CN107403427A - A kind of concrete surface crack detection method based on genetic planning and flow model in porous media - Google Patents
A kind of concrete surface crack detection method based on genetic planning and flow model in porous media Download PDFInfo
- Publication number
- CN107403427A CN107403427A CN201710593926.XA CN201710593926A CN107403427A CN 107403427 A CN107403427 A CN 107403427A CN 201710593926 A CN201710593926 A CN 201710593926A CN 107403427 A CN107403427 A CN 107403427A
- Authority
- CN
- China
- Prior art keywords
- crack
- image
- detection method
- concrete surface
- porous media
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of concrete surface crack detection method based on genetic planning and flow model in porous media, what is solved is to survey the technical problem that precision is low, efficiency is low, by using to original image optimum image processing model is trained using improved genetic programming method, original image is pre-processed based on optimum image processing model, spotted noise is removed and obtains pretreatment image；In pretreatment image, crack skeleton is extracted using parallel framework extraction method, obtains crack skeleton terminal node, crack skeleton terminal node is added into end point set Pend；Detected using seepage flow detection method, result is set to preextraction image for the region in crack；The crack of the fracture in preextraction image is attached using the crack connection method extended based on region, after carrying out denoising, the technical scheme in the true crack that result is coagulation figure surface image is obtained, preferably resolves the problem, in being detected available for concrete surface crack.
Description
Technical field
The present invention relates to concrete surface crack identification technology field, and in particular to one kind is based on genetic planning and seepage flow mould
The concrete surface crack detection method of type.
Background technology
Concrete surface crack is the main performance shape of the infrastructure architecture venereal disease evil such as building, bridge, tunnel, road surface
Formula, with the natural hazard such as interaction such as percolating water, lining cutting regionality deterioration, vicious circle is formed, reduces above capital construction facility
Security, stability, the reliability of structure, cause potential safety hazard, or even jeopardize the personal safety of people.In order to evaluate these bases
Build and apply the stability after there is structural harm, grasp the ill form and its cracking degree in crack, it is necessary to these capital construction
The concrete surface crack of facility is detected, based on facility structure security evaluation and disease management provide foundation.
Existing concrete surface crack detection method is using the crack based on genetic programming algorithm or based on flow model in porous media
Detection method.Have the following disadvantages：Carry out image filter known to tissue training using genetic programming algorithm, carry out crack inspection
Survey, there is the advantages of automatic detection, efficiency high, but partial fracture fracture be present, it is not high to fine cracks accuracy of detection.It is based on
The Crack Detection algorithm of flow model in porous media, seepage flow detection can be carried out to the local detail of significantly image, also can detect fine cracks, it is accurate
True rate is high, but algorithm carries out seepage flow processing to each seepage flow pixel in image, excessive redundant computation be present.Therefore it provides one
Kind accuracy of detection is high, the concrete surface crack detection method of efficiency high is with regard to necessary.
The content of the invention
The technical problems to be solved by the invention are that the technology that accuracy of detection present in prior art is low, efficiency is low is asked
Topic.A kind of new concrete surface crack detection method is provided, the concrete surface crack detection method have accuracy of detection it is high,
The characteristics of efficiency high.
In order to solve the above technical problems, the technical scheme used is as follows：
A kind of concrete surface crack detection method based on genetic planning and flow model in porous media, methods described include：
(1) it is original image to gather concrete surface image, is trained using improved genetic programming method at optimum image
Model is managed, original image is pre-processed based on optimum image processing model, while removes spotted noise, obtains pretreatment figure
Picture；
(2) in pretreatment image, crack skeleton is extracted using parallel framework extraction method, obtains crack skeleton terminal section
Point, crack skeleton terminal node is added into end point set Pend；
(3) detected using seepage flow detection method, result is set to preextraction image for the region in crack；
(4) crack of the fracture in preextraction image is attached using the crack connection method extended based on region,
After carrying out denoising, the true crack that result is coagulation figure surface image is obtained.
The operation principle of the present invention：The present invention is detected first by the thought based on genetic programming algorithm with conventional edge
Algorithm and connected region partitioning algorithm etc. are used as image processing model node, and choosing several has the concrete of different FRACTURE CHARACTERISTICSs
Surface image is gone out optimal Crack Detection model using improved genetic programming Algorithm for Training, then examined using crack as training set
Survey model inspection and go out image entirety crack framework, afterwards using seepage flow algorithm on the basis of previous step testing result, to tiny
Crack is accurately detected, and error detection is removed with length characteristic finally by the round degree of characteristics of connected region in testing result is calculated
Region, obtain the true crack of concrete surface.Concrete surface crack can accurately and fast be detected, can effectively be excluded
A variety of disturbing factors such as stain, chip off-falling, percolating water, there is good robustness.
In such scheme, for optimization, further, the use seepage flow detection method, which carries out detection, to be included：
(a) end point set P is takenendIn a little be anchor point, detected using seepage flow detection method fracture fine cracks；
(b) (a) is repeated by end point set PendIn all end points obtain smart detection image.
Further, the improved genetic programming method is including the use of improvement selection opertor.
Further, the improvement selection opertor is based on fitness and node scale bilayer contest selection opertor.
Further, being set forth in fitness and node scale bilayer contest selection opertor includes：
(A) select one in fitness priority principle or node scale priority principle and be selected as the first priority, it is non-selected
Principle as the second priority；
(B) parameter M control selections probability is used inside operator, fitness or node scale are the probability that selection opertor relies on
For M/2；
(C) as M=M1, fitness or node scale is randomly choosed and is relied on for selection opertor；As M=M2, select simultaneously
Selecting fitness and node scale, alternatively operator relies on.
Further, it is described to extract preextraction crack skeleton also including combining the 8 of optimization using parallel framework extraction method
Neighborhood directional chain-code, which scans, to carry out single processes pixel with following principle and eliminates burr.
Beneficial effects of the present invention：
Effect one, testing accuracy is high, efficiency high；
Effect two, it can effectively exclude a variety of disturbing factors such as stain, chip off-falling, percolating water；
Effect three, there is stronger robustness.
Brief description of the drawings
The present invention is further described with reference to the accompanying drawings and examples.
Fig. 1, the concrete surface crack detection method schematic diagram based on genetic planning and flow model in porous media.
Fig. 2, original image schematic diagram.
Fig. 3, use the processing result image schematic diagram of artificial extraction process.
Fig. 4, use genetic programming algorithm image processing model result schematic diagram.
Fig. 5, use method of seepage image processing model result schematic diagram.
Fig. 6, use the concrete surface crack detection method image processing model knot based on genetic planning and flow model in porous media
Fruit schematic diagram.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that specific embodiment described herein is not used to limit only to explain the present invention
The fixed present invention.
Embodiment 1
The present embodiment provides a kind of concrete surface crack detection method based on genetic planning and flow model in porous media, the side
Method includes：
(1) it is original image to gather concrete surface image, is trained using improved genetic programming method at optimum image
Model is managed, original image is pre-processed based on optimum image processing model, while removes spotted noise, obtains pretreatment figure
Picture；
(2) in pretreatment image, crack skeleton is extracted using parallel framework extraction method, obtains crack skeleton terminal section
Point, crack skeleton terminal node is added into end point set Pend；
(3) detected using seepage flow detection method, result is set to preextraction image for the region in crack；
(4) crack of the fracture in preextraction image is attached using the crack connection method extended based on region,
After carrying out denoising, the true crack that result is coagulation figure surface image is obtained.
The workflow of the present embodiment：First by improved genetic programming algorithm, with existing edge detection algorithm and company
Logical region partitioning algorithm etc. is used as image processing model node, and choosing several has the concrete surface image of different FRACTURE CHARACTERISTICSs
As training set, go out optimal Crack Detection model using improved genetic programming Algorithm for Training, then examined using Crack Detection model
Image entirety crack framework is measured, afterwards using seepage flow algorithm on the basis of previous step testing result, fine cracks are carried out
Accurate detection, error detection region is removed with length characteristic finally by the round degree of characteristics of connected region in testing result is calculated, is obtained
To the true crack of concrete surface.
Specifically, carrying out detection using seepage flow detection method includes：
(a) end point set P is takenendIn a little be anchor point, detected using seepage flow detection method fracture fine cracks；
(b) (a) is repeated by end point set PendIn all end points obtain smart detection image.
Specifically, it is described using improved genetic programming method train optimum image processing model in improvement mainly pair
The improvement of selection opertor, including using improvement selection opertor.
Specifically, it is based on fitness and node scale bilayer contest selection opertor to improve selection opertor.
Specifically, the process based on fitness and node scale bilayer contest selection opertor includes：
(A) select one in fitness priority principle or node scale priority principle and be selected as the first priority, it is non-selected
Principle as the second priority；
(B) parameter M control selections probability is used inside operator, fitness or node scale are the probability that selection opertor relies on
For M/2；
(C) as M=M1, fitness or node scale is randomly choosed and is relied on for selection opertor；As M=M2, select simultaneously
Selecting fitness and node scale, alternatively operator relies on.
Wherein, M1=1, M2=2.
To improve accuracy of detection, it is preferable that described also to be wrapped using parallel framework extraction method extraction preextraction crack skeleton
The 8 neighborhood directional chain-codes scanning included with reference to optimization carries out single processes pixel with following principle and eliminates burr.
If Fig. 2 is crack state, respectively Image1-Image 8 in original image, including 8.Fig. 3, use artificial extraction
The processing result image schematic diagram of processing.Fig. 4, the genetic programming algorithm image processing model result schematic diagram used.Fig. 5, make
With method of seepage image processing model result schematic diagram.Fig. 6, split using the concrete surface based on genetic planning and flow model in porous media
Stitch detection method image processing model result schematic diagram.
Table 1
Fig. 4 is analyzed, as a result as shown in table 1, the image detection model trained using genetic programming algorithm is had
Higher accuracy of detection, there is preferable Detection results to most of image, but edge of crack is fuzzy, noise rate is compared with hi-vision
Accuracy of detection is poor, and the robustness of algorithm is not strong, while institute's testing result has fracture.
| Image | P | R | NR | F1 | FPR |
| Fig8p1 | 68.42% | 65.78% | 31.58% | 67.07% | 0.046% |
| Fig8p2 | 78.45% | 66.16% | 21.55% | 71.78% | 0.200% |
| Fig8p3 | 84.37% | 84.22% | 15.63% | 84.30% | 0.620% |
| Fig8p4 | 76.04% | 63.73% | 23.96% | 69.34% | 1.190% |
| Fig8p5 | 75.24% | 78.14% | 24.76% | 76.66% | 0.780% |
| Fig8p6 | 65.64% | 90.34% | 34.36% | 76.03% | 1.060% |
| Fig8p7 | 79.49% | 75.20% | 20.91% | 77.29% | 0.220% |
| Fig8p8 | 86.53% | 68.20% | 13.47% | 76.28% | 0.230% |
Table 2
Fig. 5 is analyzed, as a result as shown in table 2, in the Crack Detection algorithm of flow model in porous media, whole detection precision is more
It is stable, there is higher robustness, crack fracture is less, but does not consider edge of crack information better than algorithm, is examined at fracture edge
Survey effect is poor, and testing result has part burr.
| Image | P | R | NR | F1 | FPR |
| Fig12s1 | 99.72% | 95.31% | 0.280% | 97.47% | 0.004% |
| Fig12s2 | 99.05% | 94.62% | 0.950% | 96.78% | 0.009% |
| Fig12s3 | 99.91% | 97.62% | 0.040% | 98.80% | 0.002% |
| Fig12s4 | 91.96% | 80.41% | 8.040% | 85.80% | 0.400% |
| Fig12s5 | 99.62% | 96.76% | 0.380% | 98.17% | 0.011% |
| Fig12s6 | 98.72% | 98.32% | 1.280% | 98.52% | 0.039% |
| Fig12s7 | 99.75% | 98.40% | 0.250% | 99.07% | 0.003% |
| Fig12s8 | 99.56% | 99.20% | 0.440% | 99.38% | 0.007% |
Table 3
Fig. 4 is analyzed, as a result as shown in table 3, the detection algorithm based on genetic planning and flow model in porous media, effective integration
The advantages of two kinds of algorithms, the treatment effeciency of genetic planning image processing model is combined, obtain preferable edge of crack, simultaneously
It compensate for algorithm extraction result and the shortcomings that fracture be present, there is higher robustness.
As a result show, the crack algorithm based on the pre- flow model in porous media of genetic planning that the present embodiment proposes, integrate genetic planning
The advantages of accuracy of detection of the detection efficiency of algorithm and crack extract algorithm based on flow model in porous media, can accurately and fast it examine
Concrete surface crack is measured, can effectively exclude a variety of disturbing factors such as stain, chip off-falling, percolating water, there is stronger robust
Property.
Although the illustrative embodiment of the present invention is described above, in order to the technology of the art
Personnel are it will be appreciated that the present invention, but the present invention is not limited only to the scope of embodiment, to the common skill of the art
For art personnel, as long as long as various change in the spirit and scope of the invention that appended claim limits and determines, one
The innovation and creation using present inventive concept are cut in the row of protection.
Claims (6)
- A kind of 1. concrete surface crack detection method based on genetic planning and flow model in porous media, it is characterised in that：Methods described Including：(1) it is original image to gather concrete surface image, and optimum image processing mould is trained using improved genetic programming method Type, original image is pre-processed based on optimum image processing model, while remove spotted noise, obtain pretreatment image；(2) in pretreatment image, crack skeleton is extracted using parallel framework extraction method, obtains crack skeleton terminal node, will Crack skeleton terminal node adds end point set Pend；(3) detected using seepage flow detection method, result is set to preextraction image for the region in crack；(4) crack of the fracture in preextraction image is attached using the crack connection method extended based on region, carried out After denoising, the true crack that result is coagulation figure surface image is obtained.
- 2. the concrete surface crack detection method according to claim 1 based on genetic planning and flow model in porous media, it is special Sign is：The use seepage flow detection method, which carries out detection, to be included：(a) end point set P is takenendIn a little be anchor point, detected using seepage flow detection method fracture fine cracks；(b) (a) is repeated by end point set PendIn all end points obtain smart detection image.
- 3. the concrete surface crack detection method according to claim 1 based on genetic planning and flow model in porous media, it is special Sign is：The improved genetic programming method is including the use of improvement selection opertor.
- 4. the concrete surface crack detection method according to claim 3 based on genetic planning and flow model in porous media, it is special Sign is：The improvement selection opertor is to be based on fitness and node scale bilayer contest selection opertor.
- 5. the concrete surface crack detection method according to claim 4 based on genetic planning and flow model in porous media, it is special Sign is：It is described to be included based on fitness and node scale bilayer contest selection opertor：(A) select one in fitness priority principle or node scale priority principle and be selected as the first priority, non-selected original Then it is used as the second priority；(B) parameter M control selections probability is used inside selection opertor；(C) as M=M1, fitness or node scale is randomly choosed and is relied on for selection opertor；As M=M2, simultaneous selection is fitted Alternatively operator relies on for response and node scale.
- 6. the concrete surface crack detection method according to claim 1 based on genetic planning and flow model in porous media, it is special Sign is：It is described to extract the preextraction crack skeleton also 8 neighborhood direction chains including combining optimization using parallel framework extraction method Code scanning carries out single processes pixel with following principle, and eliminates burr.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710593926.XA CN107403427A (en) | 2017-07-20 | 2017-07-20 | A kind of concrete surface crack detection method based on genetic planning and flow model in porous media |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710593926.XA CN107403427A (en) | 2017-07-20 | 2017-07-20 | A kind of concrete surface crack detection method based on genetic planning and flow model in porous media |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107403427A true CN107403427A (en) | 2017-11-28 |
Family
ID=60402152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710593926.XA Pending CN107403427A (en) | 2017-07-20 | 2017-07-20 | A kind of concrete surface crack detection method based on genetic planning and flow model in porous media |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107403427A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108898080A (en) * | 2018-06-19 | 2018-11-27 | 广西大学 | A kind of crack connection method based on ridge line neighborhood evaluation model |
| CN110111321A (en) * | 2019-05-10 | 2019-08-09 | 四川大学 | A kind of contactless multiple dimensioned method for crack |
| CN111325219A (en) * | 2020-02-06 | 2020-06-23 | 哈尔滨工业大学 | Concrete bridge crack rapid identification method based on optimized penetration theory |
| CN112083253A (en) * | 2020-09-18 | 2020-12-15 | 西南交通大学 | Soil electrical parameter state inversion method under direct current |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400139A (en) * | 2013-07-04 | 2013-11-20 | 中南大学 | Method for identifying concrete crack characteristic information |
| CN103839268A (en) * | 2014-03-18 | 2014-06-04 | 北京交通大学 | Method for detecting fissure on surface of subway tunnel |
| CN103942571A (en) * | 2014-03-04 | 2014-07-23 | 西安电子科技大学 | Graphic image sorting method based on genetic programming algorithm |
| CN104730596A (en) * | 2015-01-25 | 2015-06-24 | 中国石油大学(华东) | Discrete fracture modeling method based on multiscale factor restraint |
| CN104792792A (en) * | 2015-04-27 | 2015-07-22 | 武汉武大卓越科技有限责任公司 | Stepwise-refinement pavement crack detection method |
| CN105719259A (en) * | 2016-02-19 | 2016-06-29 | 上海理工大学 | Pavement crack image detection method |
-
2017
- 2017-07-20 CN CN201710593926.XA patent/CN107403427A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400139A (en) * | 2013-07-04 | 2013-11-20 | 中南大学 | Method for identifying concrete crack characteristic information |
| CN103942571A (en) * | 2014-03-04 | 2014-07-23 | 西安电子科技大学 | Graphic image sorting method based on genetic programming algorithm |
| CN103839268A (en) * | 2014-03-18 | 2014-06-04 | 北京交通大学 | Method for detecting fissure on surface of subway tunnel |
| CN104730596A (en) * | 2015-01-25 | 2015-06-24 | 中国石油大学(华东) | Discrete fracture modeling method based on multiscale factor restraint |
| CN104792792A (en) * | 2015-04-27 | 2015-07-22 | 武汉武大卓越科技有限责任公司 | Stepwise-refinement pavement crack detection method |
| CN105719259A (en) * | 2016-02-19 | 2016-06-29 | 上海理工大学 | Pavement crack image detection method |
Non-Patent Citations (3)
| Title |
|---|
| TAKAFUMI NISHIKAWA: "Concrete Crack Detection by Multiple Sequential Image Filtering", 《COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING》 * |
| 孟庆春 等: "《基于对偶理论的调控机制研究》", 30 September 2006, 山东大学出版社 * |
| 郭阳: "改进渗流模型的混凝土路面图像裂缝检测算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108898080A (en) * | 2018-06-19 | 2018-11-27 | 广西大学 | A kind of crack connection method based on ridge line neighborhood evaluation model |
| CN108898080B (en) * | 2018-06-19 | 2022-03-11 | 广西大学 | Ridge line neighborhood evaluation model-based crack connection method |
| CN110111321A (en) * | 2019-05-10 | 2019-08-09 | 四川大学 | A kind of contactless multiple dimensioned method for crack |
| CN111325219A (en) * | 2020-02-06 | 2020-06-23 | 哈尔滨工业大学 | Concrete bridge crack rapid identification method based on optimized penetration theory |
| CN112083253A (en) * | 2020-09-18 | 2020-12-15 | 西南交通大学 | Soil electrical parameter state inversion method under direct current |
| CN112083253B (en) * | 2020-09-18 | 2021-07-02 | 西南交通大学 | Soil electrical parameter state inversion method under direct current |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107403427A (en) | A kind of concrete surface crack detection method based on genetic planning and flow model in porous media | |
| Zhou et al. | Building detection in Digital surface model | |
| US9147014B2 (en) | System and method for image selection of bundled objects | |
| CN108776772A (en) | Across the time building variation detection modeling method of one kind and detection device, method and storage medium | |
| CN105719259A (en) | Pavement crack image detection method | |
| CN108021933A (en) | Neural network recognization model and recognition methods | |
| CN103839268A (en) | Method for detecting fissure on surface of subway tunnel | |
| CN109886939A (en) | Bridge Crack detection method based on Tensor Voting | |
| CN103605981A (en) | Insulator defect identification method based on image identification | |
| CN109063713A (en) | A kind of timber discrimination method and system based on the study of construction feature picture depth | |
| CN105184225B (en) | A kind of multinational banknote image recognition methods and device | |
| CN105092597B (en) | A kind of crack detecting method on hard plastic material surface | |
| CN106934829A (en) | The detection method and system of a kind of surface crack | |
| CN110232682B (en) | Image-based track foreign matter detection method | |
| CN103996023A (en) | Light field face recognition method based on depth belief network | |
| CN106023226A (en) | Crack automatic detection method based on three-dimensional virtual pavement | |
| CN113096121A (en) | Pavement crack detection method and system based on cross fracture mechanics and image processing | |
| CN109766892A (en) | A kind of ray detection image tagged information character dividing method based on edge detection | |
| CN114841927A (en) | Shale reservoir fracture identification method, device, equipment and storage medium | |
| CN106683098A (en) | Segmentation method of overlapping leaf images | |
| CN103325123A (en) | Image edge detection method based on self-adaptive neural fuzzy inference systems | |
| CN106153507B (en) | A kind of method of mini-frac proppant sphericity | |
| Fakhri et al. | Road crack detection using gaussian/prewitt filter | |
| CN107144572A (en) | Crack automatic recognition and detection method in gray level image | |
| CN104359918A (en) | Method for detecting surface defects of speaker cone |
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: 20171128 |
|
| RJ01 | Rejection of invention patent application after publication |