CN106203351A - The method of crack Intelligent Recognition classification - Google Patents
The method of crack Intelligent Recognition classification Download PDFInfo
- Publication number
- CN106203351A CN106203351A CN201610551362.9A CN201610551362A CN106203351A CN 106203351 A CN106203351 A CN 106203351A CN 201610551362 A CN201610551362 A CN 201610551362A CN 106203351 A CN106203351 A CN 106203351A
- Authority
- CN
- China
- Prior art keywords
- crack
- image
- template
- rectangular histogram
- peak
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/758—Involving statistics of pixels or of feature values, e.g. histogram matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The method that the invention discloses the classification of a kind of crack Intelligent Recognition, automatically obtains crack first with image analysis method, as projected image and peak detection isolates crack area；Then the feature in crack is extracted；As utilized vertical, floor projection and normalization process to generate crack template；Finally, judgement crack kind is compared with known data base；As mated by the high speed of the known standard form with crack template base, automatically identify the kind in crack.Present invention could apply to quickly judge Cracks character.
Description
Technical field
The present invention relates to technical field of image processing, the automated intelligent in particular to a kind of wall body slit figure is known
Other sorting technique.
Background technology
Building is after building up and coming into operation, and due to various artificial or natural cause, can produce substantial amounts of on surface
Crack, particularly now a large amount of subways and the excavation of deep basal pit, cause large area house vibrations around to produce crack, meanwhile
Along with the raising of people's living standard, the requirement to quality of life also can improve accordingly, and whether user can worry these cracks
The safety in house can be produced impact, so these cracks to be identified the demand with detection also can increase, if can not be to this
A little houses are investigated timely and effectively and identify, resident may be caused to be discontented with government department, and it is unnecessary even to cause
Dispute.But there is complex procedures in traditional detection method, workload is big, data are mixed and disorderly, be prone to features such as makeing mistakes, can not
Meet substantial amounts of detection demand.For problem above, problem previously has been developed for remote crack information gathering soft or hard
Part instrument, and paperless recording platform is replaced original papery platform, and on this platform, develop the inspection of intelligent crack
Survey on-the-spot fast recording instrument.But, original subject study knowledge completes the preliminary of crack pattern picture and identifies and take down in short-hand soon
, still there is remote capture equipment too much in record, is not easy to execute-in-place and intelligent cannot quickly identify Cracks character etc.
Problem, so automatically gathering integration mechanism in this problem firstly the need of developing crack, meanwhile, needs original crack
Intelligent processing method software upgrading so that it is Cracks character can be differentiated with fast intelligent.
Summary of the invention
It is an object of the invention to for deficiencies of the prior art, it is provided that the side of a kind of crack Intelligent Recognition classification
Method, the method can differentiate Cracks character with fast intelligent.
The technical solution used in the present invention is: the method for a kind of crack Intelligent Recognition classification, comprises the following steps:
(1) crack template database is initially set up:
(1) read crack sample image, and Color Image Processing is become gray level image；
(2) image analysis method is utilized automatically to obtain crack；
Utilize image projection to separate crack area with peak detection, the image procossing of reading is become rectangular histogram, according to directly
The peak value of side's figure, orients image-region to be processed, and then splits；
(3) feature in crack is extracted；
Vertical, floor projection and normalization process is utilized to generate crack template；
(4) the crack template of generation is saved in data base；
(2) identification then carrying out crack is classified:
(1) read test image, and Color Image Processing is become gray level image；
(2) image analysis method is utilized automatically to obtain crack；
Utilize image projection to separate crack area with peak detection, the image procossing of reading is become rectangular histogram, according to directly
The peak value of side's figure, orients image-region to be processed, and then splits；
(3) feature in crack is extracted；
Vertical, floor projection and normalization process is utilized to generate crack template；
(4) template in reading database
(5) judgement crack kind is compared with known data base；
Mated by the high speed of the known standard form with crack template base, automatically identify the kind in crack；If cannot
Find known crack kind, automatically carry out the foundation of new crack kind, and be saved in data base.
As preferably, described crack image analysis method and processing method, comprise the following steps:
(1) OpenCV is utilized to read gray scale picture；
(2) statistics often capable/each column meets the number of condition and pixel；
(3) rectangular histogram of OpenCV it is directly translated into；
(4) find vertical projective histogram and horizontal projective histogram peak value, first find peak-peak, peak separation is set
From parameter, limit seeking scope by this parameter, find second peak value；
(5) determine the position of maximum rectangle frame, obtained inside rectangle frame by ROI；
(6) floor projection and the OpenCV rectangular histogram of upright projection of rectangle inside picture is obtained by identical method；
(7) rectangular histogram normalization；
(8) rectangular histogram after template normalization is obtained.
The present invention is to input any form of wall body slit image, automatically obtains crack first with image analysis method,
As image projected and peak detection isolates crack area；Then the feature in crack is extracted；As utilized vertical, level
Projection and normalization process generate crack template；Finally, judgement crack kind is compared with known data base；As by and
The high speed coupling of the known standard form of crack template base, identifies the kind in crack automatically.
Beneficial effect: the present invention is simple to operate, workload is little, accuracy rate is high, can meet substantial amounts of detection demand, Ke Yiying
For quickly judging Cracks character.
Accompanying drawing explanation
Fig. 1 is the FB(flow block) that the present invention sets up crack template database；
Fig. 2 is the FB(flow block) identifying classification that the present invention carries out crack.
Detailed description of the invention
The present invention will be further described with detailed description of the invention below in conjunction with the accompanying drawings.
The method of a kind of crack Intelligent Recognition classification, comprises the following steps:
(1) as shown in Figure 1: initially set up crack template database:
(1) read crack sample image, and Color Image Processing is become gray level image；
(2) image analysis method is utilized automatically to obtain crack；
Utilize image projection to separate crack area with peak detection, the image procossing of reading is become rectangular histogram, according to directly
The peak value of side's figure, orients image-region to be processed, and then splits；
(3) feature in crack is extracted；
Vertical, floor projection and normalization process is utilized to generate crack template；
(4) the crack template of generation is saved in data base；
(2) as shown in Figure 2: the identification then carrying out crack is classified:
(1) read test image, and Color Image Processing is become gray level image；
(2) image analysis method is utilized automatically to obtain crack；
Utilize image projection to separate crack area with peak detection, the image procossing of reading is become rectangular histogram, according to directly
The peak value of side's figure, orients image-region to be processed, and then splits；
(3) feature in crack is extracted；
Vertical, floor projection and normalization process is utilized to generate crack template；
(4) template in reading database
(5) judgement crack kind is compared with known data base；
Mated by the high speed of the known standard form with crack template base, automatically identify the kind in crack；If cannot
Find known crack kind, automatically carry out the foundation of new crack kind, and be saved in data base.
Described crack image analysis method and processing method, comprise the following steps:
(1) OpenCV is utilized to read gray scale picture；
(2) statistics often capable/each column meets the number of condition and pixel；
(3) rectangular histogram of OpenCV it is directly translated into；
(4) find vertical projective histogram and horizontal projective histogram peak value, first find peak-peak, peak separation is set
From parameter, limit seeking scope by this parameter, find second peak value；
(5) determine the position of maximum rectangle frame, obtained inside rectangle frame by ROI；
(6) floor projection and the OpenCV rectangular histogram of upright projection of rectangle inside picture is obtained by identical method；
(7) rectangular histogram normalization；
(8) rectangular histogram after template normalization is obtained.
Control methods is for histogrammic relevant and crossing contrast, the local expression of end value the biggest (i.e. brightness is higher)
Join degree the highest；For histogrammic card side, Bhattacharyya contrast, the local expression of end value the least (the darkest)
Matching degree is the highest.
Above in association with accompanying drawing, embodiments of the present invention are described in detail, but the present invention is not limited to described reality
Execute mode.For those of ordinary skill in the art, in the range of the principle and technological thought of the present invention, these are implemented
Mode carries out multiple change, revises, replaces and deformation still falls within protection scope of the present invention.
Claims (2)
1. the method for a crack Intelligent Recognition classification, it is characterised in that: comprise the following steps:
(1) crack template database is initially set up:
(1) read crack sample image, and Color Image Processing is become gray level image；
(2) image analysis method is utilized automatically to obtain crack；
Utilize image projection to separate crack area with peak detection, the image procossing of reading is become rectangular histogram, according to rectangular histogram
Peak value, orient image-region to be processed, and then split；
(3) feature in crack is extracted；
Vertical, floor projection and normalization process is utilized to generate crack template；
(4) the crack template of generation is saved in data base；
(2) identification then carrying out crack is classified:
(1) read test image, and Color Image Processing is become gray level image；
(2) image analysis method is utilized automatically to obtain crack；
Utilize image projection to separate crack area with peak detection, the image procossing of reading is become rectangular histogram, according to rectangular histogram
Peak value, orient image-region to be processed, and then split；
(3) feature in crack is extracted；
Vertical, floor projection and normalization process is utilized to generate crack template；
(4) template in reading database
(5) judgement crack kind is compared with known data base；
Mated by the high speed of the known standard form with crack template base, automatically identify the kind in crack；If cannot find
Known crack kind, automatically carries out the foundation of new crack kind, and is saved in data base.
The method of crack the most according to claim 1 Intelligent Recognition classification, it is characterised in that: described crack graphical analysis side
Method and processing method, comprise the following steps:
(1) OpenCV is utilized to read gray scale picture；
(2) statistics often capable/each column meets the number of condition and pixel；
(3) rectangular histogram of OpenCV it is directly translated into；
(4) find vertical projective histogram and horizontal projective histogram peak value, first find peak-peak, peak separation is set from ginseng
Number, limits seeking scope by this parameter, finds second peak value；
(5) determine the position of maximum rectangle frame, obtained inside rectangle frame by ROI；
(6) floor projection and the OpenCV rectangular histogram of upright projection of rectangle inside picture is obtained by identical method；
(7) rectangular histogram normalization；
(8) rectangular histogram after template normalization is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610551362.9A CN106203351A (en) | 2016-07-13 | 2016-07-13 | The method of crack Intelligent Recognition classification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610551362.9A CN106203351A (en) | 2016-07-13 | 2016-07-13 | The method of crack Intelligent Recognition classification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106203351A true CN106203351A (en) | 2016-12-07 |
Family
ID=57476669
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610551362.9A Pending CN106203351A (en) | 2016-07-13 | 2016-07-13 | The method of crack Intelligent Recognition classification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106203351A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106683094A (en) * | 2017-01-12 | 2017-05-17 | 国家林业局北京林业机械研究所 | Quality evaluation method of wood veneer crack appearance |
| CN110823904A (en) * | 2019-10-31 | 2020-02-21 | 王佩洁 | Hydraulic engineering crack extraction method |
| CN110929565A (en) * | 2019-10-15 | 2020-03-27 | 平安科技（深圳）有限公司 | Risk monitoring method and device based on machine learning, storage medium and electronic equipment |
| CN114897803A (en) * | 2022-04-26 | 2022-08-12 | 中国电信集团工会上海市委员会 | Outer wall crack detection method and system based on unmanned aerial vehicle and edge calculation |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102412627A (en) * | 2011-11-29 | 2012-04-11 | 安徽继远电网技术有限责任公司 | Image identification-based intelligent transformer substation state monitoring system |
| CN102364496B (en) * | 2011-11-24 | 2015-06-17 | 无锡慧眼电子科技有限公司 | Method and system for identifying automobile license plates automatically based on image analysis |
| CN104794491A (en) * | 2015-04-28 | 2015-07-22 | 重庆大学 | Fuzzy clustering steel plate surface defect detection method based on pre classification |
-
2016
- 2016-07-13 CN CN201610551362.9A patent/CN106203351A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102364496B (en) * | 2011-11-24 | 2015-06-17 | 无锡慧眼电子科技有限公司 | Method and system for identifying automobile license plates automatically based on image analysis |
| CN102412627A (en) * | 2011-11-29 | 2012-04-11 | 安徽继远电网技术有限责任公司 | Image identification-based intelligent transformer substation state monitoring system |
| CN104794491A (en) * | 2015-04-28 | 2015-07-22 | 重庆大学 | Fuzzy clustering steel plate surface defect detection method based on pre classification |
Non-Patent Citations (2)
| Title |
|---|
| 蒋先刚: "《数字图像模式识别工程项目研究》", 31 March 2014, 成都：西南交通大学出版社 * |
| 郝晓静: "路面裂缝自动检测系统研究", 《中国优秀硕士学位论文全文数据库信息科技辑（月刊 ）》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106683094A (en) * | 2017-01-12 | 2017-05-17 | 国家林业局北京林业机械研究所 | Quality evaluation method of wood veneer crack appearance |
| CN106683094B (en) * | 2017-01-12 | 2019-09-17 | 国家林业和草原局北京林业机械研究所 | Wooden veneer crack Evaluation on Appearance Quality method |
| CN110929565A (en) * | 2019-10-15 | 2020-03-27 | 平安科技（深圳）有限公司 | Risk monitoring method and device based on machine learning, storage medium and electronic equipment |
| CN110929565B (en) * | 2019-10-15 | 2023-12-22 | 平安科技（深圳）有限公司 | Risk monitoring method and device based on machine learning, storage medium and electronic equipment |
| CN110823904A (en) * | 2019-10-31 | 2020-02-21 | 王佩洁 | Hydraulic engineering crack extraction method |
| CN114897803A (en) * | 2022-04-26 | 2022-08-12 | 中国电信集团工会上海市委员会 | Outer wall crack detection method and system based on unmanned aerial vehicle and edge calculation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111951237B (en) | Visual appearance detection method | |
| Zhu et al. | Concrete column recognition in images and videos | |
| CN103065134B (en) | A kind of fingerprint identification device and method with information | |
| CN106203351A (en) | The method of crack Intelligent Recognition classification | |
| CN108985170A (en) | Transmission line of electricity hanger recognition methods based on Three image difference and deep learning | |
| CN102324042B (en) | Visual recognition system and method | |
| CN103679147A (en) | Method and device for identifying model of mobile phone | |
| TWI254891B (en) | Face image detection method, face image detection system, and face image detection program | |
| CN104392229B (en) | Person's handwriting recognition methods based on stroke direction of fragments distribution characteristics | |
| CN111368682B (en) | Method and system for detecting and identifying station caption based on master RCNN | |
| WO2021046726A1 (en) | Method and device for detecting mechanical equipment parts | |
| CN106127205A (en) | A kind of recognition methods of the digital instrument image being applicable to indoor track machine people | |
| CN113076860B (en) | Bird detection system under field scene | |
| Liang et al. | Research on concrete cracks recognition based on dual convolutional neural network | |
| CN101533466A (en) | Image processing method for positioning eyes | |
| CN111612907A (en) | Multidirectional repairing system and method for damaged ancient building column | |
| CN105469099B (en) | Pavement crack detection and identification method based on sparse representation classification | |
| CN117788790A (en) | Material installation detection method, system, equipment and medium for general scene | |
| CN117351505A (en) | Information code identification method, device, equipment and storage medium | |
| CN104680520B (en) | It is a kind of scene three-dimensional information investigate method and system on the spot | |
| CN109977756A (en) | A kind of online In vivo detection system | |
| Wang et al. | As-built residential building information collection and modeling methods for energy analysis | |
| CN103278505A (en) | Blast furnace fly ash constituent analysis method based on multi-feature analysis | |
| CN113469086A (en) | Method, device, equipment and medium for dividing areas in building plan | |
| CN113627255A (en) | Mouse behavior quantitative analysis method, device, equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20161207 |