliding window that size is 3 × 3 is edge measuring point to be checked, according to lateral inspection It surveys direction and 3 × 3 sliding window is divided into three regions:L, M, R, wherein L is located on the left of sliding window, M is located at sliding window Mouth is intermediate, R is located on the right side of sliding window, judges whether edge measuring point to be checked is marginal point using edge discrimination formula, wherein institute Stating edge discrimination formula is:
In formula, H (x) is the characteristic value of edge measuring point x to be checked, GLIt (i) is the gray value of ith pixel point in the L of region, GM It (i) is the gray value of ith pixel point in the M of region, GRIt (i) is the gray value of ith pixel point in the R of region, and i=1,2,3; G (x) is the gray value of edge measuring point x to be checked;
As H (x) >=T, then edge measuring point x to be checked is marginal point, conversely, edge measuring point x to be checked is not marginal point, In, T is the threshold value of setting;
(2) all pixels point in the original image after traversal denoising, and using the method that non-extreme value inhibits to obtained side Edge point carries out edge positioning, and the set of the final marginal point of girder steel to be detected can be obtained;
(3) original image after denoising is split according to the set for the final marginal point for obtaining girder steel to be detected, i.e., The benchmark image of girder steel to be detected can be obtained.
Beneficial effect:By setting a sliding window, judge whether the central pixel point in sliding window is to be detected The marginal point of girder steel, and all pixels point in the original image after denoising is successively traversed using sliding window, which can be certainly It whether is adaptively that marginal point differentiates to each pixel, not only details is special in retaining girder steel image border point to be detected While sign, it is also able to detect that clearly marginal information, while in order to further increase edge detection precision, utilizing non-extreme value The method of inhibition repositions the marginal point detected, can further remove non-edge point, so that extract It is edge clear, complete, accurate, it is more advantageous to the accurate segmentation to girder steel image to be detected, obtains the reference map of girder steel to be detected Picture, convenient for subsequent extraction and identification to steel beam surface feature to be detected.
Preferably, described that enhancing processing is carried out to benchmark image, the target image of girder steel to be detected is obtained, is specifically utilized Enhance formula and calculates all pixels point enhancing in the benchmark image treated gray value, the enhancing treated pixel The set of composition is the target image of girder steel to be detected, wherein the enhancing formula is:
In formula, Ge(x, y) is the gray value of enhanced pixel r (x, y), and G (x, y) is pixel in the benchmark image The gray value of point r (x, y), κ (x, y) are about control coefrficient of the pixel r (x, y) along gradient direction, μ in the benchmark image For the constant greater than 0,For the second-order partial differential coefficient at pixel r (x, y) along gradient direction n,For pixel Along the second-order partial differential coefficient of the tangential direction s orthogonal with gradient direction at point r (x, y);
Wherein, pass through about pixel r (x, y) in the benchmark image along the control coefrficient κ (x, y) of gradient direction following Mode obtain:
(1) local variance in the benchmark image at each pixel in 3 × 3 neighborhoods is calculated using following formula, wherein closing It is in the formula of the local variance of pixel r (x, y):
In formula, χ2(x, y) is the local variance of pixel r (x, y), and G (x+s, y+t) is the picture that coordinate is (x+s, y+t) The gray value of vegetarian refreshments,For the gray value mean value of all pixels point in neighborhood;
(2) using normalization formula to obtained local variance χ2(x, y) is normalized, its local variance is returned One changes into the region of 0-255, wherein normalization formula is:
In formula,For the local variance after the normalization of pixel r (x, y), Max χ2With Min χ2It is respectively described The maximum value and minimum value of benchmark image local variance;
(3) according to obtained normalized value, pixel r (x, y) is calculated along the control coefrficient of gradient direction using following formula;
In formula, κ (x, y) is control coefrficient of the pixel r (x, y) along gradient direction,For the variance threshold values of setting.
Beneficial effect:Enhancing processing is carried out to the benchmark image using above-mentioned algorithm, the algorithm is in enhancing benchmark image It while minutia, avoids edge and overshoot phenomenon occurs, while also restrained effectively residual in the benchmark image Remaining noise enables enhanced benchmark image to highlight the surface details feature of girder steel to be detected, to be checked convenient for subsequent extracted The surface characteristics parameter for surveying girder steel improves girder steel table to be detected in favor of accurately identifying to steel beam surface defect to be detected The accuracy rate of planar defect detection.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered Work as understanding, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention Matter and range.

Claims (5)

1. a kind of girder steel flaw detection system, characterized in that the girder steel flaw detection system include girder steel image capture module, Girder steel image processing module, girder steel crack extraction module and girder steel crack identification module;
The girder steel image capture module, for acquiring the original image of girder steel to be detected;
The girder steel image processing module, for being denoised to the original image of acquisition, edge detection and enhancing processing, obtain The target image of girder steel to be detected;
The girder steel extracting thermal crack module, for extracting the characteristic of girder steel to be detected from the target image;
The girder steel crack identification module, for splitting the nothing being pre-stored in the characteristic of girder steel to be detected and database The characteristic of the girder steel of line is matched, and judges girder steel to be detected with the presence or absence of crackle.
2. girder steel flaw detection system according to claim 1, characterized in that it further include warning module, the early warning mould Block is connected with the girder steel crack identification module, for showing that girder steel to be detected there are when crackle, passes through when matching result The warning module issues warning information to service personnel.
3. girder steel flaw detection system according to claim 1, characterized in that the girder steel image capture module is industry Camera.
4. girder steel flaw detection system according to claim 3, characterized in that the girder steel image processing module includes going It makes an uproar unit, edge detection unit and enhancement unit;
The denoising unit, for removing the random noise in the original image;
The edge detection unit obtains the benchmark of girder steel to be detected for carrying out edge detection to the original image after denoising Image;
The enhancement unit obtains the target image of girder steel to be detected for carrying out enhancing processing to the benchmark image.
5. girder steel flaw detection system according to claim 4, characterized in that making an uproar in the removal original image at random Sound, specifically:Gray processing processing is carried out to the original image, and successively the original image after gray processing is gone point by point It makes an uproar, obtains the denoising estimated value of each pixel in the original image, and using denoising estimated value as new gray value, at this time The set that all pixels point is constituted is the original image after denoising;Wherein, pixel p (i, j) is gone in the original image Estimated value of making an uproar is calculated using following formula:
In formula,For the denoising estimated value of pixel p (i, j), i, j are respectively the abscissa and ordinate of pixel p, and Z is Regularization parameter, W are centered on pixel p (i, j), the search window that size is M × M, and q is any pixel point in search window,For the Gauss weighted euclidean distance of pixel p and pixel q, α is the standard deviation of Gaussian function, and h is flat Sliding parameter, G (q) are the gray value of pixel q, and G (p) is the gray value of pixel p,For in search window all pixels point it is flat Equal gray value.
CN201810882961.8A 2018-08-06 2018-08-06 A kind of girder steel flaw detection system Pending CN108872252A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810882961.8A CN108872252A (en) 2018-08-06 2018-08-06 A kind of girder steel flaw detection system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810882961.8A CN108872252A (en) 2018-08-06 2018-08-06 A kind of girder steel flaw detection system

Publications (1)

Publication Number Publication Date
CN108872252A true CN108872252A (en) 2018-11-23

Family

ID=64307944

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810882961.8A Pending CN108872252A (en) 2018-08-06 2018-08-06 A kind of girder steel flaw detection system

Country Status (1)

Country Link
CN (1) CN108872252A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110517245A (en) * 2019-08-20 2019-11-29 北京远舢智能科技有限公司 A kind of mechanical fault diagnosis system
CN111721361A (en) * 2020-06-29 2020-09-29 杭州鲁尔物联科技有限公司 Embankment monitoring system, method and equipment
CN116894832A (en) * 2023-07-27 2023-10-17 山东明佳科技有限公司 Method, system, equipment and storage medium for detecting bottleneck cracks of milk glass bottle

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105510344A (en) * 2015-11-24 2016-04-20 昆明理工大学 A method of detecting newly increased cracks of power transmission towers in an area
CN106600567A (en) * 2017-01-03 2017-04-26 长沙全度影像科技有限公司 Adaptive non-local mean denoising method
CN107515228A (en) * 2016-06-16 2017-12-26 许斌 A kind of carpet flaw detection system
CN107862687A (en) * 2017-11-07 2018-03-30 潘柏霖 A kind of early warning system for being used to monitor agricultural pest

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105510344A (en) * 2015-11-24 2016-04-20 昆明理工大学 A method of detecting newly increased cracks of power transmission towers in an area
CN107515228A (en) * 2016-06-16 2017-12-26 许斌 A kind of carpet flaw detection system
CN106600567A (en) * 2017-01-03 2017-04-26 长沙全度影像科技有限公司 Adaptive non-local mean denoising method
CN107862687A (en) * 2017-11-07 2018-03-30 潘柏霖 A kind of early warning system for being used to monitor agricultural pest

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
陈燕: ""工业X射线图像增强算法研究"", 《中国博士学位论文全文数据库》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110517245A (en) * 2019-08-20 2019-11-29 北京远舢智能科技有限公司 A kind of mechanical fault diagnosis system
CN110517245B (en) * 2019-08-20 2021-09-07 北京远舢智能科技有限公司 Mechanical equipment fault diagnosis system
CN111721361A (en) * 2020-06-29 2020-09-29 杭州鲁尔物联科技有限公司 Embankment monitoring system, method and equipment
CN116894832A (en) * 2023-07-27 2023-10-17 山东明佳科技有限公司 Method, system, equipment and storage medium for detecting bottleneck cracks of milk glass bottle
CN116894832B (en) * 2023-07-27 2024-01-26 山东明佳科技有限公司 Method, system, equipment and storage medium for detecting bottleneck cracks of milk glass bottle

Similar Documents

Publication Publication Date Title
CN116721106B (en) Profile flaw visual detection method based on image processing
CN109141232B (en) Online detection method for disc castings based on machine vision
CN109490316B (en) Surface defect detection algorithm based on machine vision
CN105405142B (en) A kind of the side defect inspection method and system of glass panel
JP6658711B2 (en) Surface defect detection method and surface defect detection device
CN107255641A (en) A kind of method that Machine Vision Detection is carried out for GRIN Lens surface defect
CN108872252A (en) A kind of girder steel flaw detection system
CN110827235B (en) Steel plate surface defect detection method
CN109816645B (en) Automatic detection method for steel coil loosening
WO2015066984A1 (en) Complex background-oriented optical character recognition method and device
CN112258444A (en) Elevator steel wire rope detection method
CN115861274A (en) Crack detection method integrating three-dimensional point cloud and two-dimensional image
CN113155839A (en) Steel plate outer surface defect online detection method based on machine vision
CN110009633A (en) A kind of detection method of surface flaw of steel rail based on reversed difference of Gaussian
CN116228651A (en) Cloth defect detection method, system, equipment and medium
CN115953373A (en) Glass defect detection method and device, electronic equipment and storage medium
Tang et al. Surface inspection system of steel strip based on machine vision
Kumar et al. A survey on crack detection technique in railway track
Dang et al. A novel method for detecting weld defects accurately and reliably in radiographic images
CN109146863A (en) A kind of pavement marker line defect detection device
CN113298775A (en) Self-priming pump double-sided metal impeller appearance defect detection method, system and medium
CN113240629B (en) Edge-based image matching narrow-gap weld initial point positioning device and method
Zhou et al. Automated detection of surface defects on sphere parts using laser and CDD measurements
CN111882537B (en) Visual detection method and system
CN109886912A (en) A kind of thrust bearing retainer detection method of surface flaw

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20181123

RJ01 Rejection of invention patent application after publication