CN103886602A - Radial image deflect detecting method based on veins - Google Patents
Radial image deflect detecting method based on veins Download PDFInfo
- Publication number
- CN103886602A CN103886602A CN201410123705.2A CN201410123705A CN103886602A CN 103886602 A CN103886602 A CN 103886602A CN 201410123705 A CN201410123705 A CN 201410123705A CN 103886602 A CN103886602 A CN 103886602A
- Authority
- CN
- China
- Prior art keywords
- image
- defect
- sub
- texture
- ray image
- 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
Images
Landscapes
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The invention discloses a radial image deflect detecting method based on veins. The method comprises the steps that a standard defect vein image data base is established according to the system detecting requirement and detecting target features; second, conducting fusion enhancement on a radial image of a detected workpiece; then calculating a vein feature value of a sub-block image in the enhanced image, sequentially comparing the feature value and a vein feature value of the defect vein base so as to judging whether the sub-block image is defective; traversing the whole image to detect the number and the types of the defects in the image. According to the radial image deflect detecting method based on veins, the problem of complex weak edge extraction is solved, it can be judged whether the workpiece has the defects and the positions of the defects in the detecting process, and what is more, the types and grades of the defects are directly given, so that labor strength of detecting personnel is greatly reduced.
Description
Technical field
The present invention relates to image processes and field of non destructive testing, particularly a kind of measured workpiece ray image defect inspection method based on defect textural characteristics.
Background technology
At present for ray image, people have developed many defect extraction algorithms, this type of algorithm is directly image to be carried out to rim detection mostly, because the low contrast characteristic of ray image itself makes this type of algorithm all comparatively complicated, and more consuming time, more trouble is that this type of algorithm allows to extract defect but cannot provide result to the type of defect, grade, and this is to product, whether qualified judgement is even more important.
Image texture has reflected the intensity profile rule of picture element, and the surface information that has comprised image and the relation of surrounding environment thereof have been described the random and macroscopical well-regulated feature of image local, can better take into account macrostructure and the micromechanism of image.Analyzing image texture all has a wide range of applications in many fields such as Medical Image Processing, satellite remote sensing, industrial monitoring and computer visions.Various images in remote sensing photo, major part presents texture type, and Plain, low mound and mountain range have the fluctuating of different shapes and height, are reflected in the texture that presents different roughness and direction on image; Aspect tectonic structure, dissimilar rock stratum has different beddings, trend and granularity, presents the texture of different distributions, direction, grain size and fineness degree on image; Aspect soil utilizes, man-made features, as road, settlement place etc. have the comparatively texture of rule, natural feature on a map presents texture irregular, stochastic distribution; In historical relic recovery system, the cultural relic fragments of Different Individual has different shapes and texture, by form fit and texture analysis, contributes to realize historical relic and restores; In micro-image, the nucleus structural change message reflection of cell image is the variation of texture on image; In the microstructure quantitative test of material science, the micro image of material much presents texture type; In pathological diagnosis, the texture tool of the organ surface of the texture on normal organ surface and generation pathology is very different, and can realize thus pathological diagnosis.
The existing information such as size, position that can detect image deflects to the detection of image deflects, but also cannot judge for the type grade of defect.
Summary of the invention
Given this, the object of this invention is to provide a kind of measured workpiece ray image defect inspection method based on defect textural characteristics, the method adopts the textural characteristics of defect, avoid the defect inspection method of complicated weak edge extracting, not only can effectively detect the defect of measured workpiece, more can directly obtain size and the grade of defect.
The object of the invention is to realize by such technical scheme, a kind of ray image defect inspection method based on texture, specifically comprises the following steps:
S1: the texture image database of setting up defect according to the defect characteristic in checked object radial imaging;
S2: the on-the-spot ray image that obtains object to be measured;
S3: strengthen on-the-spot ray image, obtain the enhancing ray image after strengthening;
S4: fall into a trap and calculate the textural characteristics value of sub-image from strengthening ray image, the eigenwert in this eigenwert and defect texture storehouse relatively successively, thus judge whether this sub-image is defect;
S5: travel through whole enhancing ray image and detect the textural characteristics value of this each sub-image of image, utilize the eigenwert in these eigenwerts and defect texture storehouse to compare;
S6: adopt discrimination standard to determine to strengthen each sub-block of ray image whether to comprise defect and defect type, grade;
S7: defects detection outcome record is supplied to testing staff's reference in database, and form defects detection report.
Further, in described S1, carry out as follows:
The foundation in defect texture storehouse, with reference to current existing product examination criteria and collection of illustrative plates, is carried out ray detection to every kind of workpiece to be measured, in the image from strengthening, selects defect area to join in texture storehouse.
Further, described S3 specifically comprises following sub-step:
S31: first obtain the multiple image that comprises different defect characteristics from use linear stretch method measured workpiece ray image;
S32: then adopting respectively multiresolution method to carry out multilayer decomposition to multiple image, is the coefficient of frequency on different layers by picture breakdown;
S33: coefficient of frequency is carried out to fusion treatment, the multiresolution coefficient of frequency pyramid after being merged;
S34: be finally reconstructed merging rear gained multiresolution coefficient of frequency pyramid, obtain reconstructed image and be enhancing ray image.
Further, described S5 is further comprising the steps of:
If G is the to be detected image of size for M × N, F
ifor size is that a × b is detection template, i=1,2 ..., N, uses the basic procedure of texture analysis method detected image defect as follows:
S41: image is cut apart, is divided into several F by image G to be detected
ithe sub-block of size;
S42: calculate sub-image
value, calculates each number of sub images of cutting apart rear relevant position
value;
S43: calculating detection template image
value;
S44: calculation template image and each number of sub images successively
distance between value, if distance be less than limit value this piece region be defect;
S45: mark regional location in image to be detected successively.
Further, carrying out image while cutting apart, image is divided into overlapped sub-block.
Further, carrying out image while cutting apart, image is divided into
piece.
Owing to having adopted technique scheme, the present invention has advantages of as follows:
The present invention adopts defect inspection method in a kind of ray image based on defect textural characteristics, very effective to the online detection of the real-time radial imaging of large batch of product, avoid the direct edge extracting method of ray image generally using at present, not only realize the accurate location of defect in workpiece ray image, and directly provided type, the grade of defect, reduce greatly testing staff's labour intensity.That the present invention has is easy to operate, identify advantage accurately, method is applicable to the real-time radiography inspection of typical products in mass production, can fast detecting go out the type, the grade etc. that in product, whether comprise defect and defect, and can clear out in real time in conjunction with control parameter the physical location of defect place workpiece.
Accompanying drawing explanation
In order to make the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing, the present invention is described in further detail, wherein:
Fig. 1 is the defect recognition process flow diagram based on texture;
Fig. 2 is texture storehouse process of establishing;
Fig. 3 is that texture detects the parallel schematic diagram that accelerates of operator.
Embodiment
Below with reference to accompanying drawing, the preferred embodiments of the present invention are described in detail; Should be appreciated that preferred embodiment is only for the present invention is described, rather than in order to limit the scope of the invention.
Ray image defect inspection method based on textural characteristics, comprises the following steps: S1: the texture image database of setting up defect according to the defect characteristic in checked object radial imaging; S2: the on-the-spot ray image that obtains object to be measured; S3: strengthen on-the-spot ray image, obtain the enhancing ray image after strengthening; S4: fall into a trap and calculate the textural characteristics value of sub-image from strengthening ray image, the eigenwert in this eigenwert and defect texture storehouse relatively successively, thus judge whether this sub-image is defect; S5: travel through whole enhancing ray image and detect the textural characteristics value of this each sub-image of image, utilize the eigenwert in these eigenwerts and defect texture storehouse to compare; S6: adopt discrimination standard to determine to strengthen each sub-block of ray image whether to comprise defect and defect type, grade; S7: defects detection outcome record is supplied to testing staff's reference in database, and form defects detection report.
In described S1, carry out as follows: the foundation in defect texture storehouse can be with reference to current existing product examination criteria and collection of illustrative plates, every kind of workpiece to be measured is carried out to ray detection, in image from strengthening, select defect area to join in texture storehouse, the region of selection represents various typical defects as much as possible.The size of texture region is consistent as much as possible, can reduce like this calculated amount in the time of characteristic measure, effectively improves the detection efficiency of defect.
In described S3, carry out as follows: first from use linear stretch method measured workpiece ray image, obtain the multiple image that comprises different defect characteristics; Then adopting respectively multiresolution method to carry out multilayer decomposition to multiple image, is the coefficient of frequency on different layers by picture breakdown; Coefficient of frequency is carried out to fusion treatment, the multiresolution coefficient of frequency pyramid after being merged; Finally be reconstructed merging rear gained multiresolution coefficient of frequency pyramid, obtain reconstructed image and be enhancing ray image.
Described step S5 is further comprising the steps of: establish the image to be detected that G is M × N for size, F
i(i=1,2 ..., N) and be the detection template of size for a × b, use the basic procedure of texture analysis method detected image defect as follows:
1. image is cut apart.Generally speaking, the little and to be detected image of texture formwork image is very large, therefore in order to compare F
iand the similarity between the sub-block of G, first needs G to be divided into the sub-block of Fi size one by one.If while cutting apart, image can not be divided into the sub-block of integer size just time, can first carry out cutting apart again after continuation to image.But having a problem is here exactly to cut apart by image the texture bringing to isolate effect, a texture image is divided into two sub-blocks and causes correctly detecting this texture.For digital picture, for fear of the distortion bringing because of piecemeal in image, image need to be divided into overlapped sub-block.For example, when the image of M × N is divided into a series of a × b sub-blocks, a kind of typical way is exactly at every row and often lists respectively and mark off (M-a) × (N-b) individual sub-block, lap size between adjacent two sub-blocks is (a-1) × (b-1), only in this way could cover the possibility that various textures occur completely.But the problem of band is thus, and the detection efficiency of defect reduces greatly, this be mainly because the redundance of pixel (redundance of pixel is up to that a × b), we are divided into image in order to improve detection efficiency due to too high
piece, each point of cutting apart in rear image belongs to 4 sub-blocks (except edge pixel) simultaneously, and the redundance of each pixel is 4, and this is the speed that reduces picture redundancy and exchange for detection.
2. calculate sub-image
value.Each number of sub images of cutting apart rear relevant position is calculated
value.
3. calculation template image
value.
4. calculation template image and each number of sub images successively
distance between value.If distance be less than limit value this piece region be defect.
5. mark regional location in image to be detected successively.
Defect inspection method of the present invention is applicable to the real-time radiography inspection of typical products in mass production, can fast detecting go out the type, the grade etc. that in product, whether comprise defect and defect, and can clear out in real time in conjunction with control parameter the physical location of defect place workpiece.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, obviously, those skilled in the art can carry out various changes and modification and not depart from the spirit and scope of the present invention the present invention.Like this, if within of the present invention these are revised and modification belongs to the scope of the claims in the present invention and equivalent technologies thereof, the present invention is also intended to comprise these changes and modification interior.
Claims (6)
1. the ray image defect inspection method based on texture, is characterized in that: specifically comprise the following steps:
S1: the texture image database of setting up defect according to the defect characteristic in checked object radial imaging;
S2: the on-the-spot ray image that obtains object to be measured;
S3: strengthen on-the-spot ray image, obtain the enhancing ray image after strengthening;
S4: fall into a trap and calculate the textural characteristics value of sub-image from strengthening ray image, the eigenwert in this eigenwert and defect texture storehouse relatively successively, thus judge whether this sub-image is defect;
S5: travel through whole enhancing ray image and detect the textural characteristics value of this each sub-image of image, utilize the eigenwert in these eigenwerts and defect texture storehouse to compare;
S6: adopt discrimination standard to determine to strengthen each sub-block of ray image whether to comprise defect and defect type, grade;
S7: defects detection outcome record is supplied to testing staff's reference in database, and form defects detection report.
2. the ray image defect inspection method based on texture according to claim 1, is characterized in that: in described S1, carry out as follows:
The foundation in defect texture storehouse, with reference to current existing product examination criteria and collection of illustrative plates, is carried out ray detection to every kind of workpiece to be measured, in the image from strengthening, selects defect area to join in texture storehouse.
3. the ray image defect inspection method based on textural characteristics according to claim 1, is characterized in that: described S3 specifically comprises following sub-step:
S31: first obtain the multiple image that comprises different defect characteristics from use linear stretch method measured workpiece ray image;
S32: then adopting respectively multiresolution method to carry out multilayer decomposition to multiple image, is the coefficient of frequency on different layers by picture breakdown;
S33: coefficient of frequency is carried out to fusion treatment, the multiresolution coefficient of frequency pyramid after being merged;
S34: be finally reconstructed merging rear gained multiresolution coefficient of frequency pyramid, obtain reconstructed image and be enhancing ray image.
4. the ray image defect inspection method based on textural characteristics according to claim 1, is characterized in that: described S5 is further comprising the steps of:
If G is the to be detected image of size for M × N, F
ifor size is that a × b is detection template, i=1,2 ..., N, uses the basic procedure of texture analysis method detected image defect as follows:
S41: image is cut apart, is divided into several F by image G to be detected
ithe sub-block of size;
S42: calculate sub-image
value, calculates each number of sub images of cutting apart rear relevant position
value;
S43: calculating detection template image
value;
S44: calculation template image and each number of sub images successively
distance between value, if distance be less than limit value this piece region be defect;
S45: mark regional location in image to be detected successively.
5. the ray image defect inspection method based on texture according to claim 4, is characterized in that: carrying out image while cutting apart, image is divided into overlapped sub-block.
6. the ray image defect inspection method based on texture according to claim 5, is characterized in that: carrying out image while cutting apart, image is divided into
piece.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410123705.2A CN103886602A (en) | 2014-03-28 | 2014-03-28 | Radial image deflect detecting method based on veins |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410123705.2A CN103886602A (en) | 2014-03-28 | 2014-03-28 | Radial image deflect detecting method based on veins |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103886602A true CN103886602A (en) | 2014-06-25 |
Family
ID=50955475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410123705.2A Pending CN103886602A (en) | 2014-03-28 | 2014-03-28 | Radial image deflect detecting method based on veins |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103886602A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372645A (en) * | 2016-08-29 | 2017-02-01 | 广东工业大学 | Mobile phone housing complex texture background defect detection method |
| CN107209932A (en) * | 2014-12-27 | 2017-09-26 | 希尔氏宠物营养品公司 | Food-processing method and system |
| CN107862693A (en) * | 2017-12-08 | 2018-03-30 | 湖南文理学院 | Detection method and device for nickel foam surface defect |
| CN109142379A (en) * | 2018-09-19 | 2019-01-04 | 武汉意普科技有限责任公司 | SOC embedded machine vision equipment based on FPGA |
| CN110111309A (en) * | 2019-04-12 | 2019-08-09 | 国网江苏省电力有限公司电力科学研究院 | Carbon fiber composite core wire ray image processing method, defect inspection method, device, equipment and computer storage medium |
| CN110111308A (en) * | 2019-04-12 | 2019-08-09 | 国网江苏省电力有限公司电力科学研究院 | Carbon fiber composite core wire ray image processing method, defect inspection method, device, equipment and computer storage medium |
| CN113689416A (en) * | 2021-08-30 | 2021-11-23 | 中建深圳装饰有限公司 | Building curtain wall safety nondestructive detection imaging method based on microwave imaging |
| CN117237336A (en) * | 2023-11-10 | 2023-12-15 | 湖南科技大学 | Metallized ceramic ring defect detection method, system and readable storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103149222A (en) * | 2013-02-28 | 2013-06-12 | 重庆大学 | Flaw detection device in real-time imaging of ray |
| CN103413311A (en) * | 2013-08-19 | 2013-11-27 | 厦门美图网科技有限公司 | Edge-based fuzzy detection method |
-
2014
- 2014-03-28 CN CN201410123705.2A patent/CN103886602A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103149222A (en) * | 2013-02-28 | 2013-06-12 | 重庆大学 | Flaw detection device in real-time imaging of ray |
| CN103413311A (en) * | 2013-08-19 | 2013-11-27 | 厦门美图网科技有限公司 | Edge-based fuzzy detection method |
Non-Patent Citations (1)
| Title |
|---|
| 毕碧: "局部二值模式的改进及其在工业X射线图像中的应用研究", 《中国博士学位论文全文数据库》, 15 April 2013 (2013-04-15), pages 2 - 3 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107209932A (en) * | 2014-12-27 | 2017-09-26 | 希尔氏宠物营养品公司 | Food-processing method and system |
| CN106372645A (en) * | 2016-08-29 | 2017-02-01 | 广东工业大学 | Mobile phone housing complex texture background defect detection method |
| CN107862693A (en) * | 2017-12-08 | 2018-03-30 | 湖南文理学院 | Detection method and device for nickel foam surface defect |
| CN107862693B (en) * | 2017-12-08 | 2021-10-08 | 湖南文理学院 | Method and device for detecting surface defects of foamed nickel |
| CN109142379A (en) * | 2018-09-19 | 2019-01-04 | 武汉意普科技有限责任公司 | SOC embedded machine vision equipment based on FPGA |
| CN110111309A (en) * | 2019-04-12 | 2019-08-09 | 国网江苏省电力有限公司电力科学研究院 | Carbon fiber composite core wire ray image processing method, defect inspection method, device, equipment and computer storage medium |
| CN110111308A (en) * | 2019-04-12 | 2019-08-09 | 国网江苏省电力有限公司电力科学研究院 | Carbon fiber composite core wire ray image processing method, defect inspection method, device, equipment and computer storage medium |
| CN110111309B (en) * | 2019-04-12 | 2022-08-19 | 国网江苏省电力有限公司电力科学研究院 | Carbon fiber composite core wire ray image processing, defect detection and storage medium |
| CN110111308B (en) * | 2019-04-12 | 2022-08-23 | 国网江苏省电力有限公司电力科学研究院 | Method and device for processing radiation image of carbon fiber composite core wire |
| CN113689416A (en) * | 2021-08-30 | 2021-11-23 | 中建深圳装饰有限公司 | Building curtain wall safety nondestructive detection imaging method based on microwave imaging |
| CN117237336A (en) * | 2023-11-10 | 2023-12-15 | 湖南科技大学 | Metallized ceramic ring defect detection method, system and readable storage medium |
| CN117237336B (en) * | 2023-11-10 | 2024-02-23 | 湖南科技大学 | Metallized ceramic ring defect detection method, system and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103886602A (en) | Radial image deflect detecting method based on veins | |
| Li et al. | Recognition and evaluation of bridge cracks with modified active contour model and greedy search-based support vector machine | |
| Ni et al. | Zernike‐moment measurement of thin‐crack width in images enabled by dual‐scale deep learning | |
| CN105787486B (en) | A kind of girder steel crack detecting method based on image procossing | |
| CN108460760B (en) | Bridge crack image distinguishing and repairing method based on generation type countermeasure network | |
| Koch et al. | Improving pothole recognition through vision tracking for automated pavement assessment | |
| Gui et al. | Automated defect detection and visualization for the robotic airport runway inspection | |
| JP6079948B1 (en) | Surface defect detection device and surface defect detection method | |
| CN103927553B (en) | Coal and rock recognition method based on multi-scale micro-lamination and contrast ratio joint distribution | |
| Li et al. | Post-earthquake assessment of building damage degree using LiDAR data and imagery | |
| Xie et al. | Fabric defect detection method combing image pyramid and direction template | |
| Adhikari et al. | Tracking of defects in reinforced concrete bridges using digital images | |
| Wu et al. | Concrete spalling detection for metro tunnel from point cloud based on roughness descriptor | |
| Qiu et al. | Methodology for accurate AASHTO PP67-10–based cracking quantification using 1-mm 3D pavement images | |
| CN109767426B (en) | Shield tunnel water leakage detection method based on image feature recognition | |
| Guo et al. | Visual pattern recognition supporting defect reporting and condition assessment of wastewater collection systems | |
| Adu-Gyamfi et al. | Functional evaluation of pavement condition using a complete vision system | |
| Carrasco et al. | Visual inspection of glass bottlenecks by multiple-view analysis | |
| Radopoulou et al. | Patch distress detection in asphalt pavement images | |
| Guldur et al. | Automated classification of detected surface damage from point clouds with supervised learning | |
| CN103472064A (en) | Appraisal method of circular bright polished gemstone cut | |
| CN105740869A (en) | Square operator edge extraction method and system based on multiple scales and multiple resolutions | |
| CN109785313A (en) | A kind of tire qualification detection method based on LBP | |
| CN108846839A (en) | A kind of saggar crack detecting method based on fan-shaped neighborhood difference histogram | |
| Maningo et al. | Crack detection with 2D wall mapping for building safety inspection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140625 |