CN103489182B - A kind of fabric defects detection method based on image projection and svd - Google Patents
A kind of fabric defects detection method based on image projection and svd Download PDFInfo
- Publication number
- CN103489182B CN103489182B CN201310401043.6A CN201310401043A CN103489182B CN 103489182 B CN103489182 B CN 103489182B CN 201310401043 A CN201310401043 A CN 201310401043A CN 103489182 B CN103489182 B CN 103489182B
- Authority
- CN
- China
- Prior art keywords
- subwindow
- projection
- gained
- sequence
- matrix
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Treatment Of Fiber Materials (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The present invention relates to a kind of fabric defects detection method based on image projection and svd.First indefectible textile image sample is had in the training stage and be divided into square subwindow overlappingly; Then by resulting bottle window edge direction projection in length and breadth respectively, joint projection sequence is obtained; Finally svd is implemented to the matrix that associating projection sequence forms, extract base vector; At detection-phase, textile image sample zero lap Ground Split to be detected is divided into square subwindow; Simultaneously by the projection of subwindow along direction in length and breadth, obtain joint projection sequence; The joint projection sequence of application base vector to gained is reconstructed, and judges whether subwindow comprises flaw by reconstructed error.The present invention takes full advantage of longitude and latitude orientation characteristic that is cloth textured and flaw, by analyzing direction projection gained sequence in length and breadth, not only greatly reduce the complicacy of method, and cloth textured and flaw type there is stronger adaptability, especially to linear flaw to difference.
Description
Technical field
The invention belongs to image analysis processing field, the present invention relates to a kind of fabric defects detection method based on image projection and svd, be applied to the automatic Detection & Controling field of textile surface quality.
Background technology
If matrix A is the matrix of m × n, svd (SVD) can resolve into U matrix A, Σ and V tri-matrixes.Wherein matrix U is the orthogonal matrix of m × n, and matrix V is the orthogonal matrix of n × n, and matrix Σ is the matrix of m × n, and the element beyond its diagonal line is all zero, i.e. matrix Σ=diag (σ
1, σ
2..., σ
r) be diagonal matrix, r is the order of matrix A, σ
1, σ
2..., σ
rfor the singular value of A matrix.Matrix U and V are called left singular matrix and right singular matrix, and the element on the diagonal line of matrix Σ tapers off sequentially successively, that is: σ
1>=σ
2>=...>=σ
r>=0.
The diagonal element of matrix Σ is set as σ
k+1=σ
k+2=...=σ
r=0, obtain the reconstruct of matrix A under order k (k<r)
its reconstructed error uses Frobenius norm to be expressed as:
As can be seen from the above equation, obtained by svd
the reconstruct under the optimum low-rank of A matrix.In art of image analysis, svd is mainly used in compression, the reconstruct and recovery etc. of image.
At fabric defects detection field, Tomczak and Mosorov(2006) adopt the maximum singular value of gained after SVD decomposes to carry out fabric defects detection.Chen and Feng(2010) be extracted singular value average and carry out flaw differentiation as feature.Mak and
(2010) SVD is implemented to fabric sample, extract left singular matrix and often arrange as feature subimage, and by image pattern to be detected is projected to feature subimage, calculate the quadratic sum of the projection value of gained as flaw discriminant criterion.
It should be noted that above researcher directly carries out SVD on source textile image, then extract individual features and carry out Defect Detection, projection operation do not carried out to original image and and underuse the low-rank reconstruction nature of SVD.
Summary of the invention
Object of the present invention is exactly the deficiency overcoming existing algorithm, improve algorithm to different texture and flaw adaptability and real-time, a kind of fabric defects detection method based on image projection and svd is proposed.
A kind of fabric defects detection method based on image projection and svd of the present invention comprises the following steps:
(1) training stage;
Indefectible textile image sample is had and is divided into square subwindow overlappingly, and by subwindow edge direction projection in length and breadth respectively, obtain joint projection sequence; Then the joint projection sequence of gained is formed a matrix, and svd is implemented to this matrix, extract base vector;
(2) detection-phase;
Textile image sample to be detected continuous zero lap Ground Split is divided into square subwindow, and by the projection of subwindow along direction in length and breadth, obtains joint projection sequences y; Apply the base vector of gained in (1) y is reconstructed, obtain the reconstruct of y
calculate reconstructed error
and judge whether subwindow comprises flaw by reconstructed error;
Be implemented as follows:
In the training stage, described indefectible textile image sample is had and is divided into the square subwindow that size is w × w overlappingly, wherein 8 pixels≤w≤64 pixel; Described have division overlappingly to refer in the same row, a rear subwindow is that previous subwindow transverse translation step-length s obtains, lap is had between adjacent subwindow, the lateral length of described lap is w-s, in an adjacent row, the subwindow of next line is that the subwindow longitudinal translation step-length s of lastrow obtains, and has lap between adjacent subwindow, the longitudinal length of described lap is w-s, wherein 1≤s<w;
By subwindow edge direction projection in length and breadth respectively, namely calculate in subwindow the mean value of all pixel gray-scale values often arranging and often go, obtain two projection sequence; Then joint projection sequence is obtained after two of gained projection sequence being connected;
Joint projection sequence corresponding for all subwindows is arranged as a matrix as matrix column, and svd is implemented to the matrix of gained; The front k extracting left singular matrix arranges as base vector D, i.e. D=[d
1, d
2..., d
k], wherein d
1, d
2..., d
kfor the column vector of 1 to k row before left singular matrix, and there are 4≤k≤16;
At detection-phase, the continuous zero lap of textile image sample to be detected is divided into the square subwindow that size is w × w, wherein 8 pixels≤w≤64 pixel; Then according to the method for training stage, by subwindow respectively along vertical transverse projection, joint projection sequence is obtained; Apply the joint projection sequence of described base vector to detection-phase gained to be reconstructed, and judge whether subwindow comprises flaw by the reconstructed error E calculating its gained.
As preferred technical scheme:
As above based on a fabric defects detection method for image projection and svd, described fabric to be bit depth the be gray level image of 8.
As above based on a fabric defects detection method for image projection and svd, described reconstruct refers to the reconstruct of gained under least squares error.
As above based on a fabric defects detection method for image projection and svd, described judge whether subwindow comprises flaw and refer to and then think that subwindow comprises flaw when reconstructed error exceedes the threshold value preset by reconstructed error; The determination of threshold value: first test indefectible fabric, obtains the Cumulative Distribution Function of its reconstructed error E, then chooses reconstructed error value corresponding to its Cumulative Distribution Function 95% as threshold value.
A kind of fabric defects detection method based on image projection and svd as above, described joint projection sequence, refer to two projection sequence along direction projection gained in length and breadth, one front, another rear or one rear, another front with the sequence of end to end mode gained.
Beneficial effect:
1, the present invention obtains the preprocess method of associating sequence by implementing direction projection in length and breadth, greatly reduces the computational complexity of method, improves the real-time of method;
2, method of the present invention is irregular insensitive to illumination, and robustness is better;
3, to difference, cloth textured and flaw type has stronger adaptability, especially to linear flaw to method.
Accompanying drawing explanation
The division of the window of Fig. 1 w × w
The division of Fig. 2 lateral overlap window
The division of Fig. 3 longitudinal overlap window
Fig. 4 the present invention flaw trial image used
Fig. 5 is to the final detection result of trial image Fig. 4
Fig. 6 the present invention flaw trial image used
Fig. 7 is to the final detection result of trial image Fig. 6
Fig. 8 the present invention flaw trial image used
Fig. 9 is to the final detection result of trial image Fig. 8
Figure 10 the present invention flaw trial image used
Figure 11 is to the final detection result of trial image Figure 10
Embodiment
Below in conjunction with embodiment, set forth the present invention further.Should be understood that these embodiments are only not used in for illustration of the present invention to limit the scope of the invention.In addition should be understood that those skilled in the art can make various changes or modifications the present invention, and these equivalent form of values fall within the application's appended claims limited range equally after the content of having read the present invention's instruction.
A kind of fabric defects detection method based on image projection and svd of the present invention comprises the following steps:
(1) training stage;
Indefectible textile image sample is had and is divided into square subwindow overlappingly, and by subwindow edge direction projection in length and breadth respectively, obtain joint projection sequence; Then the joint projection sequence of gained is formed a matrix, and svd is implemented to this matrix, extract base vector;
(2) detection-phase;
Textile image sample to be detected continuous zero lap Ground Split is divided into square subwindow, and by the projection of subwindow along direction in length and breadth, obtains joint projection sequences y; Apply the base vector of gained in (1) y is reconstructed, obtain the reconstruct of y
calculate reconstructed error
and judge whether subwindow comprises flaw by reconstructed error;
Be implemented as follows:
In the training stage, described indefectible textile image sample is had and is divided into the square subwindow that size is w × w overlappingly, wherein 8 pixels≤w≤64 pixel; Described have division overlappingly to refer in the same row, a rear subwindow is that previous subwindow transverse translation step-length s obtains, lap is had between adjacent subwindow, the lateral length of described lap is w-s, in an adjacent row, the subwindow of next line is that the subwindow longitudinal translation step-length s of lastrow obtains, and has lap between adjacent subwindow, the longitudinal length of described lap is w-s, wherein 1≤s<w;
By subwindow edge direction projection in length and breadth respectively, namely calculate in subwindow the mean value of all pixel gray-scale values often arranging and often go, obtain two projection sequence; Then joint projection sequence is obtained after two of gained projection sequence being connected;
Joint projection sequence corresponding for all subwindows is arranged as a matrix as matrix column, and svd is implemented to the matrix of gained; The front k extracting left singular matrix arranges as base vector D, i.e. D=[d
1, d
2..., d
k], wherein d
1, d
2..., d
kfor the column vector of 1 to k row before left singular matrix, and there are 4≤k≤16;
At detection-phase, the continuous zero lap of textile image sample to be detected is divided into the square subwindow that size is w × w, wherein 8 pixels≤w≤64 pixel; Then according to the method for training stage, by subwindow respectively along vertical transverse projection, joint projection sequence is obtained; Apply the joint projection sequence of described base vector to detection-phase gained to be reconstructed, and judge whether subwindow comprises flaw by the reconstructed error E calculating its gained.
As preferred technical scheme:
As above based on a fabric defects detection method for image projection and svd, described fabric to be bit depth the be gray level image of 8.
As above based on a fabric defects detection method for image projection and svd, described reconstruct refers to the reconstruct of gained under least squares error.
As above based on a fabric defects detection method for image projection and svd, described judge whether subwindow comprises flaw and refer to and then think that subwindow comprises flaw when reconstructed error exceedes the threshold value preset by reconstructed error; The determination of threshold value: first test indefectible fabric, obtains the Cumulative Distribution Function of its reconstructed error E, then chooses reconstructed error value corresponding to its Cumulative Distribution Function 95% as threshold value.
A kind of fabric defects detection method based on image projection and svd as above, described joint projection sequence, refer to two projection sequence along direction projection gained in length and breadth, one front, another rear or one rear, another front with the sequence of end to end mode gained.
Embodiment 1
Training stage:
(1) indefectible textile image is had to be divided into size be overlappingly 32 × 32(pixel) foursquare subwindow, horizontal and vertical translating step is all 1 pixel, and its subwindow divides schematic diagram, as shown in Figure 1, Figure 2 and Figure 3;
(2) by subwindow edge direction projection in length and breadth respectively, namely calculate in subwindow the mean value of all pixel gray-scale values often arranging and often go, obtain two projection sequence; Then, joint projection sequence is obtained after two of gained projection sequence being connected;
(3) joint projection sequence corresponding for all subwindows is arranged as a matrix as matrix column, and svd is implemented to the matrix of gained; Extract front 4 row of left singular matrix as base vector D.
The determination of threshold value: first test indefectible fabric, obtains the Cumulative Distribution Function of its reconstructed error E, and reconstructed error value when then to choose corresponding to its Cumulative Distribution Function be 95% is as threshold value, and threshold value used is 17.
Detection-phase
(1) by image to be detected, as shown in Figure 4, be divided into size is 32 × 32(pixel continuous zero lap) foursquare subwindow;
(2) according to the method for training stage, by subwindow respectively along vertical transverse projection, joint projection sequence is obtained;
(3) apply the joint projection sequence of described base vector to detection-phase gained to be reconstructed, and judge whether subwindow comprises flaw by the reconstructed error E calculating its gained, as shown in Figure 5, wherein black box represents the subwindow being judged as and comprising flaw to actual testing result.
Embodiment 2
Training stage:
(1) indefectible textile image is had to be divided into size be overlappingly 32 × 32(pixel) foursquare subwindow, horizontal and vertical translating step is all 1 pixel, and its subwindow divides schematic diagram, as shown in Figure 1, Figure 2 and Figure 3;
(2) by subwindow edge direction projection in length and breadth respectively, namely calculate in subwindow the mean value of all pixel gray-scale values often arranging and often go, obtain two projection sequence; Then, joint projection sequence is obtained after two of gained projection sequence being connected;
(3) joint projection sequence corresponding for all subwindows is arranged as a matrix as matrix column, and svd is implemented to the matrix of gained; Extract front 16 row of left singular matrix as base vector D.
The determination of threshold value: first test indefectible fabric, obtains the Cumulative Distribution Function of its reconstructed error E, and reconstructed error value when then to choose corresponding to its Cumulative Distribution Function be 95% is as threshold value, and threshold value used is 27.
Detection-phase
(1) by image to be detected, as shown in Figure 6, be divided into size is 32 × 32(pixel continuous zero lap) foursquare subwindow;
(2) according to the method for training stage, by subwindow respectively along vertical transverse projection, joint projection sequence is obtained;
(3) apply the joint projection sequence of described base vector to detection-phase gained to be reconstructed, and judge whether subwindow comprises flaw by the reconstructed error E calculating its gained, as shown in Figure 7, wherein black box represents the subwindow being judged as and comprising flaw to actual testing result.
Embodiment 3
Training stage:
(1) indefectible textile image is had to be divided into size be overlappingly 32 × 32(pixel) foursquare subwindow, horizontal and vertical translating step is all 31 pixels, and its subwindow divides schematic diagram, as shown in Figure 1, Figure 2 and Figure 3;
(2) by subwindow edge direction projection in length and breadth respectively, namely calculate in subwindow the mean value of all pixel gray-scale values often arranging and often go, obtain two projection sequence; Then, joint projection sequence is obtained after two of gained projection sequence being connected;
(3) joint projection sequence corresponding for all subwindows is arranged as a matrix as matrix column, and svd is implemented to the matrix of gained; Extract front 4 row of left singular matrix as base vector D.
The determination of threshold value: first test indefectible fabric, obtains the Cumulative Distribution Function of its reconstructed error E, and reconstructed error value when then to choose corresponding to its Cumulative Distribution Function be 95% is as threshold value, and threshold value used is 28.
Detection-phase
(1) by image to be detected, as shown in Figure 8, be divided into size is 32 × 32(pixel continuous zero lap) foursquare subwindow;
(2) according to the method for training stage, by subwindow respectively along vertical transverse projection, joint projection sequence is obtained;
(3) apply the joint projection sequence of described base vector to detection-phase gained to be reconstructed, and judge whether subwindow comprises flaw by the reconstructed error E calculating its gained, as shown in Figure 9, wherein black box represents the subwindow being judged as and comprising flaw to actual testing result.
Embodiment 4
Training stage:
(1) indefectible textile image is had to be divided into size be overlappingly 32 × 32(pixel) foursquare subwindow, horizontal and vertical translating step is all 31 pixels, and its subwindow divides schematic diagram, as shown in Figure 1, Figure 2 and Figure 3;
(2) by subwindow edge direction projection in length and breadth respectively, namely calculate in subwindow the mean value of all pixel gray-scale values often arranging and often go, obtain two projection sequence; Then, joint projection sequence is obtained after two of gained projection sequence being connected;
(3) joint projection sequence corresponding for all subwindows is arranged as a matrix as matrix column, and svd is implemented to the matrix of gained; Extract front 16 row of left singular matrix as base vector D.
The determination of threshold value: first test indefectible fabric, obtains the Cumulative Distribution Function of its reconstructed error E, and reconstructed error value when then to choose corresponding to its Cumulative Distribution Function be 95% is as threshold value, and threshold value used is 17.
Detection-phase
(1) by image to be detected, as shown in Figure 10, be divided into size is 32 × 32(pixel continuous zero lap) foursquare subwindow;
(2) according to the method for training stage, by subwindow respectively along vertical transverse projection, joint projection sequence is obtained;
(3) apply the joint projection sequence of described base vector to detection-phase gained to be reconstructed, and judge whether subwindow comprises flaw by the reconstructed error E calculating its gained, as shown in figure 11, wherein black box represents the subwindow being judged as and comprising flaw to actual testing result.
Claims (3)
1., based on a fabric defects detection method for image projection and svd, it is characterized in that comprising the following steps:
(1) training stage;
Indefectible textile image sample is had and is divided into square subwindow overlappingly,
By subwindow edge direction projection in length and breadth respectively, namely calculate in subwindow the mean value of all pixel gray-scale values often arranging and often go, obtain two projection sequence; Then joint projection sequence is obtained after two of gained projection sequence being connected; Then the joint projection sequence of gained is formed a matrix, and svd is implemented to this matrix, extract base vector;
(2) detection-phase;
Textile image sample to be detected continuous zero lap Ground Split is divided into square subwindow, and by the projection of subwindow along direction in length and breadth, obtains joint projection sequences y; Apply the base vector of gained in (1) y is reconstructed, obtain the reconstruct of y
calculate reconstructed error
and judge whether subwindow comprises flaw by reconstructed error;
Be implemented as follows:
In the training stage, described indefectible textile image sample is had and is divided into the square subwindow that size is w × w overlappingly, wherein 8 pixels≤w≤64 pixel; Described have division overlappingly to refer in the same row, a rear subwindow is that previous subwindow transverse translation step-length s obtains, lap is had between adjacent subwindow, the lateral length of described lap is w-s, in an adjacent row, the subwindow of next line is that the subwindow longitudinal translation step-length s of lastrow obtains, and has lap between adjacent subwindow, the longitudinal length of described lap is w-s, wherein 1≤s<w;
Joint projection sequence corresponding for all subwindows is arranged as a matrix as matrix column, and svd is implemented to the matrix of gained; The front k extracting left singular matrix arranges as base vector D, i.e. D=[d
1, d
2..., d
k], wherein d
1, d
2..., d
kfor the column vector of 1 to k row before left singular matrix, and there are 4≤k≤16;
At detection-phase, the continuous zero lap of textile image sample to be detected is divided into the square subwindow that size is w × w, wherein 8 pixels≤w≤64 pixel; Then according to the method for training stage, by subwindow edge direction projection in length and breadth respectively, namely calculate in subwindow the mean value of all pixel gray-scale values often arranging and often go, obtain two projection sequence; Then joint projection sequence is obtained after two of gained projection sequence being connected; Apply the joint projection sequence of described base vector to detection-phase gained to be reconstructed, and judge whether subwindow comprises flaw by the reconstructed error E calculating its gained;
Described reconstruct refers to the reconstruct of gained under least squares error;
Described judge whether subwindow comprises flaw and refer to and then think that subwindow comprises flaw when reconstructed error exceedes the threshold value preset by reconstructed error; The determination of threshold value: first test indefectible fabric, obtains the Cumulative Distribution Function of its reconstructed error E, then chooses reconstructed error value corresponding to its Cumulative Distribution Function 95% as threshold value.
2. a kind of fabric defects detection method based on image projection and svd according to claim 1, is characterized in that, described fabric to be bit depth the be gray level image of 8.
3. a kind of fabric defects detection method based on image projection and svd according to claim 1, it is characterized in that, described joint projection sequence, refer to two projection sequence along direction projection gained in length and breadth, one front, another rear or one rear, another front with the sequence of end to end mode gained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310401043.6A CN103489182B (en) | 2013-09-05 | 2013-09-05 | A kind of fabric defects detection method based on image projection and svd |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310401043.6A CN103489182B (en) | 2013-09-05 | 2013-09-05 | A kind of fabric defects detection method based on image projection and svd |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103489182A CN103489182A (en) | 2014-01-01 |
| CN103489182B true CN103489182B (en) | 2016-04-20 |
Family
ID=49829380
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310401043.6A Active CN103489182B (en) | 2013-09-05 | 2013-09-05 | A kind of fabric defects detection method based on image projection and svd |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103489182B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105426902B (en) * | 2015-09-16 | 2019-06-25 | 西安印钞有限公司 | Money quality detecting system and method based on deformation recovery technique |
| CN107194920B (en) * | 2017-05-19 | 2019-07-19 | 山东财经大学 | A kind of tire defect inspection method based on singular value decomposition |
| CN109345548B (en) * | 2018-10-23 | 2021-08-13 | 江南大学 | Fabric defect segmentation method based on total variation |
| CN110610484B (en) * | 2019-08-21 | 2022-04-12 | 西安理工大学 | Printing dot quality detection method based on rotary projection transformation |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110124090A (en) * | 2010-05-10 | 2011-11-16 | 동우 화인켐 주식회사 | System and method for evaluating quality of polarized film |
| CN102867299A (en) * | 2012-08-09 | 2013-01-09 | 东华大学 | Image analysis method based on singular value decomposition and method applied to defect detection of fabric |
| CN102938151A (en) * | 2012-11-22 | 2013-02-20 | 中国人民解放军电子工程学院 | Method for detecting anomaly of hyperspectral image |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE29521937U1 (en) * | 1995-05-10 | 1998-12-03 | Legler Industria Tèssile S.p.A., Ponte San Pietro, Bergamo | Test system for moving material |
-
2013
- 2013-09-05 CN CN201310401043.6A patent/CN103489182B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110124090A (en) * | 2010-05-10 | 2011-11-16 | 동우 화인켐 주식회사 | System and method for evaluating quality of polarized film |
| CN102867299A (en) * | 2012-08-09 | 2013-01-09 | 东华大学 | Image analysis method based on singular value decomposition and method applied to defect detection of fabric |
| CN102938151A (en) * | 2012-11-22 | 2013-02-20 | 中国人民解放军电子工程学院 | Method for detecting anomaly of hyperspectral image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103489182A (en) | 2014-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103473769B (en) | A kind of fabric defects detection method based on svd | |
| CN103871053B (en) | Vision conspicuousness-based cloth flaw detection method | |
| CN103489182B (en) | A kind of fabric defects detection method based on image projection and svd | |
| CN108090894B (en) | Fabric defect detection method based on distance matching function and perceptual hash algorithm | |
| CN108009591A (en) | A kind of contact network key component identification method based on deep learning | |
| CN102737252B (en) | Method for detecting faults caused by foreign body pollution between electrified railway insulator plates based on affine invariant moment | |
| CN110009618A (en) | A kind of Axle Surface quality determining method and device | |
| CN102855617B (en) | Method and system for processing adaptive images | |
| CN102867299B (en) | Image analysis method based on singular value decomposition and method applied to defect detection of fabric | |
| CN104268505A (en) | Automatic cloth defect point detection and recognition device and method based on machine vision | |
| CN112070727B (en) | Metal surface defect detection method based on machine learning | |
| CN106780455A (en) | A kind of product surface detection method based on the local neighborhood window for sliding | |
| CN103646381B (en) | A kind of distortion correction method of advancing of line array CCD | |
| CN104573707A (en) | Vehicle license plate Chinese character recognition method based on multi-feature fusion | |
| CN102393902A (en) | Vehicle color detection method based on H_S two-dimensional histogram and regional color matching | |
| CN111738931B (en) | Shadow removal algorithm for aerial image of photovoltaic array unmanned aerial vehicle | |
| CN112288726A (en) | Method for detecting foreign matters on belt surface of underground belt conveyor | |
| CN113674263A (en) | Small sample defect detection method based on generation type countermeasure network | |
| CN111179239B (en) | Tire X-ray flaw detection method for performing re-ranking by using background features | |
| CN102289677B (en) | Method for analyzing image based on principal component analysis and method applicable to detection of defects of fabric | |
| CN103473770B (en) | A kind of linear textiles flaw detection method based on rectangular window projection and singular value decomposition | |
| CN101976440A (en) | Sobel operator-based extraction method of profile and detail composite characteristic vector used for representing fabric texture | |
| CN103106663A (en) | Method for detecting defect of subscriber identity module (SIM) card based on image processing in computer system | |
| CN109345548B (en) | Fabric defect segmentation method based on total variation | |
| CN101540833B (en) | Anti-interference real-time tracking method for profile of object |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |