基于对偶范数低秩分解的织物疵点检测方法
|
摘要
研究一种基于对偶范数低秩分解模型的模式织物疵点检测方法。通过Log-Gabor滤波器提取织物图像的纹理特征,进而构造高度低秩的特征矩阵;采用基于对偶范数的低秩分解模型将特征矩阵分为低秩部分(背景)与非低秩部分(疵点),采用核范数的对偶范数作为正则项来替代原有低秩分解模型中的"稀疏"约束,使背景和疵点的相关度最小,从而实现疵点的有效分离;最后采用改进的自适应阈值算法对由非低秩部分生成的显著图进行分割,从而定位出疵点区域。认为:该算法具有较高的检测率及鲁棒性,且优于现有的疵点检测方法。
A pattern of fabric defect detection method based on dual norm low-rank decomposition model was studied.The textural features of the fabric image was extracted with Log-Gabor filter.The height low-rank characteristic matrix was then built.The low-rank decomposition model based on dual dorm was adopted to divide the characteristic matrix into low-rank part and non-low-rank part.The dual norm of nuclear norm was used as the regular terms to replace the sparse constraint in the original low-rank decomposition model to minimize the relevancy between background and defect.So the effective separation of defects could be achieved.In the end,the algorithm of modified self-adaption threshold value was used to segment the saliency map generated by low-rank part.Thus,the defect area could be located.It is considered that the algorithm has higher detection rate and robustness.It is better than the existing defect detection methods.
A pattern of fabric defect detection method based on dual norm low-rank decomposition model was studied.The textural features of the fabric image was extracted with Log-Gabor filter.The height low-rank characteristic matrix was then built.The low-rank decomposition model based on dual dorm was adopted to divide the characteristic matrix into low-rank part and non-low-rank part.The dual norm of nuclear norm was used as the regular terms to replace the sparse constraint in the original low-rank decomposition model to minimize the relevancy between background and defect.So the effective separation of defects could be achieved.In the end,the algorithm of modified self-adaption threshold value was used to segment the saliency map generated by low-rank part.Thus,the defect area could be located.It is considered that the algorithm has higher detection rate and robustness.It is better than the existing defect detection methods.
引文
[1] SELVER M A,AVSAR V,A槇ZDEMIR H.Textural FabricDefectDetection Using StatisticalTexture TransformationsandGradientSearch[J].Journal of the Textile Institute,2014,105(9):998-1007.
[2] YAPI D,ALLILI M S,BAAZIZ N.Automatic Fabric Defect Detection Using Learning-Based Local Textural Distributions in the Contourlet Domain[J].IEEE Transactions on Automation Science&Engineering,2017,99:1-13.
[3] SUSAN S,SHARMA M.Automatic Texture Defect Detection Using Gaussian Mixture Entropy Modeling[J].Neurocomputing,2017,239:232-237.
[4] ZHOU J,SEMENOVICH D,SOWMYA A,et al.Dictionary Learning Framework for Fabric Defect Detection[J].Journal of the Textile Institute,2014,105(3):223-234.
[5] NGAN H Y T,PANG G K H.Novel Method for Patterned Fabric Inspection Using Bollinger Bands[J].Optical Engineering,2006,45(8):087202.
[6] NGAN H Y T,PANG G K H,YUNG S P,et al.Wavelet Based Methods on Patterned Fabric Defect Detection[J].Pattern Recognition,2005,38(4):559-576.
[7] NG M K,NGAN H Y T,YUAN X,et al.Patterned Fabric Inspection and Visualization by the Method of Image Decomposition[J].IEEE Transactions on Automation Science&Engineering,2014,11(3):943-947.
[8] CANDES E J,LI X,MA Y,et al.Robust Principal Component Analysis[J].Journal of the ACM,2009,58(3):11.
[9] WANG Siqi,FENG Xiangchu,WANG Weiwei.“Lowrank+Dual”Model based Dimensionality Reduction[J].Neurocomputing,2016,178:3-10.
[10]GOLUB G H.A Generalization of the Eckart-YoungMirsky Matrix Approximation Theorem[J].Linear Algebra&Its Applications,1987,88(3):317-327.
[11]FIELD D J.Relations between the Statistics of Natural Images and the Response Properties of Cortical Cells[J].Journal of the Optical Society of America A-optics Image Science&Vision,1987,4(12):2379-2394.
[12]WRSTON J D.KOLMOGOROV A N,FOMIN S V.Elements of the Theory of Functions and Functional Analysis,vol.i:Metric and Normed Spaces[J].Proceedings of the Edinburgh Mathematical Society,2009,11(3).
[13]RECHT B,FAZEL M,Parrilo P A,et al.Guaranteed Minimumrank Solutions of Linear Matrix Equations Via Nuclear Norm Minimization[J].SIAM Review,2010,52(3):471-501.
[14]DAUBECHIES I,DEFRISE M,DE M C.An Iterative Thresholding Algorithm for Linear Inverse Problems with a Sparsity Constraint[J].Communications on Pure&Applied Mathematics,2010,57(11):1413-1457.
[15]LIN Z,GANESH A,WRIGHT J,et al.Fast Convex Optimization Algorithms for Exact Recovery of a Corrupted Low-Rank Matrix[J].Journal of the Marine Biological Association of the UK,2009,56(3):707-722.
[16]LIN Z,CHEN M,MA Y.The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices[J].Eprint Arxiv,2010:9.
[17]LIU Z,WANG J,ZHAO Q,et al.Research on Fabric Defect Detection Algorithm based on Improved Adaptive Threshold[J].Microcomputer&Its Applications,2013.
[18]IMAMOGLU N,LIN W,FANG Y.A Saliency Detection Model Using Low-Level Features Based on Wavelet Transform[J].IEEE Transactions on Multimedia,2012,15(1):96-105.
[19]CAO J,ZHANG J,WEN Z,et al.Fabric Defect Inspection Using Prior Knowledge Guided Least Squares Regression[J].Multimedia Tools&Applications,2017,76(3):4141-4157.
[20]ZHANG D,GAO G,LI C.Fabric Defect Detection Algorithm based on Gabor Filter and Low-rank Decomposition[C]∥Eighth International Conference on Digital Image Processing.International Society for Optics and Photonics,2016:100330L.
[2] YAPI D,ALLILI M S,BAAZIZ N.Automatic Fabric Defect Detection Using Learning-Based Local Textural Distributions in the Contourlet Domain[J].IEEE Transactions on Automation Science&Engineering,2017,99:1-13.
[3] SUSAN S,SHARMA M.Automatic Texture Defect Detection Using Gaussian Mixture Entropy Modeling[J].Neurocomputing,2017,239:232-237.
[4] ZHOU J,SEMENOVICH D,SOWMYA A,et al.Dictionary Learning Framework for Fabric Defect Detection[J].Journal of the Textile Institute,2014,105(3):223-234.
[5] NGAN H Y T,PANG G K H.Novel Method for Patterned Fabric Inspection Using Bollinger Bands[J].Optical Engineering,2006,45(8):087202.
[6] NGAN H Y T,PANG G K H,YUNG S P,et al.Wavelet Based Methods on Patterned Fabric Defect Detection[J].Pattern Recognition,2005,38(4):559-576.
[7] NG M K,NGAN H Y T,YUAN X,et al.Patterned Fabric Inspection and Visualization by the Method of Image Decomposition[J].IEEE Transactions on Automation Science&Engineering,2014,11(3):943-947.
[8] CANDES E J,LI X,MA Y,et al.Robust Principal Component Analysis[J].Journal of the ACM,2009,58(3):11.
[9] WANG Siqi,FENG Xiangchu,WANG Weiwei.“Lowrank+Dual”Model based Dimensionality Reduction[J].Neurocomputing,2016,178:3-10.
[10]GOLUB G H.A Generalization of the Eckart-YoungMirsky Matrix Approximation Theorem[J].Linear Algebra&Its Applications,1987,88(3):317-327.
[11]FIELD D J.Relations between the Statistics of Natural Images and the Response Properties of Cortical Cells[J].Journal of the Optical Society of America A-optics Image Science&Vision,1987,4(12):2379-2394.
[12]WRSTON J D.KOLMOGOROV A N,FOMIN S V.Elements of the Theory of Functions and Functional Analysis,vol.i:Metric and Normed Spaces[J].Proceedings of the Edinburgh Mathematical Society,2009,11(3).
[13]RECHT B,FAZEL M,Parrilo P A,et al.Guaranteed Minimumrank Solutions of Linear Matrix Equations Via Nuclear Norm Minimization[J].SIAM Review,2010,52(3):471-501.
[14]DAUBECHIES I,DEFRISE M,DE M C.An Iterative Thresholding Algorithm for Linear Inverse Problems with a Sparsity Constraint[J].Communications on Pure&Applied Mathematics,2010,57(11):1413-1457.
[15]LIN Z,GANESH A,WRIGHT J,et al.Fast Convex Optimization Algorithms for Exact Recovery of a Corrupted Low-Rank Matrix[J].Journal of the Marine Biological Association of the UK,2009,56(3):707-722.
[16]LIN Z,CHEN M,MA Y.The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices[J].Eprint Arxiv,2010:9.
[17]LIU Z,WANG J,ZHAO Q,et al.Research on Fabric Defect Detection Algorithm based on Improved Adaptive Threshold[J].Microcomputer&Its Applications,2013.
[18]IMAMOGLU N,LIN W,FANG Y.A Saliency Detection Model Using Low-Level Features Based on Wavelet Transform[J].IEEE Transactions on Multimedia,2012,15(1):96-105.
[19]CAO J,ZHANG J,WEN Z,et al.Fabric Defect Inspection Using Prior Knowledge Guided Least Squares Regression[J].Multimedia Tools&Applications,2017,76(3):4141-4157.
[20]ZHANG D,GAO G,LI C.Fabric Defect Detection Algorithm based on Gabor Filter and Low-rank Decomposition[C]∥Eighth International Conference on Digital Image Processing.International Society for Optics and Photonics,2016:100330L.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |