摘要
为了提高纺织工业产品的可靠性以及重现性，对织物外观特征进行客观评价起着越来越重要的作用，比如疵点、起球、组织结构、色差以及粗糙度等等。本文采用数字图像处理技术开展对织物疵点自动检测和分类、织物起球客观评级体系以及织物组织结构识别及分类等三个方面进行了基础理论的研究，所取得的主要研究成果为：
1.提出一种基于改进的Gabor滤波方法、数学形态学处理法和多尺度小波检测的方法库的系统检测法.首先采用改进的Gabor滤波方法，选出最优滤波结果，进行高斯平滑，确定出正常织物图像的两个阈值门限，进而分割出织物的疵点图像；其次采用形态处理学的处理方法对织物图片进行检测；最后采用了多尺度小波检测的方法，检测最终结果。
2.提出一种基于局部二进制模式与Tamura纹理特征方法相结合的织物疵点分类算法。该算法主要完成的任务是对织物特征向量的提取，局部二进制模式从局部或像素邻域描述纹理的特征，Tamura纹理特征方法从全局描述疵点纹理特征，两者结合能更好的描述疵点纹理特征。完成特征向量提取后，选用共轭梯度BP算法来处理特征向量。共轭梯度BP算法收敛性较好，提高了训练速度和训练精度。实验结果表明，提出的算法对疵点较高的分类准确率。
3.印花织物分为周期印花织物和无规则印花织物，在周期印花织物检测中，基于织物图案信息的周期性，规则带通过设定移动窗口，计算移动窗口的能量和方差，以无疵点的织物图像的能量和方差作为阈值，由计算的能量和方差值来检测疵点。在无规则印花织物检测中，通过遗传算法选择Gabor滤波器的参数，最优参数构造的Gabor滤波器匹配最佳检测织物纹理，从而提取织物的有效信息，达到分割织物疵点的目标。
4.基于二维离散小波变换和局部二值模式的织物起球客观评价方法。起球特征向量是由提取小波分解后尺度4-6的细节子图像在三个方向（水平、垂直、对角）上的小波能量值和将小波重构尺度3-6细节子图像的重构图进行LBP变换提取其特征值组成。特征值经过归一化处理后通过主成分分析（PCA）来降维，处理后的特征值作为支持向量机（SVM）的数据输入为织物起球等级分类。
5.提出了一种自动及实时的分类方法分析三种机织物即平纹，斜纹和缎纹组织。首先，用灰度共生矩阵和Gabor小波方法提取特征值。用主成分分析方法处理纹理特征向量获得最小冗余及最大主成分的特征向量。在分类过程中，应用概率神经网络分类三种基本机织物。实验结果表明有快速的训练速度的概率神经网络分类器能够精确及有效的分类机织物。比较灰度共生矩阵和Gabor小波两种方法，融合两个特征向量获得了最好的分类结果（95%）。
In order to improve the reliability and reproducibility of textile industry products,evaluating appearance characteristics objectively on fabrics plays a more and moreimportant role in textile industry, such as characteristics of defect, pilling, organizationstructure, color and roughness, et al. Processing technology of digital image is appliedto three aspects on the basis of theory research including automatic defect detection andclassification of woven material, objective rating system on fabric pilling, fabricstructure recognition and classification in this article. Main research results are obtainedas follows:
1. Joint fabric defect detection method based on method library. A joint fabricdefect detection method based on "method library" is proposed, and various effectivedefect detection algorithms on fabrics are improved and synthesized in joint fabricdefect detection method based on method library. The proposed method integratesGabor-Gauss method, background analysis, multi-scale wavelet method as joint defectdetection method library to detect defects on fabrics. A preliminary graphical userinterface (GUI) based on method library is designed in order to facilitatehuman-computer interactions.
2. Fabric defect classification algorithm based on combining texture feature oflocal binary pattern (LBP) and Tamura. Fabric defect classification algorithm viacombining texture feature of local binary pattern (LBP) and Tamura texture feature isput forward due to a single feature can not be effective description of fabric defect.Local binary patterns can describe characteristics of fabric texture from local, Globaldefect texture feature could be represented by way of Tamura method. Better descriptionof defect texture feature could be obtained by means of combining local binary pattern(LBP) and Tamura. Conjugate BP is applied to train and test extracted feature vector inproposed method.
3. Defect detection on printing fabrics. The printing fabric can be divided intocycle printing fabric and random printing fabric. In the test of cycle printing fabrics,moving window is set in regular band based on the information of periodic patternfabric. Energy and variance of defect-free fabrics could be determined as threshold.Calculation of energy and variance of sample cycle printing fabrics could realize defectdetection based on obtained threshold. In the testing of random printing fabrics,parameters of Gabor filter can be selected via genetic algorithm, Gabor filter structuredby optimal parameters is matched with fabric texture so as to extract the effective information of woven fabric in fabric defect detection, thus the purpose of fabric defectsegmentation can be achieved.
4. A new method based on wavelet transform and local binary pattern (LBP) wasproposed for fabric pilling objective evaluation. The surface of the fabric pillinginformation was inspected by using two-dimensional discrete wavelet transform(2DDWT). The pilling feature vectors were consisted of the wavelet energy value whichis the wavelet decomposition of sub-image details in scale4to6with three directions(horizontally, vertically, diagonally) and the LBP features which is waveletreconstruction image in scale3to6using LBP. It is necessary to normalization thefeatures using principal component analysis (PCA) to reduce the dimensions. Then, theprocessed feature can act as fabric pilling classification data input for support vectormachine (SVM).
5. An automatic and real-time classification method is proposed to analyze threewoven fabrics such as plain, twill, and satin weave. The methodology involves twoapproaches to extract texture features using gray-level co-occurrence matrix (GLCM)and Gabor wavelet. Then, principal component analysis (PCA) is utilized to deal withthe texture feature vectors to gain minimize redundancy and maximize principalcomponent feature vectors. Finally, for the classification phase, probabilistic neuralnetwork (PNN) is applied to classify three basic woven fabrics. With strong real-time,robustness, fault-tolerance and non-linear classification capability, PNN can be apromising tool for classification of woven fabrics. The experimental results show thatPNN classifier with faster training speed can classify woven fabrics accurately andefficiently. Besides, compared with GLCM method and Gabor wavelet method, thefusion of the two feature vectors obtain the best classification result (95%).
引文
[1] Jain A K, Duin R P W, Mao J. Statistical pattern recognition: A review. IEEE Transaction onPattern Analysis&Machine Intelligence,2000,22(1):4-37.
[2] Ngan H Y T, Pang G K H. Regularity Analysis for Patterned Texture Inspection. IEEETransactions on Automation science and engineering,2009,6(1):131-144.
[3] Ngan H Y T, Pang G K H. Novel method for patterned fabric inspection using Bollinger bands.Optical Engineering,2006,45(8):087202-087202-15.
[4] Ngan H Y T, Pang G K H, Yung N H C. Ellipsoidal decision regions for motif-based patternedfabric defect detection. Pattern Recognition,2010,43(6):2132-2144.
[5] RM Haralick, SR Sternberg, X Zhuang. Image analysis using mathematical morphology. IEEETransactions on Pattern Analysis and Machine Intelligence,2009,9(4):532-550.
[6] Zhang Y F, Bresee R R. Fabric defect detection and classification using image analysis. TextileResearch Journal,1995,65(1):1-9.
[7] Muller S, Nickolay B. Morphological image processing for the recognition of surface defects.Proceedings. SPIE2249Automated3D and2D Vision,1994:298-307.
[8] Mak K L, Peng P, Yiu K F C. Fabric defect detection using morphological filters. Image andVision Computing,2009,27(10):1585-1592.
[9] Mallick-Goswami B, Datta A K. Detecting defects in fabric with laser-based morphologicalimage processing. Textile Research Journal,2000,70(9):758-762.
[10] Boukouvalas C, Kittler J, Marik R et al. Color grading of randomly textured ceramic tiles usingcolor histograms. IEEE Transactions on Industry Electronics,1999,46(1):219-226.
[11] Pietik inen M, M enp T, Viertola J. Color texture classification with color histograms andlocal binary patterns. Workshop on Texture Analysis and Synthesis in Machine Vision,2002:109-112.
[12] Broadhurst R, Stough J, Pizer S et al. Histogram statistics of local image regions for objectsegmentation. In International Workshop on Deep Structure, Singularities, and ComputerVision,2005.
[13] Xie X, Mirmehdi M, Thomas B. Colour tonality inspection using eigenspace features. MachineVision and Applications,2006,16(6):364-373.
[14] Ng H. Automatic thresholding for defect detection. Pattern Recognition Letters,2007,27(14):1644-1649.
[15] Tajeripour F, Kabir E, Sheikhi A. Defect Detection in Patterned Fabrics Using Modified LocalBinary Patterns. Conference on Computational Intelligence and Multimedia Applications,2007(2):261-267.
[16] OjalaT, Pietik inen M, M enp T. Multiresolution gray-scale and rotation invariant textureclassification with local binary patterns. IEEE Transactions on Pattern Analysis and MachineIntelligence,2002,24(7):971-987.
[17] Ojala T, Pietik inen M, Pietik¨ainen M, Harwood D. A comparative study of texture measureswith classification based on featured distribution. Pattern Recognition,1996,29(1):51-59.
[18] Bu H G, Wang J, Huang X B. Fabric defect detection based on multiple fractal features andsupport vector data description. Engineering Applications of Artificial Intelligence,2009,22(2):224-235.
[19] Conci A, Proen a C B. A fractal image analysis system for fabric inspection based onbox-counting method. Computer Networks and ISDN Systems,1998,30(20):1887-1895.
[20] Randen T, Husoy J. Filtering for texture classification: A comparative study. IEEE Transactionson pattern Analysis and Machine Intelligence,1999,21(4):291-310.
[21] Conners R, Harlow C. A theoretical comparison of texture algorithms. IEEE Trans. on PatternAnalysis and Machine Intelligence,1980,2(3):204-222.
[22] Siew L H, Hodgson R M, Wood E J. Texture measures for carpet wear assessment. IEEETransactions on Pattern Analysis and Machine Intelligence,1988,10(1):92-105.
[23] Tsai Z D, Perng M H. Defect detection in periodic patterns using a multi-band-pass filter.Machine Vision and Applications,2013,24(3):551-565.
[24] Harris F J. On the use of windows for harmonic analysis with the discrete Fourier transform.Proceedings of the IEEE,1978,66(1):51-83.
[25] Wood E J. Applying Fourier and associated transforms to pattern characterization in textiles.Textile Research Journal,1990,64(2):212-220.
[26] Tsai I S, Hu M C. Automated inspection of fabric defects using an artificial neural network.Textile Research Journal,1996,66(7):474-482.
[27] Hoffer L M, Francini F, Tiribilli B et al. Neural network for the optical recognition of defects incloth. Optical Engineering,1996,35(11):3183-3190.
[28] Casterllini C, Francini F, Longobardi G et al. On-line textile quality control using opticalFourier transforms. Optics and Lasers in Engineering,1996,24(1):19-32.
[29] Tsai D M, Heish C Y. Automated surface inspection for directional textures. Image and VisionComputing,1999,18(1):49-62.
[30] Choi K J, Lee Y H, Moon J W et al. Development of an automatic stencil inspection systemusing modified Hough transform and fuzzy logic. IEEE Trans. Industrial Electronics,2007,54(1):604-611.
[31] Chan C H, Pang G. Fabric defect detection by Fourier analysis. Industry Applications, IEEETransactions on,2000,36(5):1267-1276.
[32] Bovik A C, Clark M, Geisler W S. Multichannel texture analysis using localised spatial filters.IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(1):55-72.
[33] Vautrot P, Bonnet N, Herbin M. Comparative study of di9erent spatial/spatial-frequencymethods (Gabor filters, wavelets, wavelets packets) for texture segmentation classification.Proceedings of the1996IEEE International Conference in Image Processing, ICIP’96,1996,3:145-148.
[34] Weldon T P, Higgins W E, Dunn D F. Efficient Gabor filter design for texture segmentation.Pattern Recognition,1996,29(12):2005-2015.
[35] Mehrotra R, Namuduri KR, Ranganathan N. Gabor filter-based edge detection. PatternRecognition,1992,25(12):1479-1494.
[36] Casasent D, Smokelin JS. Neural net design of macro Gabor wavelet filters fordistortion-invariant object detection in clutter. Optical Engineering,1994,33(7):2264-2271.
[37] Mak K L, Peng P, Yiu K F C. Fabric defect detection using multi-level tuned-matched Gaborfilters. Journal of Industrial and Management Optimization,2012,8(2):325-341.
[38] Kumar A, Pang G K. H. Defect detection in textured materials using Gabor filters. IEEETransaction on Industry Applications,2002,38(2):425-440.
[39] Mak K L, Peng P. An automated inspection system for textile fabrics based on Gabor filters.Robotics and Computer-Integrated Manufacturing,2008,24(3):359-369.
[40] Bodnarova A, Bennamoun M, Latham S. Optimal Gabor filters for textile flaw detection.Pattern Recognition,2002,35(12):2973-2991.
[41] Mallat S G. A theory for multiresolution signal decomposition: the wavelet representation.IEEE Transactions on Pattern Analysis&Machine Intelligence,1989,11(7):674-693.
[42] Lu C S, Chung P C, Chen C F. Unsupervised texture segmentation via wavelet transform.Pattern Recognition,1997,30(5):729-742.
[43] Lambert G, Bock F. Wavelet methods for texture defect detection. Image Processing,1997.Proceedings, International Conference on. IEEE,1997,3:201-204.
[44] Yang X Z, Pang G K H, Yung N H C. Discriminative fabric defect detection using adaptivewavelets. Optical Engineering,2002,41(12):3116-3126.
[45] Tsai D M, Hsiao B. Automatic surface inspection using wavelet reconstruction. PatternRecognition,2001,34(6):1285-1305.
[46] Tsai D M, Chiang C H. Automatic band selection for wavelet reconstruction in the applicationof defect detection. Image and Vision Computing,2003,21(5):413-431.
[47] Sari-Sarraf H, Goddard J S. Vision system for on-loom fabric inspection, IEEE Transaction onIndustry Applications,1999,35(6):1252-1259.
[48] Han Y, Shi P. An adaptive level-selecting wavelet transform for texture defect detection. Imageand Vision Computing,2007,25(8):1239-1248.
[49] Yang X Z, Pang G K H, Yung N H C. Discriminative training approaches to fabric defectclassification based on wavelet transform. Pattern Recognition,2004,37(5):889-899.
[50] Truchetet F, Laligant O. Wavelets in industrial applications: a review. Optics East. InternationalSociety for Optics and Photonics,2004:1-14.
[51] Mufti M, Vachtsevanos G. Automated fault detection and identification using a fuzzy-waveletanalysis technique. AUTOTESTCON'95. Systems Readiness: Test Technology for the21stCentury. Conference Record. IEEE,1995:169-175.
[52] Sarraf H S, Goddard Jr J S. Robust Defect Segmentation in Woven Fabrics. Computer Visionand Pattern Recognition,1998. Proceedings.1998IEEE Computer Society Conference on.IEEE,1998:938-944.
[53] Haralick R M. Statistical and structural approaches to texture. Proceedings of the IEEE,1979,67(5):786-804.
[54] Basu M, Lin Z Y. Multi-scale Modeling of Texture. Pattern Recognition,1992. Vol. III.Conference C: Image, Speech and Signal Analysis, Proceedings,11th IAPR InternationalConference on. IEEE,1992:421-424.
[55] Hajimowlana S H, Muscedere R, Jullien G A et al.1D Autoregressive Modeling for DefectDetection in Web Inspection Systems. Circuits and Systems,1998. Proceedings.1998MidwestSymposium on. IEEE,1998:318-321.
[56] Geman S, Graffigne C. Markov random field image models and their applications to computervision. Proceedings of the International Congress of Mathematicians. AMS, Providence, RI,1986,1:2.
[57] Deng H, Clausi D A. Gaussian MRF rotation-invariant features for image classification. IEEETransactions on Pattern Analysis&Machine Intelligence,2004,26(7):951-955.
[58] Wang L, Liu J. Texture classification using multi-resolution Markov random field models.Pattern Recognition Letters,1999,20:171-182.
[59] Suen P H, Healey. Modeling and classifying color textures using random fields in a randomenvironment. Pattern Recognition,1999,32(6):1009-1017.
[60] zdemir S, Er il A. Markov random fields and Karhunen-Loève transforms for defectinspection of textile products. Emerging Technologies and Factory Automation,1996. EFTA'96.Proceedings,1996IEEE Conference on. IEEE,1996,2:697-703.
[61] Cohen F S, Fan Z G, Attali S. Automated inspection of textile fabric using textural models,IEEE Transaction on Pattern Analysis&Machine Intelligence,1991,13(8):803-808.
[62] Brzakovic D P, Bakic P R, Vujovic N S, et al. A generalized development environment forinspection of web materials. Robotics and Automation,1997. Proceedings,1997IEEEInternational Conference on. IEEE,1997,1:1-8.
[63] Brzakovi D P, Baki P R, Liakopoulos A. An approach to quality control of texture webmaterials. Photonics East'95. International Society for Optics and Photonics,1995:60-69.
[64] CampbellJ G, Fraley C, Murtagh F et al. Linear flaw detection in woven textiles usingmodel-based clustering. Pattern Recognition Letters,1997,18(14):1539-1548.
[65] Kassand R E, Raftery A E. Bayes factors. Journal of the american statistical association,1995,90(430):773-795.
[66] Kong K Y, Kittler J, Petrou M et al. Chromato-Structural approach towards surface defectdetection in random textured images. Proceedings of the SPIE.1994,2183:193-204.
[67] Pentland A P. Fractal-based description of natural scenes. IEEE Transactions on PatternAnalysis and Machine Intelligence,1984(6):661-674.
[68] Wen C Y, Chiu S H, Hsu W S et al. Defect segmentation of texture images with wavelettransform and a co-occurrence matrix, Textile Research Journal,2001,71(8):743-749.
[69] Amet1A L, Ertüzün A, Er il A. Texture defect detection using subband domain co-occurrencematrices. Image Analysis and Interpretation,1998IEEE Southwest Symposium on. IEEE,1998:205-210.
[70] Bu H G, Wang J, Tian C T. Optimum time series fractal features for inspection of woven fabricflaws. Program and Short Abstract of the10th Asian Textile conference,2009:93-96.
[71] Wang S Q, Zang X B, Guan Z Q. A new method of texture analysis based on wolddecomposition. Engineering of Surveying and Mapping,2006,15(1):20-23.
[72] Rowley H A, Baluja S, Kanade T. Neural network-based face detection. Pattern Analysis andMachine Intelligence, IEEE Transactions on,1998,20(1):23-38.
[73] Stojanovic R, Mitropulos P, Koulamas C et al. Real-time vision-based system for textile fabricinspection. Real-Time Imaging,2001,7(6):507-518.
[74] Kumar A. Neural network based detection of local textile defects. Pattern Recognition,2003,36(7):1645-1659.
[75] Kuo C F J, Lee C, Tsai C. Using a Neural Network to Identify Fabric Defects in Dynamic ClothInspection. Textile Research Journal,2003,73(3):238-244.
[76] Kuo C F J, Lee C. A back-propagation neural network for recognizing fabric defects. TextileResearch Journal,2003,73(2):147-151.
[77] Yin Y, Zhang K, Lu W. Textile Flaw Classification by Wavelet Reconstruction and BP NeuralNetwork. Advances in Neural Networks–ISNN2009. Springer Berlin Heidelberg,2009:694-701.
[78] Castiho H P, Goncalves P J S, Pinto J R C et al. Intelligent Real-time Fabric Defect Detection.Image Analysis and Recognition. Springer Berlin Heidelberg,2007:1297-1307.
[79] ZhangY, Lu Z, Li J. Fabric defect classification using radial basis function network. PatternRecognition Letters,2010,31(13):2033-2042.
[80] Tsai I S, Lin C H, Lin J J. Applying an artificial neural network to pattern recognition in fabricdefects. Textile Research Journal,1995,65(3):123-130.
[81] Karayiannis Y A, Stojanovic R, Mitropoulos P, et al. Defect Detection and Classification onWeb Textile Fabric using Multiresolution Decomposition and Neural Networks. Electronics,Circuits and Systems,1999. Proceedings of ICECS'99. The6th IEEE International Conferenceon. IEEE,1999,2:765-768.
[82] NeubauerC. Segmentation of Defects in Textile Fabric. Pattern Recognition,1992. Vol. I.Conference A: Computer Vision and Applications, Proceedings.11th IAPR InternationalConference on. IEEE,1992:688-691.
[83] HungC C, Chen I C. Neural-Fuzzy classification for fabric defects. Textile Research Journal.2001,71(3):220-224.
[84] Rohrmus D. Invariant web defect detection and classification system. Computer Vision andPattern Recognition,2000. Proceedings. IEEE Conference on. IEEE,2000,2:794-795.
[85] M enp T, Turtinen M, Pietik inen M. Real-time surface inspection by texture. Real-TimeImaging,2003,9(5):289-296.
[86] Lasińska J. Assessment of a Fabric Surface after the Pilling Process Based on Image Analysis.Fibres&Textiles in Eastern Europe,2009,2(73):55-58.
[87] Konda A, XIN L C, Takadera, et al. Evaluation of pilling by computer image analysis. Journalof the Textile Machinery Society of Japan,1990,36(3):96-107.
[88] Ramgulan R B, Amirbayat J, Porat I. The objective assessment of fabric pilling. Part I:Methodology. Journal of the Textile Institute,1993,84(2):221-226.
[89] Xu B. Instrumental evaluation of fabric pilling. Journal of the Textile Institute,1997,88(4):488-500.
[90] His H C, Bresee R R, Annis P A. Characterizing fabric pilling using image analysis techniques.Part I: Pill detection and description. Journal of the Textile Institute,1998,89(1):96-100.
[91] His H C, Bresee R R. Pilling evaluation of laboratory, abraded, laundered and worn fabricsusing image analysis. AATCC,1996:465-479.
[92] His H C, Bresee R R, Annis P A. Characterizing fabric pilling using image-analysis techniquespart I: pill detection and description. Journal of the Textile Institute,1998,89(1):80-95.
[93] Abril H C, Millan M S, Torres Y. Automatic method based on image analysis for pilling infabric. Optical Engineer,1998,37(6):1477-1488.
[94] Abril H C, Millan M S, Torres Y. Image synthesis of pilling textiles by Karhunen-Loevetransform.3rd Iberoamerican Optics Meeting and6th Latin American Meeting on Optics,Lasers, and Their Applications. International Society for Optics and Photonics,1999:254-258.
[95] Palmer S, Wang X. Objective classification of fabric pilling based on the two-dimensionaldiscrete wavelet transform. Textile Research Journal,2003,73(8):713-720.
[96] Hu J L, Xin B J. Image based modeling and analysis of textile materials. The InternationalSeries in Engineering and Computer Science,2004,762:283-307.
[97] Kim S C, Kang, T J. Image analysis of standard pilling photographs using waveletreconstruction. Textile Research Journal,2005,75(12):801-811.
[98] Sungmin Kim, Chang Kyu Park. Evaluation of fabric pilling using hybrid imaging methods.Fibers and Polymers,2006,7(1):57-61.
[99] Zhang J M, Wang X G, Palmer S. Objective grading of fabric pilling with wavelet textureanalysis. Textile Research Journal,2007,77(11):871-879.
[100] Zhang J M, Wang X G, Palmer S. Objective pilling evaluation of wool fabrics. TextileResearch Journal,2007,77(12):929-936.
[101] Zhang J M, Wang X G, Palmer S. The robustness of objective fabric pilling evaluationmethod. Fibers and Polymers,2009,10(1):108-115.
[102] Akiyama R, Iguro T, Uchiyama S, et al. Detection of weave types in woven fabrics byobserving optical diffraction pattern. J. Text. Mach. Soc. Japan,1989,35(2):1-4.
[103] Kinoshita M, Hashimoto Y, Akiyama R, et al. Determination of weave type in wovenfabric by digital image processing. Journal of the Textile Machinery Society of Japan,1989,35(2):1-4.
[104] Wood E J. Carpet texture measurement using image analysis. Textile Research Journal,1989,59(1):1-12.
[105] Ravandi S A H, Torumi K. Fourier transform analysis of plain weave fabric appearance.Textile Research Journal,1995,65(11):676-683.
[106] Xu B. Identifying fabric structure with fast Fourier transform techniques. Textile ResearchJournal,1996,66(8):496-506.
[107] Millan M S, Escoft J. Fourier-domain-based angular correlation for quasiperiodic patternrecognition applications to web inspection. Applied Optics,1996,35(31):6253-6260.
[108] Escoft J, Millan M S, Rallo M. Modeling of woven fabric structures based on Fourierimage analysis. Applied Optics,2001,40(34):6170-6176.
[109] Rallo M, Escoft J, Millan M S. Weave-repeat identification by structural analysis of fabricimage. Applied Optics,2003,42(17):3361-3372.
[110] Kang T J, Kim C H, Oh K W. Automatic recognition of fabric weave patterns by digitalimage analysis. Textile Research Journal,1999,69(2):77-83.
[111] Huang C C, Liu S C, Yu W H. Woven fabric analysis by image processing, PartI:Identification of weave patterns. Textile Research Journal,2000,70(6):481-485.
[112] Lin J J. Applying a co-occurrence matrix to automatic inspection of weaving density forwoven fabrics. Textile Research Journal,2002,72(6):486-490.
[113] Jeon B S, Bae J H, Suh M W. Automatic recognition of woven fabric patterns by anartificial neural network. Textile Research Journal,2003,73(7):645-650.
[114] Lachkar A, Gadi T, Benslimane R, et al. Textile woven-fabric recognition by using Fourierimage-analysis techniques. Part I: A fully automatic approach for crossed-points detection.Journal of the Textile Institute,2003,94(3):194-201.
[115] Lachkar A, Gadi T, Benslimane R, et al. Textile woven-fabric recognition by using Fourierimage-analysis techniques. Part II: Texture analysis for crossed-states detection. Journal of theTextile Institute,2005,96(3):179-183.
[116] Kuo C F J, Shih C Y, Lee J Y. Automatic recognition of fabric weave patterns by a fuzzyC-means clustering method. Textile Research Journal,2004,74(2):107-111.
[117] Jeong Y J, Jang J. Applying image analysis to automatic inspection of fabric density forwoven fabrics. Fibers and Polymers,2005,26(2):156-161.
[118] Zhang X, Gao W, Liu J. Automatic recognition of yarn count in fabric based on digitalimage processing. Image and Signal Processing,2008. CISP'08. Congress on. IEEE,2008,3:100-103.
[119] Tunák M, Linka A, Volf P. Automatic assessing and monitoring of weaving density.Fibers and Polymers,2009,10(6):830-836.
[120] Ajallouian F, Tavanai H, Palhang M, et al. A novel method for the identification of weaverepeat through image processing. Journal of the Textile Institute,2009,100(3):195-206.
[121] Pan R, Gao W, Liu J et al. Automatic recognition of woven fabric patterns based onpattern database. Fibers and Polymers,2010,11(2):303-308.
[122] Pan R, Gao W, Liu J et al. Automatic Inspection of Woven Fabric Density of Solid ColorFabric Density by the Hough Transform. Fibres&Textiles in Eastern Europe,2010,4(81):46-51.
[123] Wang X, Georganas N D, Petriu E M. Fabric Texture Analysis Using Computer VisionTechniques. I EEE Transactions on Instrumentation and Measurement,2011,60(1):44-56.
[1] Kumar A, Grantham K H P. Defect detection in textured materials using Gabor filters. IEEETransactions on Industry Applications,2002,38(2):425-440.
[2] Han L W, Xu D. Statistic learning-based defect detection for twill fabrics. International Journalof Automation and Computing,2010,7(1):86-94.
[3] Kula J, Tunak M, Linka A. Inspection system of fabric based on texture segmentation utilizingGabor filters.7th International Conference-TEXSCI2010.2010:6-8.
[4] Zhang Y. Automatic fabric defect detection and classification using machine learningtechnology. Xidian University Master’s Thesis,2010:8-23.
[5] Cord A, Jeulin D, Bach F. Segmentation of random textures by morphological and linearoperators.8th ISMM,2007:387-398.
[6] Teuner A, Pichler O, Hosticka BJ. Unsupervised texture segmentation of images using tunedmatched Gabor filters. IEEE Transactions on Image Processing,1995,4(6):863-870.
[7] Hou Z, Parker JM. Texture defect detection using support vector machines with adaptive Gaborwavelet features. Application of Computer Vision,2005. WACV/MOTIONS'05Volume1.Seventh IEEE Workshops on. IEEE,2005,1:275-280.
[8] Chaux C, Duval L, Pesquet J C. Image analysis using a dual-tree M-band wavelet transform.IEEE Transactions on Image Processing,2006,15(8):2397-2412.
[9] Guo H, Zhao J, Li X. Preprocessing method for NaXi pictographs character recognition usingwavelet transform. International Journal of Digital Content Technology and its Applications,2010,4(3):117-131.
[10] Chan C,Grantham KHP. Fabric defect detection by Fourier analysis. IEEE Transactions onIndustry Applications,2000,36(5):1267-1276.
[11] Bodnarova A, Bennamoun M, Latham S. Optimal Gabor filters for textile flaw detection.Pattern Recognition,2002,35(12):2973-2991.
[12] Ahmadyfard A, Alimohamadi H, Shariati A et al. A novel approach for detecting defects ofrandom textured tiles using Gabor wavelet. World Applied Sciences Journal,2009,7(9):1114-1119.
[13] Bianconi F, Fernandez A. Evaluation of the effects of Gabor filter parameters on textureclassification. Pattern Recognition,2007,40(12):3325-3335.
[14] Xue J H, Titterington D M. T-tests, F-tests and Otsu’s methods for image thresholding. IEEETransactions on Image Process2010;20:2392-2396.
[1] Ellingson W A, Steckenrider J S, Meitzler T J. Defect detection in ceramic armor using phasedarray ultrasound. Advances in Science and Technology,2010,65:143-152.
[2] Zhao J, Kong Q, Zhao X. A method for detection and classification of glass defects in lowresolution images. Image and Graphics (ICIG),2011Sixth International Conference on. IEEE,2011:642-647.
[3] Yang X, Qi D, Li X. Multi-scale edge detection of wood defect images based on the dyadicwavelet transforms. Machine Vision and Human-Machine Interface (MVHI),2010International Conference on. IEEE,2010:120-123.
[4] Srinivasan K, Dastoor P H, Radhakrishnaiah P, et al. FDAS: aknowledge based framework foranalysis of defects in woven textile structures. Journal of the textile institute,1992,83(3):431-448.
[5] Stojanovic R, Mitropulos P, Koulamas C, et al. An approach for automated defect detection andneural classification of web textile fabric. Mach Graph Vis,2000,9(3):587–607.
[6] Cohen F. S, Fan Z, Attalt S. Automated inspection of textile fabric using textural models. IEEETransactions on Pat-tern Analyses and Machine Intelligence,1991,13(8):345-350.
[7] Wen C Y, Chiu S H, Hsuw S. Defect segmentation of texture images with wavelet transformand a co-occurrence matrix. Textile Research Journal,2001,71(8):743-749.
[8] Kuo C F J, Su T L. Gray relational analysis for recognizing fabric defects. Textile ResearchJournal,2003,73(5):461-465.
[9] Latif-Amet A., Ertuzun A, Erci L A. Texture Defect Detection Using Subband DomainCo-occurrence Matrices. Image Analysis and Interpretation,1998IEEE Southwest Symposiumon. IEEE,1998:205-210.
[10] Latif-Amet A, Ertuzun A, Ercil A. An efficient method for texture defect detection: sub-banddomain co-occurrence matrices. Image and Vision Computing,2000,18(6):543-553.
[11] Chan C H, Pang G K H. Fabric defect detection by Fourier analysis. IEEE Transactions onIndustry Applications,2000,36(5):1267-1276.
[12] Tsai D M, Hsieh C Y. Automated surface inspection for directional textures. Image and VisionComputing,1999,18(1):49-62.
[13] Tsai D, Huang T. Automated surface inspection for statistical textures. Image and VisionComputing,2003,21(4):307-323.
[14] Sari-Sarrafh H, Goddard Jr J S. Vision system for on-loom fabric inspection, IEEE Transactionson Industry Application.1999,35(6):1252-1259.
[15] Yang X Z, Pang G K H, Yung N H C. Discriminative fabric defect detection using adaptivewavelet. Optical Engineer,2002,41(12):3116-3126.
[16] Liu X Z, Wen Z, Su Z, et al. Slub extraction in woven fabric images using Gabor filters. TextileResearch Journal,2008,78(4),320-325.
[17] Liu H, Han J. Defect Detection in Textiles Using Optimal Gabor Wavelet Filter. IntelligentControl and Automation,2006. WCICA2006. The Sixth World Congress on. IEEE,2006,2:10005-10007.
[18] Zhang Y, Lu Z, Li J. Fabric Defect Detection and Classification Using Gabor Filters andGaussian Mixture Model. Computer Vision–ACCV2009. Springer Berlin Heidelberg,2010:635-644.
[19] Randen T, Husoy J H, Schlumberger Geco-Prakla, et al. Filtering for texture classification: acomparative study. IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(4):291-310.
[20] Shady E, Gowayed Y, Abouiiana M, et al. Detection and Classification of Defects in KnittedFabric Structures. Textile Research Journal,2006,76(4):295-300.
[21] Ojala T, Pietikainen M, Maenpaa T. Multiresolution Gray-Scale and Rotation Invariant TextureClassification with Local Binary Patterns. IEEE Transactions on Pattern Analysis and MachineIntelligence,2002,24(7):971-987.
[22] Tamura H, Mori, S, Yamawaki T. Textural Features Corresponding to Visual Perception. IEEETransactions on Systems, Man and Cybernetics,1978,8(6):460-473.
[23] Workgroup on texture analysis of DFG, TILDA textile texture database. August,1996.(http://lmb.informatik.uni-freiburg.de/research/dfg-texture/tilda).
[1] K.L.Mak and P.Peng. Detecting defects in textile fabrics with optimal Gabor filters.International Journal of Computer Science,2006,1(4):274-282.
[2] Junjie Chen and Chunping Xie. Automatic cloth inspection system. Textile Science andTechnology Progress,2004,5:56-57.
[3] Junfeng Jing,Huanhuan Zhang,Pengfei Li and Jinyuan Jia. Fabric defect detection using Gaborfilters and defect classification based on LBP and Tamura method. The Journal of the TextileInstitute,2013,104(1):18-27.
[4] Yong Li and Yin Zhou. Automatic grey inspection technology based on machine vision. Journalof Textile Research,2007,28(8):124-128.
[5] Alfred Dockery. Automated fabric inspection: Assessing the current state of the art.techexchange.com,2001:1-4.
[6] Amit Rawal,Prasad Potluri and Colin Steele. Prediction of yarn paths in braided structuresformed on a square pyramid. Journal of Industrial Textiles,2007,36(3):221-226.
[7] Ajay Kumar. Computer vision-based fabric defect detection: A survey. IEEE Transactions onIndustrial Electronics,2008,55(1):348-363.
[8] Henry Y.T.Ngan, Grantham K.H.Pang and Nelson H.C.Yung. Automated fabric defectdetection-A review. Image and Vision Computing,2011,29(7):442-458.
[9] Xin Li and Zengpu Xu. Based on image energy fabric defect detection method. ComputerMeasurement and Control,2008,16(9):1243-1245.
[10] Zeng Y. Surface defects detection based on anisotropy of local fractal dimensions. Proceedingsof SPIE,2009,7506:75062E.
[11] B.S.Manjunath and R.Chellappa. Unsupervised texture segmentation using Markov RandomFiled Models.IEEE Transactions on Pattern Analysis,1991,13(5):478-482.
[12] Du-Ming Tsai and Shin-Min Chao. An anisotropic diffusion-based defect detection forsputtered surfaces with inhomogeneous textures. Image and Vision Computing,2005,23(3):325-338.
[13] Du-Ming Tsai and Chih-Chia Kuo. Defect detection in inhomogeneously textured sputteredsurfaces using3D Fourier image reconstruction. Machine Vision and Applications,2007,18(6):383-400.
[14] Arkady Cherkassky and Amotz Weinberg.Objective evaluation of textile fabric appearance part1: basic principles, protrusion detection, and parameterization. Textile Research Journal,2010,3(80):226-235.
[15] Xianghua Xie and Mirmehdi, M. TEXEMS: Texture Exemplars for Defect Detection onRandom Textured Surfaces. Pattern Analysis and Machine Intelligence,2007,29(8):1454-1464.
[16] D. Chetverikov. Pattern regularity as a visual key. Image and Vision Computing,2000,18(12):975-985.
[17] Rimac-Drlje S, Keller A and Nyarko K E. Self-Learning system for surface failure detection.EURASIP13th European Signal Processing Conference EUSIPCO,2005.
[18] A. Ahmadyfard,et al. A novel approach for detecting defects of random textured tiles usingGabor wavelet. World Applied Sciences Journal,2009,7(9):1114-1119.
[19] Khodaparast and A, Mostafa A. On line quality control of tiles using wavelet and statisticalproperties. Proceedings of the2nd Iranian Conference on Machine Vision and Image Processing,2003:153-159.
[20] Kumar A. Automated inspection of textured web materials using real Gabor functions. SecondInternational Conference on Image and Graphics. International Society for Optics andPhotonics,2002:298-302.
[21] Mostafavi Mahkameh S. A new method in detection of ceramic tiles color defects using geneticC-means algorithm. Proceeding of World Academy of Science, Engineering and Technology,2006:168-171.
[22] Chin R T. Automated visual inspection:1981to1987. Computer Vision, Graphics, and ImageProcessing,1988,41(3):346-381
[23] Du-Ming and Tsai, Ya-Hui Tsai.Rotation-invariant pattern matching with color ring-projection.Pattern Recognition,2002,35(1):131-141.
[24] YH Zhang, CWM Yuen, WK Wong and Chi-wai Kan. An intelligent model for detecting andclassifying color-textured fabric defects using genetic algorithms and the Elman neural network.Textile Research Journal,2011,81(17):1772-1787.
[25] Ngan H Y T, Pang G K H, and Yung S P, et al. Defect detection on patterned jacquard fabric.Applied Imagery Pattern Recognition Workshop,2003. Proceedings.32nd. IEEE,2003:163-168.
[26] Ngan H Y T and Pang G K H. Novel method for patterned fabric inspection using Bollingerbands. Optical Engineering,2006,45(8):087202-087202-15
[27] Ngan H Y T and Pang G K H. Regularity analysis for patterned texture inspection. AutomationScience and Engineering, IEEE Transactions on,2009,6(1):131-144.
[28] Jaume Escofet,Rafael Navarro and Mar S.Milla'n. Detection of local defects in textile websusing Gabor filters. SPIE Digital Library,1998,37(8):2297-2307.
[29] Mheidat H, Uysal M and Al-Dhahir N. Equalization techniques for distributed space-time blockcodes with amplify-and-forward relaying. Signal Processing, IEEE Transactions on,2007,55(5):1839-1852.
[30] Reddy R O K, Reddy B E and Reddy E K. Texture analysis and defect classification for fabricimages using regular bands and quadratic programming. Proceedings of InternationalConference on Advances in Computing. Springer India,2012:927-934.
[31] Zeeshan Khatri, Muhammad Hanif Memon, Awais Khatri and Anwaruddin Tanwari. ColdPad-Batch dyeing method for cotton fabric dyeing with reactive dyes using ultrasonic energy.Ultrasonics Sonochemistry,2011,18(6):1301-1307.
[32] Workgroup on texture analysis of DFG, TILDA textile texture database. August,1996.(http://lmb.informatik.uni-freiburg.de/research/dfg-texture/tilda).
[33] Kula J, Tunak M and Linka A. Inspection system of fabric based on texture segmentationutilizing Gabor filters.7th International Conference–TEXSCI2010,2010:6-8.
[34] Ani1K.Jain and F Farrokhnia. Unsupervised texture segmentation using Gabor filters. Patternrecognition,1991,24(12):14-19.
[35] Jianwei Yang, Lifeng Liu,Tianzi Jiang et al. A modified Gabor filter design method forfingerprint image enhancement. Pattern Recognition Letters,2003,24(12):1805-1817.
[36] Junfeng Jing, Hang Li and Pengfei Li. Combined fabric defects detection approach andquadtree decomposition. Journal of Industrial Textiles,2012,41(4):331-344.
[37] Stephanie Forrest. Genetic algorithms: principles of natural selection applied to computation.Science,1993,261(5123):872-878.
[38] Lingming Zhang. Fabric Defect Detection Method and Its Software Design Based On DM642Image Processing System. Beijing Institute of Fashion Technology, Thesis applying for MasterDegree,2008.
[39] Juliang Jin, Xiaohua Yang and Jing Ding. An improved simple genetic algorithm—acceleratinggenetic algorithm. System Engineering Theory and Practice,2001,(4):8-13.
[40] Qiwen Yang and Jinping Jiang. Genetic algorithm used to optimize the improvement of speed.Journal of Software,2001,12(2):270-275.
[41] K.L.Mak and P.Peng. An automated inspection system for textile fabrics based on Gabor filters.Robotics and Computer-Integrate Manufacturing,2008,24(3):359-369.
[42] Bo Qu and Zhaoyang Lu. Fabric defect detection with an improved multichannel Gabor filter.Journal of Textile Research,2009,30(12):37-40.
[43] Ajay Kumar and Grantham K.H.Pang. Defect detection in textured materials using Gabor filters.IEEE Transactions on Industry Applications,2002,38(2):425-439.
[44] Kai-Ling Mak and Pai Peng. Fabric defect detection using multi-level tuned-matched Gaborfilters. Journal of Industrial and management optimization,2012,8(2):325-341.
[1] Yap P H, Wang X, Wang L, et al. Prediction of wool knitwear pilling propensity using supportvector machines. Textile Research Journal,2010,80(1):77-83.
[2] Tortora P G and Collier B J. Understanding Textiles. Prentice-Hall, Englewood Cliffs, NewJersey, United States,1997.
[3] Deng Z, Wang L，Wang X. An integrated method of feature extraction and objective evaluationof fabric pilling. J Text Inst,2011,102(1):1-13.
[4] Amirbayat J，Alagha M J. The objective assessment of fabric pilling-Part II: experimentalwork. J Text Inst,1994,85(3):397-401.
[5] Xu B. Instrumental evaluation of fabric pilling. J Text Inst,1997,88(4):488-500.
[6] Abril H C, Millan M S, Torres Y, et al. An automatic method based on image analysis for pillingevaluation in fabrics. Opt Eng,1998,37(11):2937-2947.
[7] Sirikasemleert A，Tao X. Objective evaluation of textural changes in knitted fabrics by lasertriangulation. Textile Research Journal,2000,70(12):1076-1087.
[8] Chen X，Huang X B. Evaluating fabric pilling with light-projected image analysis. Text Res J,2004,74(11):977-981.
[9] Palmer S，Wang X. Objective classification of fabric pilling based on the two-dimensionaldiscrete wavelet transform. Textile Research Journal,2003,73(8):713-720.
[10] Mallat S G. A theory for multiresolution signal decomposition: the wavelet representation. IEEETrans Pattern Anal Mach Intell,1989,11(7):674-693.
[11] Wen C Y, Chiu S H, Hsu W S, et al. Defect segmentation of texture images with wavelettransform and a co-occurrence matrix. Textile Research Journal,2001,71(8):743-749.
[12] Tsai D M，Chiang C H. Automatic band selection for wavelet reconstruction in the applicationof defect detection. Image Vision Computer,2003,21(5):413-431.
[13] Lu C S, Chung P C, Chen C F. Unsupervised texture segmentation via wavelet transform.Pattern Recognit,1997,30(5):729-742.
[14] Bashar M K, Matsumoto T, Ohnishi N. Wavelet transform-based locally orderless images fortexture segmentation. Pattern Recognition Letters,2003,24(15):2633-2650.
[15] Zhang J, Wang X，Palmer S. Objective pilling evaluation of wool fabrics. Text Res J,2007,77(12):929-936.
[16] Ojala T, Pietikainen M，Maenpaa T. Multi-resolution gray-scale and rotation invariant textureclassification with local binary patterns. IEEE Trans Pattern Anal Mach Intell,2002,24(7):971-978.
[17] Ahonen T, Hadid A, Pietikainen M. Face description with local binary patterns: application toface recognition. IEEE Trans Pattern Anal Mach Intell,2006,28(12):2037-2041.
[18] Shen K Q, Ong C J, Li X P, et al. Feature selection using SVM probabilistic outputs. NeuralInformation Processing. Springer Berlin Heidelberg,2006:782-791.
[19] Mavroforakis M E，Theodoridis S. A geometric approach to support vector machine (SVM)classification. IEEE Trans Neural Networks,2006,17(3):671-682.
[1] J.L. Hu. Textile classification based on Bayesian approach, Journal of Textile Research2004,25(1):48-49.
[2] C.Y. Shih and J.Y. Lee. Automatic recognition of fabric weave patterns by a fuzzy C-meansclustering method, Textile Research Journal2004,74(2):107-111.
[3] C.F.J. Kuo,C.Y. Shin,C.E Ho and K.C. Peng. Application of computer vision in the automaticidentification and classification of woven fabric weave patterns, Textile Research Journal2010,80(20):2144-2157.
[4] X. Wang, N.D. Georganas and E.M. Petriu. Fabric Texture Analysis Using Computer VisionTechniques, Instrumentation and Measurement, IEEE Transactions on2011,60(1):44-56.
[5] Y.Ben Salem, S. Nasri and R. Tourki. Classification of tissues by neural network,12th IEEEInternational Conference Electronics Circuits and Systems, Proceeding of ICECS2005:1-4.
[6] B.S. Jeon, J.H. Bae and M.W. Suh. Automatic recognition of woven fabric patterns by anartificial neural network, Textile Research Journal2003,73(7):645-650.
[7] C.F.J. Kuo and C.C. Tsai. Automatic recognition of fabric nature by using the approach oftexture analysis, Textile research journal2006,76(5):375-382.
[8] Y.B. Salem and S. Nasri. Automatic recognition of woven fabrics based on texture and usingSVM, Signal, image and video processing2010,4(4):429-434.
[9] M. Hanmandlu, D. Sujata and Choudhury D K. Fabric image defect detection by using GLCMand ROSETTA, International Journal Of Computer Science And Applications2009,2(1):47-50.
[10] J.F. Jing, J. Wang, P.F. Li and Y. Li. Automatic Classification of Woven Fabric Structure byUsing Learning Vector Quantization, Procedia Engineering2011,15:5005-5009.
[11] R.M. Haralick, K. Shanmugam and I.H. Dinstein. Textural features for image classification,IEEE Transactions Systems, Man and Cybernetics1973,3(6):610-621.
[12] G.M. Haley and B.S. Manjunath. Rotation invariant texture classification using modified Gaborfilters, Image Processing1995. Proceedings., International Conference on. IEEE1995,1:262-265.
[13] J.Y. Yan, C.R. Wang and Y.X. Wang. Image Retrieval based on Texture Features, Network andComputer Security2010,12:46-48.
[14] X.A. Zhu and L. Cao. Wavelet Analysis and Its Application in Digital Image Processing,Beijing, Publishing House Of Electronics Industry2012.
[15] Z. Zhang, Y.P. Wang and G.X. Xue. Digital image processing and machine vision, Beijing, Postsand Telecom Press2012.
[16] D.F. Specht. Probabilistic Neutral Networks, Neural Networks1990,3(1):109-118.
[17] J. Iounousse, A. Farhi, H.Chehouanil and S. Erraki. Unsupervised classification of grayscaleimage using Probabilistic Neural Network (PNN)[C], Multimedia Computing and Systems(ICMCS),2012International Conference on. IEEE,2012:101-105.
