布匹瑕疵识别中的关键技术研究
|
摘要
布匹的质量控制在纺织品行业中起着非常关键的作用，而布匹瑕疵是影响布匹质量控制的重要因素。目前，布匹瑕疵识别主要依靠传统的人工离线完成，存在工作量大、检测速度慢且准确度低等问题。随着计算机和模式识别技术的快速发展，布匹瑕疵自动识别是纺织工业生产中质量监控的必然趋势。当前，布匹瑕疵自动识别的研究虽然已经取得了一定的成果，但是由于采集图像受光照变化、噪声等影响，以及瑕疵具有类别较多等问题，使得布匹瑕疵识别仍然是一个具有挑战性的研究课题。本文将重点放在瑕疵识别中检测和分类等关键算法的研究上，将近年来模式识别领域的前沿理论引入布匹瑕疵识别中，针对10类常见瑕疵的识别问题进行深入研究，论文取得了以下主要研究成果：
1．针对瑕疵类别较多，以及单一方法只对某些类别瑕疵有效的问题，设计了一种小波变换多尺度积和数学形态学的瑕疵检测算法。首先采用非下采样小波变换把瑕疵图像分解成多个子图，然后对低频近似子图进行数学形态学运算，得到瑕疵的形状特征，对高频子图采用小波多尺度积方法，可以抑制噪声的同时增强瑕疵的边缘特征，最后用加权平均法融合得到检测结果。实验从主观和客观两方面进行评价，与经典的Gabor和小波变换算法比较，该算法能快速有效地实现布匹瑕疵检测，综合性能优于对比算法。
2．利用非下采样Contourlet变换（Nonsubsampled Contourlet Transform，NSCT）的分解系数能较好地描述瑕疵图像轮廓的特性，提出了两种基于NSCT的布匹瑕疵检测算法。（1）提出一种基于NSCT标准差的检测算法。通过方差代价函数得到最优子带，由于瑕疵和非瑕疵区域系数差别较小，阈值法很难进行瑕疵分割，采用标准差法可以较好地处理这个问题。该算法对瑕疵定位较准且计算量小。（2）提出一种基于NSCT的高斯混合模型（Gaussian Mixture Model，GMM）的检测算法。该算法通过代价函数法获取最优子带，然后实时地估计瑕疵和非瑕疵区域的GMM参数，避免了对每一类瑕疵的估计，最后根据最大后验概率进行瑕疵分割。该算法不需要瑕疵的先验知识，与几种对比算法相比性能得到了较大的提升。
3．针对布匹瑕疵种类多，相似类瑕疵不易区分的问题，提出一种基于改进GMM参数估计的布匹瑕疵分类算法。对变换域的子带提取全局统计特征，实验表明全局特征在类内具有稳定性；针对局部二值模式（Local Binary Pattern，LBP）和灰度共生矩阵（Gray Level Co-occurrence Matrix，GLCM）各自的优势，提出采用两者融合的局部特征提取方法，该特征反映了瑕疵的细节特性且维数较小。然后引入最小误分率函数，提出一种联合估计GMM参数的方法，最后通过贝叶斯分类器进行分类。实验结果表明，混合特征能更好地表述瑕疵特征，相对于传统分类方法，本文算法得到更高的分类正确率，而且样本变化对性能影响较小。
4．基于过完备字典的稀疏表示是一种新兴的信号表示理论。针对过完备字典可以有效地捕捉图像各种特征的优势，以及已有瑕疵分类算法对分割效果的依赖性，提出了基于字典学习的稀疏表示布匹瑕疵识别算法。通过判别字典学习方法得到瑕疵样本的过完备字典，该字典能更好地捕捉瑕疵图像的鲁棒特征。利用Gabor虚部变换快速得到瑕疵粗定位以及粗分类，避免了分类算法在整个图像上分块运算。接着采用追踪算法得到瑕疵块在过完备字典上的稀疏表示，并用线性分类器进行分类。最后将子块类别信息统计分析，输出识别结果。实验结果表明，本文所提算法不仅提升了分类性能且对误分子块具有纠错能力，同时提高了瑕疵识别的稳定性和准确性。
Fabric quality control plays a very crucial role in the textile industry, and fabricdefect is an important factor affecting the quality of fabric. Currently, fabric defectrecognition is mainly by the traditional human offline inspection, which is in heavylabor intensive, slow detection speed and low detection accuracy. As the rapiddevelopment of computer technology and pattern recognition technology, fabric defectautomatic recognition is an inevitable trend in production quality control of the textileindustry. At present, research of fabric defect automatic recognition has made someachievements. But as the problems of image acquisition affect by light change and noise,and the defects have more categories, the fabric defect recognition is still a challengingresearch topic. In this thesis, we mainly investigate the defect detection andclassification algorithms. We introduce the front theories of pattern recognition in recentyears into fabric defect recognition, and further study the recognitions for10categoriescommon defects. The main contributions of this dissertation are as follows.
1. According to the problems that the number of fabric defect category is large anda unity method is only effective for some types of defects, a novel fabric defectdetection algorithm is studied which combines wavelet multi-scale product andmathematical morphology. First, defect image is decomposed into sub-images using thenonsubsampled wavelet transform. Then, defect shape features are obtained bymathematical morphology operations over the low frequency sub-image. Waveletmulti-scale products methods are adopted to suppress the noise and enhance defect edgelinear features through the high frequency sub-images. Finally, the weighted averagefusion algorithm is used to get the result. The experiments are from both subjective andobjective evaluation. Compared with the classical Gabor and wavelet transformalgorithms, the proposed algorithm is fast and effective for fabric defect detection, andthe comprehensive performance of the algorithm is superior to contrast algorithms.
2. Considering the advantage of decomposition coefficients in NonsubsampledContourlet transform (NSCT) of fabric images better describing the contourcharacteristics, two novel algorithms for detection of fabric defect images based onNSCT, are presented.(1) A fabric defect detection algorithm based on the standarddeviation of NSCT subbands is proposed. The optimal sub-band of NSCT is obtained bythe variance cost function. As difference of the coefficients' between defect andnon-defective regions in the sub-band is smaller, the segmentation threshold is difficult to obtain. The standard deviation method can effectively solve this problem to getaccurate results. The algorithm is more accurate positioning of the defect and is with thesmall amount of calculation.(2) A fabric defect detection approach is presented with theGaussian Mixture Model (GMM) based on NSCT. The optimal sub-band of NSCT isacquired by the cost function method. Then, parameters of defect and non-defectiveimages are timely estimated separately by GMM, which availably avoids evaluatingeach defect. Finally, segmentation of the defect is obtained by the maximum posteriorprobability. The algorithm does not require prior knowledge of defect images, and hasgreatly improved the performance comparing with other algorithms.
3. To solve the problems that the kinds of fabric defects are many and similar kindsamong are difficult to distinguish, a fabric defect classification algorithm based on theimproved GMM parameters estimation method is proposed. The global statisticalfeature is extracted from the transform sub-bands, and the experiment shows that globalfeature is stability within the class. For the advantages of Local Binary Pattern (LBP)and Gray Level Co-occurrence Matrix (GLCM), an integration feature extractionmethod of the two methods is adopted. The feature reflects the minutiae feature of thedefect and is in lower feature dimension. Later, the minimum misclassification functionis introduced to joint estimation the GMM parameters. Finally, classification is realizedby Bayesian classifier. The experimental results indicate that the hybrid features can bebetter described characteristics of the defects. Compared with the traditionalclassification methods, this algorithm obtains the higher classification accuracy, and isless impacted on the performance as the change of the sample number.
4. Sparse representation based on the over-complete dictionary is a further signalrepresentation theory. As the over-complete dictionary can be effectively captured thecharacteristics of the images, and the existing defect classification algorithms rely onthe defect segmentation result, a fabric defect recognition algorithm via dictionarylearning for sparse representation is proposed. The over-complete dictionary is obtainedby the discriminative dictionary learning method, which can better capture the defectimage’s robust feature. The imaginary Gabor function is used to get the coarse positionand the rough classification of the defect, which avoids the block operations on thewhole image. Then, sparse representation based on the over-complete dictionary isobtained through the pursuit algorithm, and the classification is realized by a linearclassifier. Finally, to count and analyze the sub-block class classification information,the recognition result is obtained. The experimental results show that the proposed algorithm not only improves the classification performance but also has the errorcorrection capability for the misclassification blocks. The sparse representation methodhas improved the stability and accuracy for defects recognition.
1．针对瑕疵类别较多，以及单一方法只对某些类别瑕疵有效的问题，设计了一种小波变换多尺度积和数学形态学的瑕疵检测算法。首先采用非下采样小波变换把瑕疵图像分解成多个子图，然后对低频近似子图进行数学形态学运算，得到瑕疵的形状特征，对高频子图采用小波多尺度积方法，可以抑制噪声的同时增强瑕疵的边缘特征，最后用加权平均法融合得到检测结果。实验从主观和客观两方面进行评价，与经典的Gabor和小波变换算法比较，该算法能快速有效地实现布匹瑕疵检测，综合性能优于对比算法。
2．利用非下采样Contourlet变换（Nonsubsampled Contourlet Transform，NSCT）的分解系数能较好地描述瑕疵图像轮廓的特性，提出了两种基于NSCT的布匹瑕疵检测算法。（1）提出一种基于NSCT标准差的检测算法。通过方差代价函数得到最优子带，由于瑕疵和非瑕疵区域系数差别较小，阈值法很难进行瑕疵分割，采用标准差法可以较好地处理这个问题。该算法对瑕疵定位较准且计算量小。（2）提出一种基于NSCT的高斯混合模型（Gaussian Mixture Model，GMM）的检测算法。该算法通过代价函数法获取最优子带，然后实时地估计瑕疵和非瑕疵区域的GMM参数，避免了对每一类瑕疵的估计，最后根据最大后验概率进行瑕疵分割。该算法不需要瑕疵的先验知识，与几种对比算法相比性能得到了较大的提升。
3．针对布匹瑕疵种类多，相似类瑕疵不易区分的问题，提出一种基于改进GMM参数估计的布匹瑕疵分类算法。对变换域的子带提取全局统计特征，实验表明全局特征在类内具有稳定性；针对局部二值模式（Local Binary Pattern，LBP）和灰度共生矩阵（Gray Level Co-occurrence Matrix，GLCM）各自的优势，提出采用两者融合的局部特征提取方法，该特征反映了瑕疵的细节特性且维数较小。然后引入最小误分率函数，提出一种联合估计GMM参数的方法，最后通过贝叶斯分类器进行分类。实验结果表明，混合特征能更好地表述瑕疵特征，相对于传统分类方法，本文算法得到更高的分类正确率，而且样本变化对性能影响较小。
4．基于过完备字典的稀疏表示是一种新兴的信号表示理论。针对过完备字典可以有效地捕捉图像各种特征的优势，以及已有瑕疵分类算法对分割效果的依赖性，提出了基于字典学习的稀疏表示布匹瑕疵识别算法。通过判别字典学习方法得到瑕疵样本的过完备字典，该字典能更好地捕捉瑕疵图像的鲁棒特征。利用Gabor虚部变换快速得到瑕疵粗定位以及粗分类，避免了分类算法在整个图像上分块运算。接着采用追踪算法得到瑕疵块在过完备字典上的稀疏表示，并用线性分类器进行分类。最后将子块类别信息统计分析，输出识别结果。实验结果表明，本文所提算法不仅提升了分类性能且对误分子块具有纠错能力，同时提高了瑕疵识别的稳定性和准确性。
Fabric quality control plays a very crucial role in the textile industry, and fabricdefect is an important factor affecting the quality of fabric. Currently, fabric defectrecognition is mainly by the traditional human offline inspection, which is in heavylabor intensive, slow detection speed and low detection accuracy. As the rapiddevelopment of computer technology and pattern recognition technology, fabric defectautomatic recognition is an inevitable trend in production quality control of the textileindustry. At present, research of fabric defect automatic recognition has made someachievements. But as the problems of image acquisition affect by light change and noise,and the defects have more categories, the fabric defect recognition is still a challengingresearch topic. In this thesis, we mainly investigate the defect detection andclassification algorithms. We introduce the front theories of pattern recognition in recentyears into fabric defect recognition, and further study the recognitions for10categoriescommon defects. The main contributions of this dissertation are as follows.
1. According to the problems that the number of fabric defect category is large anda unity method is only effective for some types of defects, a novel fabric defectdetection algorithm is studied which combines wavelet multi-scale product andmathematical morphology. First, defect image is decomposed into sub-images using thenonsubsampled wavelet transform. Then, defect shape features are obtained bymathematical morphology operations over the low frequency sub-image. Waveletmulti-scale products methods are adopted to suppress the noise and enhance defect edgelinear features through the high frequency sub-images. Finally, the weighted averagefusion algorithm is used to get the result. The experiments are from both subjective andobjective evaluation. Compared with the classical Gabor and wavelet transformalgorithms, the proposed algorithm is fast and effective for fabric defect detection, andthe comprehensive performance of the algorithm is superior to contrast algorithms.
2. Considering the advantage of decomposition coefficients in NonsubsampledContourlet transform (NSCT) of fabric images better describing the contourcharacteristics, two novel algorithms for detection of fabric defect images based onNSCT, are presented.(1) A fabric defect detection algorithm based on the standarddeviation of NSCT subbands is proposed. The optimal sub-band of NSCT is obtained bythe variance cost function. As difference of the coefficients' between defect andnon-defective regions in the sub-band is smaller, the segmentation threshold is difficult to obtain. The standard deviation method can effectively solve this problem to getaccurate results. The algorithm is more accurate positioning of the defect and is with thesmall amount of calculation.(2) A fabric defect detection approach is presented with theGaussian Mixture Model (GMM) based on NSCT. The optimal sub-band of NSCT isacquired by the cost function method. Then, parameters of defect and non-defectiveimages are timely estimated separately by GMM, which availably avoids evaluatingeach defect. Finally, segmentation of the defect is obtained by the maximum posteriorprobability. The algorithm does not require prior knowledge of defect images, and hasgreatly improved the performance comparing with other algorithms.
3. To solve the problems that the kinds of fabric defects are many and similar kindsamong are difficult to distinguish, a fabric defect classification algorithm based on theimproved GMM parameters estimation method is proposed. The global statisticalfeature is extracted from the transform sub-bands, and the experiment shows that globalfeature is stability within the class. For the advantages of Local Binary Pattern (LBP)and Gray Level Co-occurrence Matrix (GLCM), an integration feature extractionmethod of the two methods is adopted. The feature reflects the minutiae feature of thedefect and is in lower feature dimension. Later, the minimum misclassification functionis introduced to joint estimation the GMM parameters. Finally, classification is realizedby Bayesian classifier. The experimental results indicate that the hybrid features can bebetter described characteristics of the defects. Compared with the traditionalclassification methods, this algorithm obtains the higher classification accuracy, and isless impacted on the performance as the change of the sample number.
4. Sparse representation based on the over-complete dictionary is a further signalrepresentation theory. As the over-complete dictionary can be effectively captured thecharacteristics of the images, and the existing defect classification algorithms rely onthe defect segmentation result, a fabric defect recognition algorithm via dictionarylearning for sparse representation is proposed. The over-complete dictionary is obtainedby the discriminative dictionary learning method, which can better capture the defectimage’s robust feature. The imaginary Gabor function is used to get the coarse positionand the rough classification of the defect, which avoids the block operations on thewhole image. Then, sparse representation based on the over-complete dictionary isobtained through the pursuit algorithm, and the classification is realized by a linearclassifier. Finally, to count and analyze the sub-block class classification information,the recognition result is obtained. The experimental results show that the proposed algorithm not only improves the classification performance but also has the errorcorrection capability for the misclassification blocks. The sparse representation methodhas improved the stability and accuracy for defects recognition.
引文
[1] Kumar A. Computer-Vision-Based Fabric Defect Detection: A Survey[J]. IEEETransactions on Industrial Electronics.2008, Vol.55(1):348-363.
[2]邹超.布匹疵点在线检测系统研究[D].华中科技大学博士学位论文,2009.
[3]毕明德.基于机器视觉的布匹疵点检测系统[D].华中科技大学博士学位论文,2012.
[4] Xie Xianghua. A Review of Recent Advances in Surface Defect Detection usingTexture analysis Techniques[J]. Electronic Letters on Computer Vision and ImageAnalysis.2008, Vol.7(3):1-22.
[5] Tsai D M, Chang C C, Chao S M. Micro-crack Inspection in HeterogeneouslyTextured Solar Wafers Using Anisotropic Diffusion[J]. Image and VisionComputing.2010, Vol.28(3):491-501.
[6] Pan Z, Chen L, Li W,et al. A Novel Defect Inspection Method for SemiconductorWafer Based on Magneto-Optic Imaging[J]. Journal of Low Temperature Physics.2013, Vol.170(5-6):436-441.
[7] Hocenski Z, Keser T, Baumgartner A. A Simple and Efficient Method forCeramic Tile Surface Defects Detection[C]. IEEE International Symposium onIndustrial Electronics. IEEE,2007:1606-1611.
[8]李立轻.基于计算机视觉的织物疵点自动检测研究[D].东华大学博士学位论文,2003.
[9] Dockery A. Automated Fabric Inspection: Assessing The Current State of The Art.http://www.techexchange. com.2001.
[10] GB/T17759-2009.本色布布面疵点检验方法[S].
[11] Henry Y T N, Grantham K H P, Nelson H C Y. Automated Fabric DefectDetection－A review[J]. Image and Vision Computing.2011, Vol.29(7):442-458.
[12] Mandelbrot B B. The fractal Geometry of Nature[M]. Macmillan,1983.
[13] Otsu N. A Threshold Selection Method from Gray-Level Histograms[J].Automatica.1975, Vol.11(285-296):23-27.
[14] Serra J. Image Analysis and Mathematical Morphology[M]. London.: AcademicPress,1982.
[15] Soh L K, Tsatsoulis C. Texture Analysis of SAR Sea Ice Imagery Using GrayLevel Co-Occurrence Matrices[J]. IEEE Transactions on Geoscience and RemoteSensing.1999, Vol.37(2):780-795.
[16] Hagan M T, Demuth H B, Beale M H. Neural Network Design[M]. Pws Pub.Boston,1996.
[17] Conci A, Proenca C B. A Fractal Image Analysis System for Fabric InspectionBased on a Box-Counting Method[J]. Computer Networks&ISDN Systems.1998, Vol.30(20):1887-1895.
[18]步红刚,黄秀宝,汪军.基于多分形特征参数的织物瑕疵检测[J].计算机工程与应用.2007, Vol.36:233-237.
[19] Bu H G, Wang J, Huang X B. Fabric Defect Detection Based on Multiple FractalFeatures and Support Vector Data Description[J]. Engineering Applications ofArtificial Intelligence.2009, Vol.22(2):224-235.
[20] Zhang Y F, Bresee R R. Fabric Defect Detection and Classification using ImageAnalysis[J]. Textile Research Journal.1995, Vol.65(1):1-9.
[21] Thomas T, Cattoen M. Automatic Inspection of Simply Patterned Material in TheTextile Industry[J]. Machine Vision Applications in Industrial Inspection.1994,Vol.2183:2-12.
[22] Haralick Robert M, Sternberg Stanley R, Zhuang Xinhua. Image analysis usingmathematical morphology[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence.1987, Vol.(4):532-550.
[23] Dougherty E R. An Introduction to Morphological Image Processing[M]. SPIEOptical Engineering Press,1992.
[24] Mallick-Goswami B, Datta A K. Detecting Defects in Fabric with Laser-BasedMorphological Image Processing[J]. Textile Research Journal.2000, Vol.70(9):758-762.
[25] Chetverikov D, Henbury A. Finding Defects in Texture using Regularity andLocal Orientation[J]. Pattern Recognition.2002, Vol.35(10):2165-2180.
[26] Mak K L, Peng P, Yiu K F C. Fabric Defect Detection Using MorphologicalFilters[J]. Image and Vision Computing.2009, Vol.27(10):1585-1592.
[27] Haralick R M, Shanmugam K, Dinstein I. Textural Features for ImageClassification[J]. IEEE Transactions on Systems,Man,and Cybernetics.1973, Vol.3(6):610-621.
[28] Tsai I, Lin C, Lin J. Applying an Artificial Neural Network to Pattern Recognitionin Fabric Defects[J]. Textile Research Journal.1995, Vol.65(3):123-130.
[29] Bodnarova A, Williams J A, Bennamoun M, et al. Optimal Textural Features forFlaw Detection in Textile Materials[C]. IEEE Conference on Speech and ImageTechnologies for Computing and Telecommunications.1997, Vol.1:307-310.
[30] Latif-Amet A, Ertuzun A, Ercil A. An Efficient Method for Texture DefectDetection: Subband Domain Co-Occurrence Matrices[J]. Image and VisionComputing.2000, Vol.18(6-7):543-553.
[31]邹超，朱德森，肖力.基于类别共生矩阵的纹理疵点检测方法[J].华中科技大学学报（自然科学版）.2006, Vol.34(6):25-28.
[32]邹超，朱德森，肖力.基于模糊类别共生矩阵的纹理疵点检测方法[J].中国图象图形学报.2007, Vol.12(1):92-97.
[33] Jain A K, Duin R P W, Mao J. Statistical Pattern Recognition a Review[J]. IEEETransactions on Pattern Analysis and Machine Intelligence.2000, Vol.22(1):4-37.
[34] Kumar A, Shen H C. Texture Inspection for Defects using Neural Networks andSupport Vector Machines[C]. International Conference on Image Processing.2002, Vol.3:353-356.
[35] Kumar A. Neural Network Based Detection of Local Textile Defects[J]. PatternRecognition.2003, Vol.36(7):1645-1659.
[36]宋寅卯,袁端磊,卢易枫,乔桂花.基于最优PCNN模型的织物疵点自动检测[J].仪器仪表学报.2008, Vol.29(4):888-891.
[37] Tolba A S. Fast Defect Detection in Homogeneous Flat Surface Products[J].Expert Systems with Applications.2011, Vol.38(10):12339-12347.
[38] TILDA, Textile Defect Image Database. Germany: University of Freiburg.1996.
[39] Bracewell R N, Bracewell R N. The Fourier Transform and Its Applications[M].McGraw-Hill New York,1986.
[40] Gabor D. Theory of Communication[J]. Journal of the Institution of ElectricalEngineers.1946, Vol.93:429-457.
[41] Mallat S G. A Theory for Multiresolution Signal Decomposition: The WaveletRepresentation[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence.1989, Vol.11(7):674-693.
[42] Cunha A L, Zhou Jianping, Do M N. The Nonsubsampled Contourlet Transform:Theory, Design,and Application[J]. IEEE Transactions on Image Processing.2006, Vol.15(10):3089-3101.
[43]焦李成，侯彪，王爽，等.图像多尺度几何分析理论与应用[M].2008.
[44] Mead D C, Kasdan H L, Dorrity J L.Method for Automatic Fabric Inspection[P].1978. U.S. Patent4124300.
[45] Ciamberlini C, Francini F, Longobardi G. Defect Detection in Textured Materialsby Optical Filtering with Structured Detectors and Self-Adaptable Masks[J].Optical Engineering.1996, Vol.35(3):835-844.
[46] Chan Chi-Ho, Pang G K H. Fabric Defect Detection by Fourier Analysis[J]. IEEETransactions on Industry Applications.2000, Vol.36(5):1267-1276.
[47] Tsai D M, Hsieh C Y. Automated Surface Inspection for Directional Textures[J].Image and Vision Computing.1999, Vol.18(1):49-62.
[48] Bodnarova A, Bennamoun M, Latham S J. A Constrained MinimisationApproach to Optimise Gabor Filters for Detecting Flaws in Woven Textiles[C].International Conference on Acoustics, Speech and Signal Process.2000, Vol.6:3606-3609.
[49] Bodnarova A, Bennamoun M, Latham S J. Textile Flaw Detection using OptimalGabor Filters[C].2000, Vol.4:799-802.
[50] Bodnarova A, Bennamoun A, Latham S J. Optimal Gabor filters textile flawdetection[J]. Pattern Recognition.2002, Vol.35:2973-2991.
[51] Kumar A, Pang G K H. Defect Detection in Textured Materials Using GaborFilters[C]. IEEE Industry Applications Conference. Rome,Italy.2000, Vol.2:1041-1047.
[52] Kumar A, Pang G K H. Defect Detection in Textured Materials Using GaborFilters[J]. IEEE Transactions on Industry Applications.2002, Vol.38(2):425-440.
[53] Kumar A, Pang G K H. Fabric Defect Segmentation using Multichannel BlobDetectors[J]. Optical Engineering.2000, Vol.39(12):3176-3190.
[54]肖乐，朱玉文，丁丽宏，等.基于Gabor滤波器的布匹瑕疵自动检测方法[J].北京理工大学学报.2002, Vol.22(6):718-721.
[55] Zhang Yu, Lu Zhaoyang, Li Jing. Fabric Defect Detection and ClassificationUsing Gabor Filters and Gaussian Mixture Model[C]. The9th Asian Conferenceon Computer Vision–ACCV2009. Xi'an, China. Springer Berlin Heidelberg,2010, Vol.5995:635-644.
[56] Mak K L, Peng P. An Automated Inspection System for Textile Fabrics Based onGabor Filters[J]. Robotics and Computer-Integrated Manufacturing.2008, Vol.24(3):359-369.
[57] Sari-Sarraf H, Goddard J S. Vision Systems for On-Loom Fabric Inspection[J].IEEE Transactions ON Industry Application.1999, Vol.35(6):1252-1259.
[58] Dorrity J L, Vachtsevanos G. On-Line Defect Detection for Weaving Systems[C].IEEE Annual Technical Conference on Textile, Fiber and Film Industry. IEEE,1996:1-6.
[59] Jasper W J, Garnier S J, Potapalli H. Texture Characterization and DefectDetection using Adaptive Wavelets[J]. Optical Engineering.1996, Vol.35(11):3140-3149.
[60] Zeng PeiFeng, Hirata Tomio On-Loom Fabric Inspection using Multi-ScaleDifferentiation Filtering[C]. IEEE Industry Application Conference.2002, Vol.:320-326.
[61] Zeng PeiFeng, Hirata Tomio Fast Defect Detection in Cloths with B-splines[J].Iranian Journal of Electrical and Computer Engineering.2002, Vol.1:29-34.
[62] Yang XueZhi, Pang G K H, Yung N H C. Fabric Defect Detection using AdaptiveWavelet[C]. IEEE International Conference on Acoustics, Speech, and SignalProcessing(ICASSP).2001, Vol.6:3697-3700.
[63] Yang Xuezhi, Pang G K H, Yung N H C. Discriminative Fabric Defect Detectionusing Adaptive Wavelets[J]. Society of Photo-Optical Instrumentation Engineers.2002, Vol.41(12):3116-3126.
[64] Yang XueZhi, Pang G K H, Yung N H C. Discriminative Training Approaches toFabric Defect Classification Based on Wavelet Transform[J]. Pattern Recognition.2004, Vol.37(5):889-899.
[65] Tsai D M, Hsiao B. Automatic Surface Inspection using WaveletReconstruction[J]. Pattern Recognition.2001, Vol.34(6):1285-1305.
[66] Guan Shengqi, Yuan Jianchang, Ma Ke. Fabric Defect Detection Based onWavelet Reconstruction[C]. International Conference on Multimedia Technology(ICMT).2011:3520-3523.
[67] Serdaroglu A, Ertuzun A, Ercil A. Defect Detection in Textile Fabric Imagesusing Wavelet Transforms and Independent Component Analysis[J]. PatternRecognition and Image Analysis.2006, Vol.16(1):61-64.
[68] Han Yanfang, Shi Pengfei. An Adaptive Level-selecting Wavelet Transform forTexture Defect Detection[J]. Image and Vision Computing.2007, Vol.25(8):1239-1248.
[69] Jiang HuiYu, Dong Min, Li Wei. Detection of Fabric Defect Based on OptimalTree Structure of Wavelet Decomposition[C]. International Symposium onIntelligent Ubiquitous Computing and Education. IEEE,2009, Vol.:210-213.
[70] Guan Shengqi, Shi Xiuhua, Cui Haiying,et al. Fabric Defect Detection Based onWavelet Characteristics[C]. Pacific-Asia Workshop on ComputationalIntelligence and Industrial Application, PACIIA'08. IEEE,2008, Vol.1:366-370.
[71] Ngan H Y T, Pang G K H, Yung S P. Wavelet based methods on patterned fabricdefect detection[J]. Pattern Recognition.2005, Vol.38(4):559-576.
[72]焦李成，谭山.图像的多尺度几何分析:回顾和展望[J].电子学报.2003, Vol.31(12):1975-1981.
[73]潘泓，李晓兵，金立左，等.基于多尺度几何分析的目标描述和识别[J].红外与毫米波学报.2011, Vol.30(1):85-90.
[74] Candes E J. Ridgelets:Theory and Applications[D]. USA:Department ofStatistics,Stanford University,1998.
[75] Candes E J, Donoho D L. Curvelets[R], USA: Department of Statistics, StanfordUniversity,1999.
[76] Meyer F G, Coifman R R. Brushlets: A Tool for Directional Image Analysis andImage Compression[J]. Applied and Computational Harmonic Analysis.1997,Vol.5:147-187.
[77] Do M N, Vetterli M. Contourlets[J]. Studies in Computational Mathematics.2003,Vol.10:83-105.
[78] Ai Yonghao, Xu Ke. Surface Detection of Continuous Casting Slabs Based onCurvelet Transform and Kernel Locality Preserving Projections[J]. InternationalJournal of Iron and Steel Research.2013, Vol.20(5):80-86.
[79] Zhang Yan, Li Tao, Li Qingling. Defect Detection for Tire Laser ShearographyImage Using Curvelet Transform Based Edge Detector[J]. Optics&LaserTechnology.2013, Vol.47:64-71.
[80] Ghorai S, Singh R, Gangadaran M. Wavelet Versus Contourlet Features forAutomatic Defect Detection on Hot Rolled Steel Sheet[C].2012ThirdInternational Conference on Emerging Applications of Information Technology(EAIT).2012:149-152.
[81] Kindermann R, Snell J L. Markov Random Fields and Their Applications[M].American Mathematical Society Providence, RI,1980.
[82] Akaike H. Fitting autoregressive models for prediction[J]. Annals of the instituteof Statistical Mathematics.1969, Vol.21(1):243-247.
[83] Andrey P, Tarroux P. Unsupervised Segmentation of Markov Random FieldModeled Textured Images Using Selectionist Relaxation[J]. IEEE Transactionson Pattern Analysis and Machine Intelligence.1998, Vol.20(3):252-262.
[84] Feng Wei, Jia Jiaya, Liu Zhiqiang. Self-Validated Labeling of Markov RandomFields for Image Segmentation[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence.2010, Vol.32(10):1871-1887.
[85] Deng Huawu, Clausi D A. Gaussian MRF Rotation-Invariant Features for ImageClassification[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence.2004, Vol.26(7):951-955.
[86] Yamazaki T, Gingras D. Image Classification Using Spectral and SpatialInformation Based on MRF Models[J]. IEEE Transactions on Image Processing.1995, Vol.4(9):1333-1339.
[87] Attali S F, Cohen F S. Surface Inspection Based on Stochastic Modeling[C].SPIE Proceedings.1986, Vol.665:46-52.
[88] Cohen F S, Fan Z, Attali S. Automated Inspection of Textile Fabrics UsingTextural Models[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence.1991, Vol.8(13):803-808.
[89] Ozdemir S, Ercil A. Markov Random Fields and Karhunen-Loeve Transforms forDefect Inspection of Textile Products[C]. IEEE Conference on EmergingTechnologies and Factory Automation.1996,Vol.2:697-703.
[90] Limas S A F. Segmentation of Natural Images Based on Multiresolution PyramidsLinking of the Parameters of an Autoregressive Rotation Invariant ModelApplication to Leather Defects Detection[C]. International Conference on PatternRecognition, Conference C: Image, Speech and Signal Analysis,11th IAPR1992:41-44.
[91] Hajimowlana S H, Muscedere R, Jullien G A,et al.1D Autoregressive Modelingfor Defect Detection in Web Inspection Systems[C]. Midwest Symposium onCircuits and Systems,1998:318-321.
[92] Bu H G, Huang X B, Wang J, et al. Detection of Fabric Defects byAuto-Regressive Spectral Analysis and Support Vector Data Description[J].Textile Research Journal.2010, Vol.80(7):579-589.
[93] Xuezhi, Yang. Discriminative Fabric Defect Detection and Classification UsingAdaptive Wavelet[D].香港大学博士学位论文,2003.
[94]李晶皎，王爱侠，张广渊，等译.模式识别（第三版）[M].电子工业出版社,2008.
[95] Hargrove L J, Li G, Englehart K B,et al. Principal Components AnalysisPreprocessing for Improved Classification Accuracies inPattern-Recognition-Based Myoelectric Control[J]. IEEE Transactions onBiomedical Engineering.2009, Vol.56(5):1407-1414.
[96] Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning[M]. NewYork: Springer-Verlag,2001.
[97] Duda Richard O, Hart Peter E, Stork David G. Pattern Classification[M]. JohnWiley&Sons,2012.
[98] He X F, Niyogi P. Locality Preserving Projections[C]. Advances in NeuralInformation Processing Systems. Vancouver: MIT Press,2003:153-162.
[99] Stojanovic R, Mitropulos P, Koulamas C,et al. Automated Detection and NeuralClassification of Local Defects in Textile Web[C]. Seventh InternationalConference on Image Processing and Its Applications. IET,1999,Vol.2:647-651.
[100] Mitropoulos P, Koulamas C, Stojanovic R D,et al. Real-time Vision System forDefect Detection and Neural Classification of Web Textile Fabric[C]. ElectronicImaging'99. International Society for Optics and Photonics,1999:59-69.
[101] Kwak C, Ventura J A, Tofang-Sazi K. A Neural Network Approach for DefectIdentification and Classification on Leather Fabric[J]. Journal of IntelligentManufacturing.2000, Vol.11(5):485-499.
[102]卿湘运，段红，魏俊民，等.一种新的基于小波分析与神经网络的织物疵点检测与识别方法[J].仪器仪表学报.2005, Vol.26(6):618-622.
[103] Elragal H M. Neuro-Fuzzy Fabric Defect Detection and Classification forKnitting Machine[C]. Proceedings of the Twenty Third National Radio ScienceConference,NRSC2006, IEEE,2006:1-8.
[104] Kuo C F J, Lee C J,Tsai C C. Using a Neural Network to Identify Fabric Defectsin Dynamic Cloth Inspection[J]. Textile Research Journal.2003, Vol.73(3):238-244.
[105] Stojanovic R, Mitropulos P, Koulamas C,et al. Real-time Vision-Based Systemfor Textile Fabric Inspection[J]. Real-Time Imaging.2001, Vol.7(6):507-518.
[106] Hung C C, Chen I C. Neural-Fuzzy Classification for Fabric Defects[J]. TextileResearch Journal.2001, Vol.71(3):220-224.
[107] Pang G K H, Yang X, Yung N. Fabric Defect Classification Using WaveletFrames and Minimum Classification Error-Based Neural Network[C]. The9thIEEE Conference on Mechatronics and Machine Vision in Practice. Chiang Mai,Thailand.2002:77-85.
[108] Kuo C, Lee C. A Back-Propagation Neural Network for Recognizing FabricDefects[J]. Textile Research Journal.2003, Vol.73(2):147-151.
[109] Islam A, Akhter S, Mursalin T E. Automated Textile Defect Recognition SystemUsing Computer Vision and Artificial Neural Networks[C]. Proceedings of WorldAcademy Of Science, Engineering and Technology.2006,Vol.13:1-6.
[110] Liu Su-Yi, Zhang Le-Duo, Wang Qian,et al. BP Neural Network in Classificationof Fabric Defect Based on Particle Swarm Optimization[C]. InternationalConference on Wavelet Analysis and Pattern Recognition, ICWAPR'08. IEEE,2008, Vol.1:216-220.
[111] Zhang Y H, Yuen C W M, Wong W K. A New Intelligent Fabric Defect Detectionand Classification System Based on Gabor Filter and Modified Elman NeuralNetwork[C].2nd International Conference on Advanced Computer Control(ICACC). IEEE,2010,Vol.2:652-656.
[112] Zhang Yu, Lu Zhaoyang, Li Jing. Fabric Defect Classification Using Radial BasisFunction Network[J]. Pattern Recognition Letters.2010, Vol.31(13):2033-2042.
[113]刘万春,罗双华,朱玉文,等.基于聚类分析和支持向量机的布匹瑕疵分类方法[J].北京理工大学学报.2004, Vol.24(8):687-690.
[114] Basu A, Chandra J K, Banerjee P K,et al. Sub Image Based Eigen Fabrics MethodUsing Multi-Class Svm Classifier for the Detection and Classification of Defectsin Woven Fabric[C]. Computing Communication&Networking Technologies(ICCCNT),2012Third International Conference on. IEEE,2012:1-6.
[115] Kwak C, Ventura J A, Tofang-Sazi, K. Automated Defect Inspection andClassification of Leather Fabric[J]. Intelligent Data Analysis.2001, Vol.5(4):355-370.
[116] Jeong S H, Choi H T, Kim S R. Detecting Fabric Defects with Computer Visionand Fuzzy Rule Generation Part I: Defect Classification by Image Processing[J].Textile Research Journal.2001, Vol.71(6):518-526.
[117] Yang X, Pang G, Yung N. Fabric Defect Classification Using Wavelet Frames andMinimum Classification Error Training[C].37th IAS Annual Meeting Conferenceof the Industry Applications.2002,Vol.1:290-296.
[118] Yang X, Pang G, Yung N. Robust Fabric Defect Detection and Classificationusing Multiple Adaptive Wavelets[J]. IEE Proceedings-Vision,Image and SignalProcessing.2005, Vol.152(6):715-723.
[119]李益红，卢朝阳，李静，等.一种提取局部区域共同向量的瑕疵分类算法[J].西安电子科技大学学报.2011, Vol.38(5):59-64.
[120]李远征.人体目标跟踪和表情识别中的若干问题研究[D].西安电子科技大学博士学位论文,2013.
[121]胡小锋,赵辉. Visual C++/MATLAB图像处理与识别实用案例精选[M].人民邮电出版社,2004.
[122]阮秋琦等.数字图像处理: MATLAB版[M].电子工业出版社,2005.
[123] Haralick R M. Statistical and Structural Approaches to Texture[J]. Proceedings ofthe IEEE.1979, Vol.67(5):786-804.
[124] Ojala T, Pietikainen M, Harwood D. A Comparative Study of Texture Measureswith Classification Based on Featured Distributions[J]. Pattern Recognition.1996,Vol.29(1):51-59.
[125] Ojala T, Pietikainen M, Maenpaa T. Multiresolution Gray-Scale and RotationInvariant Texture Classification with Local Binary Patterns[J]. IEEE Transactionson Pattern Analysis and Machine Intelligence.2002, Vol.24(7):971-987.
[126] Sadler B M, Swami A. Analysis of Multiscale Products for Step Detection andEstimation[J]. IEEE Transactions on Information Theory.1999, Vol.45(3):1043-1051.
[127]张文革，刘芳，高新波，焦李成.一种自适应多尺度积阈值的图像去噪算法[J].电子与信息学报.2009, Vol.31(8):1779-1785.
[128] Zhang Lei, Bao Paul. Edge Detection by Scale Multiplication in WaveletDomain[J]. Pattern Recognition Letters.2002, Vol.23(14):1771-1784.
[129] Chetverikov D, Henbury A. Finding Defects in Texture using Regularity andLocal Orientation[J]. Pattern Recognition.2002, Vol.35(10):2165-2180.
[130] Mak K L, Peng P, Lau H Y K. Optimal Morphological Filter Design for FabricDefect Detection[C]. IEEE International Conference on Industrial Technology,2005:799-804.
[131] Mallat. A Wavelet Tour of Signal Processing[M]. Academic Press,1999.
[132]张德丰. Matlab小波分析[M].机械工业出版社,2009.
[133]黄世亮，裘鉴卿.基于小波变换多尺度积的图像融合算法[J].红外与激光工程.2007, Vol.36(3):391-394.
[134] Tuia D, Pacifici F, Kanevski M, Emery W J. Classification of Very High SpatialResolution Imagery Using Mathematical Morphology and Support VectorMachines[J]. IEEE Transactions on Geoscience and Remote Sensing.2009, Vol.47(11):3866-3879.
[135] Otsu N. A threshold selection method from gray-level histograms[J]. IEEETransactions on Systems,Man,and Cybernetics.1979, Vol.9(1):62-66.
[136]洪文学等.基于多元统计图表示原理的信息融合和模式识别技术[M].国防工业出版社,2007.
[137]毛士艺，赵巍.多传感器图像融合技术综述[J].北京航空航天大学学报.2002,Vol.28(5):512-518.
[138] Pennec E L, Mallat S. Image Compression with Geometrical Wavelets[C].International Conference on Image Processing. IEEE,2000,Vol.1:661-664.
[139] Tang Lei, Zhao Feng, Zhao Zong-Gui. The Nonsubsampled Contourlet Transformfor Image Fusion[C]. International Conference on Wavelet Analysis and PatternRecognition. IEEE,2007,Vol.1:305-310.
[140]贾建，焦李成.利用方向特性实现非下采样Contourlet变换阈值去噪[J].西安电子科技大学学报.2009, Vol.36(2):269-273.
[141]常霞，焦李成，刘芳，等.基于斑点方差估计的非下采样Contourlet域SAR图像去噪[J].电子学报.2010, Vol.38(6):1328-1333.
[142] Do M N, Vetterli M. Contourlets[J]. Studies in Computational Mathematics,2003, Vol.10:83-105..
[143] Bamberger, Roberto H,Smith, Mark JT. A filter bank for the directionaldecomposition of images: Theory and design[J]. IEEE Transactions on ImageProcessing.1992, Vol.40(4):882-893.
[144] Shensa M J. The Discrete Wavelet Transform: Wedding the àtrous and MallatAlgorithms[J]. IEEE Transactions on Signal Processing.1992, Vol.40(10):2464-2482.
[145] Burt P J, Adelson E H. The Laplacian Pyramid as a Compact Image Code [J].IEEE Transactions on Communication.1983, Vol.31(4):532-540.
[146] Bamberger R H, Smith M J T. A filter bank for the directional decomposition ofimage:Theory and design[J]. IEEE Transactions on Signal Process.1992, Vol.40(4):882-893.
[147] Chiou Y C. Intelligent Segmentation Method for Real-Time Defect InspectionSystem[J]. Computers in Industry2010, Vol.61(7):646-658.
[148] Dempster A, Laird N, Rubin D. Maximum likehood estimation from incompletedata via the EM algorithm[J]. Journal of the royal statistical society:Series B.1977, Vol.39(1):1-38.
[149] Kumar A. Computer-Vision-Based Fabric Defect Detection: A Survey[J]. IEEETransactions on Industrial Electronics.2008, Vol.55(1):348-363.
[150] Kumar A, Pang G K H. Defect Detection in Texture Material using OptimizedFilters[J]. IEEE Transactions on Systems,Man,and Cybernetics-PartB:Cybernetics.2002, Vol.32(5):553-570.
[151] Choonjong K, Jose A. Ventura, Karim Tofang-Sazi. A Neural Network Approachfor Defect Identification and Classification on Leather Fabric[J]. Journal ofIntelligent Manufacturing.2000, Vol.11(5):485-499.
[152] Thomas Deselaers, Georg Heigold, Hermann Ney. Object Classification byFusing SVMs and Gaussian mixtures[J]. Pattern Recognition.2010, Vol.43(7):2476-2484.
[153]李娟，邵春福，杨励雅.基于混合高斯模型的行人检测方法[J].吉林大学学报（工学版）.2011, Vol.41(1):41-45.
[154]詹小孟.人脸表情识别关键技术研究[D].西安电子科技大学硕士学位论文,2012.
[155]王国德,张培林,任国全,等.融合LBP和GLCM的纹理特征提取方法[J].Computer Engineering.2012, Vol.38(11):199-201.
[156]马继涌，高文.一种基于最小误分率估计高斯混合模型参数的方法[J].计算机学报.1999, Vol.22(8):804-808.
[157]董宏辉，孙智源，葛大伟，秦勇，贾利民.基于高斯混合模型的铁路入侵物体目标识别方法[J].中国铁道科学.2011, Vol.32(2):131-135.
[158] Chang C C, Lin C J. LIBSVM: a library for support vector machines[J]. ACMTransactions on Intelligent Systems and Technology.2011, Vol.2(3):27:1--27:27.
[159] Olshausen B A. Emergence of Simple-Cell Receptive Field Properties byLearning a Sparse Code for Natural Images[J]. Nature.1996, Vol.381(6583):607-609.
[160] Wright J, Ma Yi, Mairal J, et al. Sparse Representation for Computer Vision andPattern Recognition[J]. Proceedings of the IEEE.2010, Vol.98(6):1031-1044.
[161] Mairal J, Elad M, Sapiro G. Sparse Representation for Color Image Restoration[J].IEEE Transactions on Image Processing.2008, Vol.17(1):53-69.
[162] Wright J, Yang A Y, Ganesh A, et al. Robust Face Recognition Via SparseRepresentation[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence.2009, Vol.31(2):210-227.
[163] Li Shutao, Fang Leyuan, Yin Haitao.An Efficient Dictionary Learning Algorithmand Its Application to3-D Medical Image Denoising[J]. IEEE Transactions onBiomedical Engineering2012, Vol.59(2):417-427.
[164] Wei C P, Chao Y W, Yeh Y R,et al. Locality-sensitive Dictionary Learning forSparse Representation Based Classification[J]. Pattern Recognition.2013, Vol.46(5):1277-1287.
[165] Engan Kjersti, Aase Sven Ole, Hakon Husoy J. Method of Optimal Directions forFrame Design[C]. IEEE International Conference on Acoustics, Speech, andSignal Processing. IEEE,1999, Vol.5:2443-2446.
[166] Aharon M, Elad M, Bruckstein A. K-SVD: An Algorithm for DesigningOvercomplete Dictionaries for Sparse Representation[J]. IEEE Transcations onSignal Processing.2006, Vol.54(11):4311-4322.
[167] Zhang Qiang, Li Baoxin. Discriminative K-SVD for Dictionary Learning in FaceRecognition[C]. IEEE Conference on Computer Vision and Pattern Recognition(CVPR). IEEE,2010:2691-2698.
[168] Jiang Zhuolin, Lin Zhe, Davis L S. Learning a Discriminative Dictionary forSparse Coding Via Label Consistent K-SVD[C]. IEEE Conference on ComputerVision and Pattern Recognition (CVPR). IEEE,2011:1697-1704.
[169] Mallat S G, Zhang Z. Matching Pursuits with Time-Frequency Dictionaries[J].IEEE Transactions on Signal Processing.1993, Vol.41(12):3397-3415.
[170] Pati Y C, Rezaiifar R, Krishnaprasad P S. Orthogonal Matching Pursuit:Recursive Function Approximation with Applications to WaveletDecomposition[C]. The27th Asilomar Conference on Signals, Systems andComputers. IEEE,1993:40-44.
[171] Chen S S, Donoho D L, Saunders M A. Atomic Decomposition by BasisPursuit[J]. SIAM Journal on Scientific Computing.1998, Vol.20(1):33-61.
[172]周颖玥.变分模型和稀疏冗余表示在图像恢复中的应用研究[D].中国科学技术大学工学博士学位论文,2013.
[173] Friedman J H, Stuetzle W. Projection Pursuit Regression[J]. Journal of theAmerican Statistical Association.1981, Vol.76(376):817-823.
[174] Efron B, Hastie T, Johnstone I,et al. Least Angle Regression[J]. The Annals ofstatistics.2004, Vol.32(2):407-499.
[175] Daubechies I, Defrise M, De Mol C. An Iterative Thresholding Algorithm forLinear Inverse Problems With a Sparsity Constraint[J]. Communications on Pureand Applied Mathematics.2004, Vol.57(11):1413-1457.
[176]戴道清，杨力华译.信号处理的小波导引：稀疏方法[M].机械工业出版社,2011.
[177] Mairal J, Bach F, Ponce J,et al. Discriminative Learned Dictionaries for LocalImage Analysis[C]. IEEE Conference on Computer Vision and PatternRecognition. IEEE,2008:1-8.
[2]邹超.布匹疵点在线检测系统研究[D].华中科技大学博士学位论文,2009.
[3]毕明德.基于机器视觉的布匹疵点检测系统[D].华中科技大学博士学位论文,2012.
[4] Xie Xianghua. A Review of Recent Advances in Surface Defect Detection usingTexture analysis Techniques[J]. Electronic Letters on Computer Vision and ImageAnalysis.2008, Vol.7(3):1-22.
[5] Tsai D M, Chang C C, Chao S M. Micro-crack Inspection in HeterogeneouslyTextured Solar Wafers Using Anisotropic Diffusion[J]. Image and VisionComputing.2010, Vol.28(3):491-501.
[6] Pan Z, Chen L, Li W,et al. A Novel Defect Inspection Method for SemiconductorWafer Based on Magneto-Optic Imaging[J]. Journal of Low Temperature Physics.2013, Vol.170(5-6):436-441.
[7] Hocenski Z, Keser T, Baumgartner A. A Simple and Efficient Method forCeramic Tile Surface Defects Detection[C]. IEEE International Symposium onIndustrial Electronics. IEEE,2007:1606-1611.
[8]李立轻.基于计算机视觉的织物疵点自动检测研究[D].东华大学博士学位论文,2003.
[9] Dockery A. Automated Fabric Inspection: Assessing The Current State of The Art.http://www.techexchange. com.2001.
[10] GB/T17759-2009.本色布布面疵点检验方法[S].
[11] Henry Y T N, Grantham K H P, Nelson H C Y. Automated Fabric DefectDetection－A review[J]. Image and Vision Computing.2011, Vol.29(7):442-458.
[12] Mandelbrot B B. The fractal Geometry of Nature[M]. Macmillan,1983.
[13] Otsu N. A Threshold Selection Method from Gray-Level Histograms[J].Automatica.1975, Vol.11(285-296):23-27.
[14] Serra J. Image Analysis and Mathematical Morphology[M]. London.: AcademicPress,1982.
[15] Soh L K, Tsatsoulis C. Texture Analysis of SAR Sea Ice Imagery Using GrayLevel Co-Occurrence Matrices[J]. IEEE Transactions on Geoscience and RemoteSensing.1999, Vol.37(2):780-795.
[16] Hagan M T, Demuth H B, Beale M H. Neural Network Design[M]. Pws Pub.Boston,1996.
[17] Conci A, Proenca C B. A Fractal Image Analysis System for Fabric InspectionBased on a Box-Counting Method[J]. Computer Networks&ISDN Systems.1998, Vol.30(20):1887-1895.
[18]步红刚,黄秀宝,汪军.基于多分形特征参数的织物瑕疵检测[J].计算机工程与应用.2007, Vol.36:233-237.
[19] Bu H G, Wang J, Huang X B. Fabric Defect Detection Based on Multiple FractalFeatures and Support Vector Data Description[J]. Engineering Applications ofArtificial Intelligence.2009, Vol.22(2):224-235.
[20] Zhang Y F, Bresee R R. Fabric Defect Detection and Classification using ImageAnalysis[J]. Textile Research Journal.1995, Vol.65(1):1-9.
[21] Thomas T, Cattoen M. Automatic Inspection of Simply Patterned Material in TheTextile Industry[J]. Machine Vision Applications in Industrial Inspection.1994,Vol.2183:2-12.
[22] Haralick Robert M, Sternberg Stanley R, Zhuang Xinhua. Image analysis usingmathematical morphology[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence.1987, Vol.(4):532-550.
[23] Dougherty E R. An Introduction to Morphological Image Processing[M]. SPIEOptical Engineering Press,1992.
[24] Mallick-Goswami B, Datta A K. Detecting Defects in Fabric with Laser-BasedMorphological Image Processing[J]. Textile Research Journal.2000, Vol.70(9):758-762.
[25] Chetverikov D, Henbury A. Finding Defects in Texture using Regularity andLocal Orientation[J]. Pattern Recognition.2002, Vol.35(10):2165-2180.
[26] Mak K L, Peng P, Yiu K F C. Fabric Defect Detection Using MorphologicalFilters[J]. Image and Vision Computing.2009, Vol.27(10):1585-1592.
[27] Haralick R M, Shanmugam K, Dinstein I. Textural Features for ImageClassification[J]. IEEE Transactions on Systems,Man,and Cybernetics.1973, Vol.3(6):610-621.
[28] Tsai I, Lin C, Lin J. Applying an Artificial Neural Network to Pattern Recognitionin Fabric Defects[J]. Textile Research Journal.1995, Vol.65(3):123-130.
[29] Bodnarova A, Williams J A, Bennamoun M, et al. Optimal Textural Features forFlaw Detection in Textile Materials[C]. IEEE Conference on Speech and ImageTechnologies for Computing and Telecommunications.1997, Vol.1:307-310.
[30] Latif-Amet A, Ertuzun A, Ercil A. An Efficient Method for Texture DefectDetection: Subband Domain Co-Occurrence Matrices[J]. Image and VisionComputing.2000, Vol.18(6-7):543-553.
[31]邹超，朱德森，肖力.基于类别共生矩阵的纹理疵点检测方法[J].华中科技大学学报（自然科学版）.2006, Vol.34(6):25-28.
[32]邹超，朱德森，肖力.基于模糊类别共生矩阵的纹理疵点检测方法[J].中国图象图形学报.2007, Vol.12(1):92-97.
[33] Jain A K, Duin R P W, Mao J. Statistical Pattern Recognition a Review[J]. IEEETransactions on Pattern Analysis and Machine Intelligence.2000, Vol.22(1):4-37.
[34] Kumar A, Shen H C. Texture Inspection for Defects using Neural Networks andSupport Vector Machines[C]. International Conference on Image Processing.2002, Vol.3:353-356.
[35] Kumar A. Neural Network Based Detection of Local Textile Defects[J]. PatternRecognition.2003, Vol.36(7):1645-1659.
[36]宋寅卯,袁端磊,卢易枫,乔桂花.基于最优PCNN模型的织物疵点自动检测[J].仪器仪表学报.2008, Vol.29(4):888-891.
[37] Tolba A S. Fast Defect Detection in Homogeneous Flat Surface Products[J].Expert Systems with Applications.2011, Vol.38(10):12339-12347.
[38] TILDA, Textile Defect Image Database. Germany: University of Freiburg.1996.
[39] Bracewell R N, Bracewell R N. The Fourier Transform and Its Applications[M].McGraw-Hill New York,1986.
[40] Gabor D. Theory of Communication[J]. Journal of the Institution of ElectricalEngineers.1946, Vol.93:429-457.
[41] Mallat S G. A Theory for Multiresolution Signal Decomposition: The WaveletRepresentation[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence.1989, Vol.11(7):674-693.
[42] Cunha A L, Zhou Jianping, Do M N. The Nonsubsampled Contourlet Transform:Theory, Design,and Application[J]. IEEE Transactions on Image Processing.2006, Vol.15(10):3089-3101.
[43]焦李成，侯彪，王爽，等.图像多尺度几何分析理论与应用[M].2008.
[44] Mead D C, Kasdan H L, Dorrity J L.Method for Automatic Fabric Inspection[P].1978. U.S. Patent4124300.
[45] Ciamberlini C, Francini F, Longobardi G. Defect Detection in Textured Materialsby Optical Filtering with Structured Detectors and Self-Adaptable Masks[J].Optical Engineering.1996, Vol.35(3):835-844.
[46] Chan Chi-Ho, Pang G K H. Fabric Defect Detection by Fourier Analysis[J]. IEEETransactions on Industry Applications.2000, Vol.36(5):1267-1276.
[47] Tsai D M, Hsieh C Y. Automated Surface Inspection for Directional Textures[J].Image and Vision Computing.1999, Vol.18(1):49-62.
[48] Bodnarova A, Bennamoun M, Latham S J. A Constrained MinimisationApproach to Optimise Gabor Filters for Detecting Flaws in Woven Textiles[C].International Conference on Acoustics, Speech and Signal Process.2000, Vol.6:3606-3609.
[49] Bodnarova A, Bennamoun M, Latham S J. Textile Flaw Detection using OptimalGabor Filters[C].2000, Vol.4:799-802.
[50] Bodnarova A, Bennamoun A, Latham S J. Optimal Gabor filters textile flawdetection[J]. Pattern Recognition.2002, Vol.35:2973-2991.
[51] Kumar A, Pang G K H. Defect Detection in Textured Materials Using GaborFilters[C]. IEEE Industry Applications Conference. Rome,Italy.2000, Vol.2:1041-1047.
[52] Kumar A, Pang G K H. Defect Detection in Textured Materials Using GaborFilters[J]. IEEE Transactions on Industry Applications.2002, Vol.38(2):425-440.
[53] Kumar A, Pang G K H. Fabric Defect Segmentation using Multichannel BlobDetectors[J]. Optical Engineering.2000, Vol.39(12):3176-3190.
[54]肖乐，朱玉文，丁丽宏，等.基于Gabor滤波器的布匹瑕疵自动检测方法[J].北京理工大学学报.2002, Vol.22(6):718-721.
[55] Zhang Yu, Lu Zhaoyang, Li Jing. Fabric Defect Detection and ClassificationUsing Gabor Filters and Gaussian Mixture Model[C]. The9th Asian Conferenceon Computer Vision–ACCV2009. Xi'an, China. Springer Berlin Heidelberg,2010, Vol.5995:635-644.
[56] Mak K L, Peng P. An Automated Inspection System for Textile Fabrics Based onGabor Filters[J]. Robotics and Computer-Integrated Manufacturing.2008, Vol.24(3):359-369.
[57] Sari-Sarraf H, Goddard J S. Vision Systems for On-Loom Fabric Inspection[J].IEEE Transactions ON Industry Application.1999, Vol.35(6):1252-1259.
[58] Dorrity J L, Vachtsevanos G. On-Line Defect Detection for Weaving Systems[C].IEEE Annual Technical Conference on Textile, Fiber and Film Industry. IEEE,1996:1-6.
[59] Jasper W J, Garnier S J, Potapalli H. Texture Characterization and DefectDetection using Adaptive Wavelets[J]. Optical Engineering.1996, Vol.35(11):3140-3149.
[60] Zeng PeiFeng, Hirata Tomio On-Loom Fabric Inspection using Multi-ScaleDifferentiation Filtering[C]. IEEE Industry Application Conference.2002, Vol.:320-326.
[61] Zeng PeiFeng, Hirata Tomio Fast Defect Detection in Cloths with B-splines[J].Iranian Journal of Electrical and Computer Engineering.2002, Vol.1:29-34.
[62] Yang XueZhi, Pang G K H, Yung N H C. Fabric Defect Detection using AdaptiveWavelet[C]. IEEE International Conference on Acoustics, Speech, and SignalProcessing(ICASSP).2001, Vol.6:3697-3700.
[63] Yang Xuezhi, Pang G K H, Yung N H C. Discriminative Fabric Defect Detectionusing Adaptive Wavelets[J]. Society of Photo-Optical Instrumentation Engineers.2002, Vol.41(12):3116-3126.
[64] Yang XueZhi, Pang G K H, Yung N H C. Discriminative Training Approaches toFabric Defect Classification Based on Wavelet Transform[J]. Pattern Recognition.2004, Vol.37(5):889-899.
[65] Tsai D M, Hsiao B. Automatic Surface Inspection using WaveletReconstruction[J]. Pattern Recognition.2001, Vol.34(6):1285-1305.
[66] Guan Shengqi, Yuan Jianchang, Ma Ke. Fabric Defect Detection Based onWavelet Reconstruction[C]. International Conference on Multimedia Technology(ICMT).2011:3520-3523.
[67] Serdaroglu A, Ertuzun A, Ercil A. Defect Detection in Textile Fabric Imagesusing Wavelet Transforms and Independent Component Analysis[J]. PatternRecognition and Image Analysis.2006, Vol.16(1):61-64.
[68] Han Yanfang, Shi Pengfei. An Adaptive Level-selecting Wavelet Transform forTexture Defect Detection[J]. Image and Vision Computing.2007, Vol.25(8):1239-1248.
[69] Jiang HuiYu, Dong Min, Li Wei. Detection of Fabric Defect Based on OptimalTree Structure of Wavelet Decomposition[C]. International Symposium onIntelligent Ubiquitous Computing and Education. IEEE,2009, Vol.:210-213.
[70] Guan Shengqi, Shi Xiuhua, Cui Haiying,et al. Fabric Defect Detection Based onWavelet Characteristics[C]. Pacific-Asia Workshop on ComputationalIntelligence and Industrial Application, PACIIA'08. IEEE,2008, Vol.1:366-370.
[71] Ngan H Y T, Pang G K H, Yung S P. Wavelet based methods on patterned fabricdefect detection[J]. Pattern Recognition.2005, Vol.38(4):559-576.
[72]焦李成，谭山.图像的多尺度几何分析:回顾和展望[J].电子学报.2003, Vol.31(12):1975-1981.
[73]潘泓，李晓兵，金立左，等.基于多尺度几何分析的目标描述和识别[J].红外与毫米波学报.2011, Vol.30(1):85-90.
[74] Candes E J. Ridgelets:Theory and Applications[D]. USA:Department ofStatistics,Stanford University,1998.
[75] Candes E J, Donoho D L. Curvelets[R], USA: Department of Statistics, StanfordUniversity,1999.
[76] Meyer F G, Coifman R R. Brushlets: A Tool for Directional Image Analysis andImage Compression[J]. Applied and Computational Harmonic Analysis.1997,Vol.5:147-187.
[77] Do M N, Vetterli M. Contourlets[J]. Studies in Computational Mathematics.2003,Vol.10:83-105.
[78] Ai Yonghao, Xu Ke. Surface Detection of Continuous Casting Slabs Based onCurvelet Transform and Kernel Locality Preserving Projections[J]. InternationalJournal of Iron and Steel Research.2013, Vol.20(5):80-86.
[79] Zhang Yan, Li Tao, Li Qingling. Defect Detection for Tire Laser ShearographyImage Using Curvelet Transform Based Edge Detector[J]. Optics&LaserTechnology.2013, Vol.47:64-71.
[80] Ghorai S, Singh R, Gangadaran M. Wavelet Versus Contourlet Features forAutomatic Defect Detection on Hot Rolled Steel Sheet[C].2012ThirdInternational Conference on Emerging Applications of Information Technology(EAIT).2012:149-152.
[81] Kindermann R, Snell J L. Markov Random Fields and Their Applications[M].American Mathematical Society Providence, RI,1980.
[82] Akaike H. Fitting autoregressive models for prediction[J]. Annals of the instituteof Statistical Mathematics.1969, Vol.21(1):243-247.
[83] Andrey P, Tarroux P. Unsupervised Segmentation of Markov Random FieldModeled Textured Images Using Selectionist Relaxation[J]. IEEE Transactionson Pattern Analysis and Machine Intelligence.1998, Vol.20(3):252-262.
[84] Feng Wei, Jia Jiaya, Liu Zhiqiang. Self-Validated Labeling of Markov RandomFields for Image Segmentation[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence.2010, Vol.32(10):1871-1887.
[85] Deng Huawu, Clausi D A. Gaussian MRF Rotation-Invariant Features for ImageClassification[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence.2004, Vol.26(7):951-955.
[86] Yamazaki T, Gingras D. Image Classification Using Spectral and SpatialInformation Based on MRF Models[J]. IEEE Transactions on Image Processing.1995, Vol.4(9):1333-1339.
[87] Attali S F, Cohen F S. Surface Inspection Based on Stochastic Modeling[C].SPIE Proceedings.1986, Vol.665:46-52.
[88] Cohen F S, Fan Z, Attali S. Automated Inspection of Textile Fabrics UsingTextural Models[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence.1991, Vol.8(13):803-808.
[89] Ozdemir S, Ercil A. Markov Random Fields and Karhunen-Loeve Transforms forDefect Inspection of Textile Products[C]. IEEE Conference on EmergingTechnologies and Factory Automation.1996,Vol.2:697-703.
[90] Limas S A F. Segmentation of Natural Images Based on Multiresolution PyramidsLinking of the Parameters of an Autoregressive Rotation Invariant ModelApplication to Leather Defects Detection[C]. International Conference on PatternRecognition, Conference C: Image, Speech and Signal Analysis,11th IAPR1992:41-44.
[91] Hajimowlana S H, Muscedere R, Jullien G A,et al.1D Autoregressive Modelingfor Defect Detection in Web Inspection Systems[C]. Midwest Symposium onCircuits and Systems,1998:318-321.
[92] Bu H G, Huang X B, Wang J, et al. Detection of Fabric Defects byAuto-Regressive Spectral Analysis and Support Vector Data Description[J].Textile Research Journal.2010, Vol.80(7):579-589.
[93] Xuezhi, Yang. Discriminative Fabric Defect Detection and Classification UsingAdaptive Wavelet[D].香港大学博士学位论文,2003.
[94]李晶皎，王爱侠，张广渊，等译.模式识别（第三版）[M].电子工业出版社,2008.
[95] Hargrove L J, Li G, Englehart K B,et al. Principal Components AnalysisPreprocessing for Improved Classification Accuracies inPattern-Recognition-Based Myoelectric Control[J]. IEEE Transactions onBiomedical Engineering.2009, Vol.56(5):1407-1414.
[96] Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning[M]. NewYork: Springer-Verlag,2001.
[97] Duda Richard O, Hart Peter E, Stork David G. Pattern Classification[M]. JohnWiley&Sons,2012.
[98] He X F, Niyogi P. Locality Preserving Projections[C]. Advances in NeuralInformation Processing Systems. Vancouver: MIT Press,2003:153-162.
[99] Stojanovic R, Mitropulos P, Koulamas C,et al. Automated Detection and NeuralClassification of Local Defects in Textile Web[C]. Seventh InternationalConference on Image Processing and Its Applications. IET,1999,Vol.2:647-651.
[100] Mitropoulos P, Koulamas C, Stojanovic R D,et al. Real-time Vision System forDefect Detection and Neural Classification of Web Textile Fabric[C]. ElectronicImaging'99. International Society for Optics and Photonics,1999:59-69.
[101] Kwak C, Ventura J A, Tofang-Sazi K. A Neural Network Approach for DefectIdentification and Classification on Leather Fabric[J]. Journal of IntelligentManufacturing.2000, Vol.11(5):485-499.
[102]卿湘运，段红，魏俊民，等.一种新的基于小波分析与神经网络的织物疵点检测与识别方法[J].仪器仪表学报.2005, Vol.26(6):618-622.
[103] Elragal H M. Neuro-Fuzzy Fabric Defect Detection and Classification forKnitting Machine[C]. Proceedings of the Twenty Third National Radio ScienceConference,NRSC2006, IEEE,2006:1-8.
[104] Kuo C F J, Lee C J,Tsai C C. Using a Neural Network to Identify Fabric Defectsin Dynamic Cloth Inspection[J]. Textile Research Journal.2003, Vol.73(3):238-244.
[105] Stojanovic R, Mitropulos P, Koulamas C,et al. Real-time Vision-Based Systemfor Textile Fabric Inspection[J]. Real-Time Imaging.2001, Vol.7(6):507-518.
[106] Hung C C, Chen I C. Neural-Fuzzy Classification for Fabric Defects[J]. TextileResearch Journal.2001, Vol.71(3):220-224.
[107] Pang G K H, Yang X, Yung N. Fabric Defect Classification Using WaveletFrames and Minimum Classification Error-Based Neural Network[C]. The9thIEEE Conference on Mechatronics and Machine Vision in Practice. Chiang Mai,Thailand.2002:77-85.
[108] Kuo C, Lee C. A Back-Propagation Neural Network for Recognizing FabricDefects[J]. Textile Research Journal.2003, Vol.73(2):147-151.
[109] Islam A, Akhter S, Mursalin T E. Automated Textile Defect Recognition SystemUsing Computer Vision and Artificial Neural Networks[C]. Proceedings of WorldAcademy Of Science, Engineering and Technology.2006,Vol.13:1-6.
[110] Liu Su-Yi, Zhang Le-Duo, Wang Qian,et al. BP Neural Network in Classificationof Fabric Defect Based on Particle Swarm Optimization[C]. InternationalConference on Wavelet Analysis and Pattern Recognition, ICWAPR'08. IEEE,2008, Vol.1:216-220.
[111] Zhang Y H, Yuen C W M, Wong W K. A New Intelligent Fabric Defect Detectionand Classification System Based on Gabor Filter and Modified Elman NeuralNetwork[C].2nd International Conference on Advanced Computer Control(ICACC). IEEE,2010,Vol.2:652-656.
[112] Zhang Yu, Lu Zhaoyang, Li Jing. Fabric Defect Classification Using Radial BasisFunction Network[J]. Pattern Recognition Letters.2010, Vol.31(13):2033-2042.
[113]刘万春,罗双华,朱玉文,等.基于聚类分析和支持向量机的布匹瑕疵分类方法[J].北京理工大学学报.2004, Vol.24(8):687-690.
[114] Basu A, Chandra J K, Banerjee P K,et al. Sub Image Based Eigen Fabrics MethodUsing Multi-Class Svm Classifier for the Detection and Classification of Defectsin Woven Fabric[C]. Computing Communication&Networking Technologies(ICCCNT),2012Third International Conference on. IEEE,2012:1-6.
[115] Kwak C, Ventura J A, Tofang-Sazi, K. Automated Defect Inspection andClassification of Leather Fabric[J]. Intelligent Data Analysis.2001, Vol.5(4):355-370.
[116] Jeong S H, Choi H T, Kim S R. Detecting Fabric Defects with Computer Visionand Fuzzy Rule Generation Part I: Defect Classification by Image Processing[J].Textile Research Journal.2001, Vol.71(6):518-526.
[117] Yang X, Pang G, Yung N. Fabric Defect Classification Using Wavelet Frames andMinimum Classification Error Training[C].37th IAS Annual Meeting Conferenceof the Industry Applications.2002,Vol.1:290-296.
[118] Yang X, Pang G, Yung N. Robust Fabric Defect Detection and Classificationusing Multiple Adaptive Wavelets[J]. IEE Proceedings-Vision,Image and SignalProcessing.2005, Vol.152(6):715-723.
[119]李益红，卢朝阳，李静，等.一种提取局部区域共同向量的瑕疵分类算法[J].西安电子科技大学学报.2011, Vol.38(5):59-64.
[120]李远征.人体目标跟踪和表情识别中的若干问题研究[D].西安电子科技大学博士学位论文,2013.
[121]胡小锋,赵辉. Visual C++/MATLAB图像处理与识别实用案例精选[M].人民邮电出版社,2004.
[122]阮秋琦等.数字图像处理: MATLAB版[M].电子工业出版社,2005.
[123] Haralick R M. Statistical and Structural Approaches to Texture[J]. Proceedings ofthe IEEE.1979, Vol.67(5):786-804.
[124] Ojala T, Pietikainen M, Harwood D. A Comparative Study of Texture Measureswith Classification Based on Featured Distributions[J]. Pattern Recognition.1996,Vol.29(1):51-59.
[125] Ojala T, Pietikainen M, Maenpaa T. Multiresolution Gray-Scale and RotationInvariant Texture Classification with Local Binary Patterns[J]. IEEE Transactionson Pattern Analysis and Machine Intelligence.2002, Vol.24(7):971-987.
[126] Sadler B M, Swami A. Analysis of Multiscale Products for Step Detection andEstimation[J]. IEEE Transactions on Information Theory.1999, Vol.45(3):1043-1051.
[127]张文革，刘芳，高新波，焦李成.一种自适应多尺度积阈值的图像去噪算法[J].电子与信息学报.2009, Vol.31(8):1779-1785.
[128] Zhang Lei, Bao Paul. Edge Detection by Scale Multiplication in WaveletDomain[J]. Pattern Recognition Letters.2002, Vol.23(14):1771-1784.
[129] Chetverikov D, Henbury A. Finding Defects in Texture using Regularity andLocal Orientation[J]. Pattern Recognition.2002, Vol.35(10):2165-2180.
[130] Mak K L, Peng P, Lau H Y K. Optimal Morphological Filter Design for FabricDefect Detection[C]. IEEE International Conference on Industrial Technology,2005:799-804.
[131] Mallat. A Wavelet Tour of Signal Processing[M]. Academic Press,1999.
[132]张德丰. Matlab小波分析[M].机械工业出版社,2009.
[133]黄世亮，裘鉴卿.基于小波变换多尺度积的图像融合算法[J].红外与激光工程.2007, Vol.36(3):391-394.
[134] Tuia D, Pacifici F, Kanevski M, Emery W J. Classification of Very High SpatialResolution Imagery Using Mathematical Morphology and Support VectorMachines[J]. IEEE Transactions on Geoscience and Remote Sensing.2009, Vol.47(11):3866-3879.
[135] Otsu N. A threshold selection method from gray-level histograms[J]. IEEETransactions on Systems,Man,and Cybernetics.1979, Vol.9(1):62-66.
[136]洪文学等.基于多元统计图表示原理的信息融合和模式识别技术[M].国防工业出版社,2007.
[137]毛士艺，赵巍.多传感器图像融合技术综述[J].北京航空航天大学学报.2002,Vol.28(5):512-518.
[138] Pennec E L, Mallat S. Image Compression with Geometrical Wavelets[C].International Conference on Image Processing. IEEE,2000,Vol.1:661-664.
[139] Tang Lei, Zhao Feng, Zhao Zong-Gui. The Nonsubsampled Contourlet Transformfor Image Fusion[C]. International Conference on Wavelet Analysis and PatternRecognition. IEEE,2007,Vol.1:305-310.
[140]贾建，焦李成.利用方向特性实现非下采样Contourlet变换阈值去噪[J].西安电子科技大学学报.2009, Vol.36(2):269-273.
[141]常霞，焦李成，刘芳，等.基于斑点方差估计的非下采样Contourlet域SAR图像去噪[J].电子学报.2010, Vol.38(6):1328-1333.
[142] Do M N, Vetterli M. Contourlets[J]. Studies in Computational Mathematics,2003, Vol.10:83-105..
[143] Bamberger, Roberto H,Smith, Mark JT. A filter bank for the directionaldecomposition of images: Theory and design[J]. IEEE Transactions on ImageProcessing.1992, Vol.40(4):882-893.
[144] Shensa M J. The Discrete Wavelet Transform: Wedding the àtrous and MallatAlgorithms[J]. IEEE Transactions on Signal Processing.1992, Vol.40(10):2464-2482.
[145] Burt P J, Adelson E H. The Laplacian Pyramid as a Compact Image Code [J].IEEE Transactions on Communication.1983, Vol.31(4):532-540.
[146] Bamberger R H, Smith M J T. A filter bank for the directional decomposition ofimage:Theory and design[J]. IEEE Transactions on Signal Process.1992, Vol.40(4):882-893.
[147] Chiou Y C. Intelligent Segmentation Method for Real-Time Defect InspectionSystem[J]. Computers in Industry2010, Vol.61(7):646-658.
[148] Dempster A, Laird N, Rubin D. Maximum likehood estimation from incompletedata via the EM algorithm[J]. Journal of the royal statistical society:Series B.1977, Vol.39(1):1-38.
[149] Kumar A. Computer-Vision-Based Fabric Defect Detection: A Survey[J]. IEEETransactions on Industrial Electronics.2008, Vol.55(1):348-363.
[150] Kumar A, Pang G K H. Defect Detection in Texture Material using OptimizedFilters[J]. IEEE Transactions on Systems,Man,and Cybernetics-PartB:Cybernetics.2002, Vol.32(5):553-570.
[151] Choonjong K, Jose A. Ventura, Karim Tofang-Sazi. A Neural Network Approachfor Defect Identification and Classification on Leather Fabric[J]. Journal ofIntelligent Manufacturing.2000, Vol.11(5):485-499.
[152] Thomas Deselaers, Georg Heigold, Hermann Ney. Object Classification byFusing SVMs and Gaussian mixtures[J]. Pattern Recognition.2010, Vol.43(7):2476-2484.
[153]李娟，邵春福，杨励雅.基于混合高斯模型的行人检测方法[J].吉林大学学报（工学版）.2011, Vol.41(1):41-45.
[154]詹小孟.人脸表情识别关键技术研究[D].西安电子科技大学硕士学位论文,2012.
[155]王国德,张培林,任国全,等.融合LBP和GLCM的纹理特征提取方法[J].Computer Engineering.2012, Vol.38(11):199-201.
[156]马继涌，高文.一种基于最小误分率估计高斯混合模型参数的方法[J].计算机学报.1999, Vol.22(8):804-808.
[157]董宏辉，孙智源，葛大伟，秦勇，贾利民.基于高斯混合模型的铁路入侵物体目标识别方法[J].中国铁道科学.2011, Vol.32(2):131-135.
[158] Chang C C, Lin C J. LIBSVM: a library for support vector machines[J]. ACMTransactions on Intelligent Systems and Technology.2011, Vol.2(3):27:1--27:27.
[159] Olshausen B A. Emergence of Simple-Cell Receptive Field Properties byLearning a Sparse Code for Natural Images[J]. Nature.1996, Vol.381(6583):607-609.
[160] Wright J, Ma Yi, Mairal J, et al. Sparse Representation for Computer Vision andPattern Recognition[J]. Proceedings of the IEEE.2010, Vol.98(6):1031-1044.
[161] Mairal J, Elad M, Sapiro G. Sparse Representation for Color Image Restoration[J].IEEE Transactions on Image Processing.2008, Vol.17(1):53-69.
[162] Wright J, Yang A Y, Ganesh A, et al. Robust Face Recognition Via SparseRepresentation[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence.2009, Vol.31(2):210-227.
[163] Li Shutao, Fang Leyuan, Yin Haitao.An Efficient Dictionary Learning Algorithmand Its Application to3-D Medical Image Denoising[J]. IEEE Transactions onBiomedical Engineering2012, Vol.59(2):417-427.
[164] Wei C P, Chao Y W, Yeh Y R,et al. Locality-sensitive Dictionary Learning forSparse Representation Based Classification[J]. Pattern Recognition.2013, Vol.46(5):1277-1287.
[165] Engan Kjersti, Aase Sven Ole, Hakon Husoy J. Method of Optimal Directions forFrame Design[C]. IEEE International Conference on Acoustics, Speech, andSignal Processing. IEEE,1999, Vol.5:2443-2446.
[166] Aharon M, Elad M, Bruckstein A. K-SVD: An Algorithm for DesigningOvercomplete Dictionaries for Sparse Representation[J]. IEEE Transcations onSignal Processing.2006, Vol.54(11):4311-4322.
[167] Zhang Qiang, Li Baoxin. Discriminative K-SVD for Dictionary Learning in FaceRecognition[C]. IEEE Conference on Computer Vision and Pattern Recognition(CVPR). IEEE,2010:2691-2698.
[168] Jiang Zhuolin, Lin Zhe, Davis L S. Learning a Discriminative Dictionary forSparse Coding Via Label Consistent K-SVD[C]. IEEE Conference on ComputerVision and Pattern Recognition (CVPR). IEEE,2011:1697-1704.
[169] Mallat S G, Zhang Z. Matching Pursuits with Time-Frequency Dictionaries[J].IEEE Transactions on Signal Processing.1993, Vol.41(12):3397-3415.
[170] Pati Y C, Rezaiifar R, Krishnaprasad P S. Orthogonal Matching Pursuit:Recursive Function Approximation with Applications to WaveletDecomposition[C]. The27th Asilomar Conference on Signals, Systems andComputers. IEEE,1993:40-44.
[171] Chen S S, Donoho D L, Saunders M A. Atomic Decomposition by BasisPursuit[J]. SIAM Journal on Scientific Computing.1998, Vol.20(1):33-61.
[172]周颖玥.变分模型和稀疏冗余表示在图像恢复中的应用研究[D].中国科学技术大学工学博士学位论文,2013.
[173] Friedman J H, Stuetzle W. Projection Pursuit Regression[J]. Journal of theAmerican Statistical Association.1981, Vol.76(376):817-823.
[174] Efron B, Hastie T, Johnstone I,et al. Least Angle Regression[J]. The Annals ofstatistics.2004, Vol.32(2):407-499.
[175] Daubechies I, Defrise M, De Mol C. An Iterative Thresholding Algorithm forLinear Inverse Problems With a Sparsity Constraint[J]. Communications on Pureand Applied Mathematics.2004, Vol.57(11):1413-1457.
[176]戴道清，杨力华译.信号处理的小波导引：稀疏方法[M].机械工业出版社,2011.
[177] Mairal J, Bach F, Ponce J,et al. Discriminative Learned Dictionaries for LocalImage Analysis[C]. IEEE Conference on Computer Vision and PatternRecognition. IEEE,2008:1-8.