基于纹理梯度的纺织品缺陷检测方法研究
|
摘要
纺织品缺陷检测是纺织品工业生产中必要且重要的环节。人工方式的纺织品缺陷检测,其检测质量的好坏严重地依赖于主观经验、判断力和注意力。在现代纺织品工业中,纺织品自动检测正在逐步取代人工视觉检测方法。纺织品自动检测的主要目标是能够有效地提取纺织品缺陷,且对缺陷区域进行准确定位。近年来,纹理梯度是图像分割的热点问题,在纹理梯度图像中能够准确地分辨出不同类别纹理的边界。因此,本文通过采用纹理梯度算法,研究提出了一种新的有效的纹理缺陷检测方法,并且,将该方法进一步用于实际的纺织品缺陷的检测中。主要研究内容如下:
1研究建立基于纹理梯度的纹理图像分割方法。通过结合纹理梯度和标记分水岭,构造出一种纹理图像分割算法——简单的纹理分水岭算法。在此基础上,为了消除成像噪声及不相关细节的影响,突出纹理间的差异,在进行纹理分水岭分割之前,先采用非局部均值滤波实现纹理增强,构造基于纹理增强的纹理分水岭算法,能够获得更加准确的纹理缺陷检测结果。
2研究建立基于纹理梯度的MRF纹理缺陷检测方法。通过分析MRF模型,提出了基于纹理梯度的MRF纹理缺陷检测方法,克服了基于纹理分水岭的纹理缺陷检测方法需要人工设定阈值的弊端。该检测过程先进行纹理增强,再计算纹理梯度,最后利用Markov随机场模型高自动化地完成纹理缺陷检测。
3研究建立基于纹理梯度的纺织品检测方法。将三种基于纹理梯度的纹理缺陷检测方法,即简单的纹理分水岭算法、基于纹理增强的纹理分水岭算法和基于纹理梯度的MRF算法分别用于实际的纺织品缺陷图像的检测,并比较各方法的优缺点。实验结果表明,简单的纹理分水岭算法能够实现对于纹理差异较明显,即检测难度较小的纺织品缺陷的检测,且速度较快。但是对于检测难度较大的纺织品缺陷图像,基于纹理增强的纹理分水岭算法的检测效果较好,但缺点是耗时较长。基于纹理梯度的MRF算法能够实现高自动化地纺织品缺陷检测,且也能有效提取出纺织品缺陷区域,缺陷边界定位准确。
In the textile industry, quality control is of vital importance for fabric products. Currently, the inspection task is primarily performed by human inspectors and hence heavily relies on their experience, judgement and attention. Automated inspection of the fabric defects is becoming an attractive alternative to the human visual inspection in modern textile industry. The main goal of fabric automated inspection is able to precisely locate the defect regions in the fabric. In recent years, texture gradientis a popular tool for image segmentation that considerally improves contour detection performance, and it is further used in the inspection of fabric defects. The main work is as follows:
1. To develop a texture image segmentation method based on texture gradient. Based on texture gradient and marker-based watershed, simple texture watershed is designed for texture image segmentation. In order to reduce noise (which in a general sense includes fine texture and non-stationary behaviors), nonlocal means (NL-means) filter is used for enhancing the differences between the defect texture and background texture. Combined with the texture watershed transform, it is called texture watershed based on texture enhancemence. The defect regions in fabric images can be defected accurately in this method.
2. To develop a method for texture defect detection based on texture gradient and MRF. By analyzing the model of MRF, the automated texture defect detection based texture gradient and MRF is proposed to overcome the drawback of simple texture watershed. In this method, Markov random field model is used in the final segmentation, followed by the texture enhancemence and texture gradient.
3. To develop a method for fabric defect detection based on texture gradient. The three methods based on texture gradient are used in the inspection of fabric defects. Experiment results have demonstrated that simple texture watershed can get fast and accurate result of fabric image containing obviously different texture. The texture watershed based on texture enhancement can get accurate result of more difficultly defected fabric image, but it costs more time. The detection based on texture gradient and MRF model can get accurate result automatically.
1研究建立基于纹理梯度的纹理图像分割方法。通过结合纹理梯度和标记分水岭,构造出一种纹理图像分割算法——简单的纹理分水岭算法。在此基础上,为了消除成像噪声及不相关细节的影响,突出纹理间的差异,在进行纹理分水岭分割之前,先采用非局部均值滤波实现纹理增强,构造基于纹理增强的纹理分水岭算法,能够获得更加准确的纹理缺陷检测结果。
2研究建立基于纹理梯度的MRF纹理缺陷检测方法。通过分析MRF模型,提出了基于纹理梯度的MRF纹理缺陷检测方法,克服了基于纹理分水岭的纹理缺陷检测方法需要人工设定阈值的弊端。该检测过程先进行纹理增强,再计算纹理梯度,最后利用Markov随机场模型高自动化地完成纹理缺陷检测。
3研究建立基于纹理梯度的纺织品检测方法。将三种基于纹理梯度的纹理缺陷检测方法,即简单的纹理分水岭算法、基于纹理增强的纹理分水岭算法和基于纹理梯度的MRF算法分别用于实际的纺织品缺陷图像的检测,并比较各方法的优缺点。实验结果表明,简单的纹理分水岭算法能够实现对于纹理差异较明显,即检测难度较小的纺织品缺陷的检测,且速度较快。但是对于检测难度较大的纺织品缺陷图像,基于纹理增强的纹理分水岭算法的检测效果较好,但缺点是耗时较长。基于纹理梯度的MRF算法能够实现高自动化地纺织品缺陷检测,且也能有效提取出纺织品缺陷区域,缺陷边界定位准确。
In the textile industry, quality control is of vital importance for fabric products. Currently, the inspection task is primarily performed by human inspectors and hence heavily relies on their experience, judgement and attention. Automated inspection of the fabric defects is becoming an attractive alternative to the human visual inspection in modern textile industry. The main goal of fabric automated inspection is able to precisely locate the defect regions in the fabric. In recent years, texture gradientis a popular tool for image segmentation that considerally improves contour detection performance, and it is further used in the inspection of fabric defects. The main work is as follows:
1. To develop a texture image segmentation method based on texture gradient. Based on texture gradient and marker-based watershed, simple texture watershed is designed for texture image segmentation. In order to reduce noise (which in a general sense includes fine texture and non-stationary behaviors), nonlocal means (NL-means) filter is used for enhancing the differences between the defect texture and background texture. Combined with the texture watershed transform, it is called texture watershed based on texture enhancemence. The defect regions in fabric images can be defected accurately in this method.
2. To develop a method for texture defect detection based on texture gradient and MRF. By analyzing the model of MRF, the automated texture defect detection based texture gradient and MRF is proposed to overcome the drawback of simple texture watershed. In this method, Markov random field model is used in the final segmentation, followed by the texture enhancemence and texture gradient.
3. To develop a method for fabric defect detection based on texture gradient. The three methods based on texture gradient are used in the inspection of fabric defects. Experiment results have demonstrated that simple texture watershed can get fast and accurate result of fabric image containing obviously different texture. The texture watershed based on texture enhancement can get accurate result of more difficultly defected fabric image, but it costs more time. The detection based on texture gradient and MRF model can get accurate result automatically.
引文
[1] K. Srinivasan, P. H. Dastor, P. Radhakrishnaihan and S. Jayaraman. FDAS: A Knowledge-based Frame Detection Work for Analysis of Defects in Woven Textile Structures [J].Journal of Textile Institute, vol. 83, pp.431-447,1992.
[2] B. Nickolay, K. Schicktanz and H. Schmalfub.Automatic Fabric Inspection- Utopia or Reality? [J]. Translation of Melliand Textilberichte, vol. 1, pp.E33-E37, 1993.
[3] B. Smith.Making War on Defects [J]. IEEE Spectrum, vol. 30, no. 9, pp.43-47, 1993
[4] R. Meylani, A. Ertuzun, and A. Ercil.Texture Defect Detection Using the Adaptive Two-dimensional Lattice Filter [C].Proceedings of IEEE International Conference on Image Processing, vol. 3, pp. 165-168,1996.
[5] M. Mufti.Fault Detection and Identification Using Fuzzy Wavelets [D]. Ph. D. Thesis, School of Electrical and Computer Engineering, Georgia Institute of Technology, 1995.
[6] H. Sari-Sarraf and J. S. Goddard.Vision system for on-loom fabricinspection [J].IEEE Transactions on Industrial Applications, vol. 35, no. 6, pp. 1252-1259,1999.
[7] R. Stojanpvic, M. Panagiotis, K. Christos, K. Yorgos, K. Stavros and P. George. Real-Time Vision-Based System for Textile Fabric Inspection [J].Real-Time Imaging, vol. 7,pp.507-518,2001.
[8] C. Neubauer.Segmentation of defects in textile fabric[C].Proceedings of IEEE International Conference on Pattern Recognition, vol. 1, pp. 688-691,1992.
[9] A.L. Amet, A.Ertuzun, A.Ercil.An Efficient Method for Texture Defect Detection: Sub-band Domain Co-occurrence Matrices [J].Image and Vision Computing, vol. 18, pp543-553,2000.
[10]Y. F. Zhang and R. R. Bresee.Fabric defect detection and classification using image analysis [J].Textile Research Journal, vol. 65, no. 1, pp.1-9, 1995.
[11]C. Fernandez, S. Fernandez, P. Campoy, R.Aracil.On-line Texture Analysis for Flat Products Inspection. Neural Nets Implementation[C].Proceedings of 20th IEEE International Conference on Industrial Electronics, Control and Instrumentation, vol. 2, pp. 867-872,1994.
[12]D. Chetverikov.Detecting Defects in Texture[C].Proceedings of 9th IEEE International Conference on Pattern Recognition, vol. 1, pp.61-63, 1988.
[13] J. Escofet, R. Navarro, and M. S. Millan.Detection of local defects in textile webs using Gabor filters [J].Optical Engineering, vol. 37, no. 8, pp.2297-2307, 1998.
[14]Y. F. Zhang and R. R. Bresee.Fabric defect detection and classification using image analysis [J].Textile Research Journal, vol. 65, no. 1, pp.1-9, 1995.
[15]A.L. Amet, A.Ertuzun, A.Ercil.An Efficient Method for Texture Defect Detection: Sub-band Domain Co-occurrence Matrices [J].Image and Vision Computing, vol. 18, pp543-553, 2000.
[16]S. Ozdemir, A. Baykut, R. Meylani, A. Ercil and A.Ertuzun.Comparative Evaluation of Texture Analysis Algorithms For Defect Inspection of Textile Products [C].Proceedings of the IEEE 14th International Conference on Pattern Recognition, vol. 2, pp 173 8-1740, 1998.
[17]F. Ade, N. Lins and M. Unser.Comparison of various filter sets for defect detection in textiles[C].Proceedings of 7th International Conference in Pattern Recognition, pp.428-431,1984.
[18]P. Dewaele, P. Van Gool and A. Oosterlinck.Texture Inspection with Self-Adaptive Convolution Filters[C].Proceedings of 9th International Conference in Pattern Recognition, pp.56-60, 1988.
[19]Z. Fazekas, J. Komuves, I. Renyi and L. Surjan.Automatic Visual Assessment of Fabric Quality[C].Proceedings of IEEE International Symposium on Industrial Electronics, vol. 1, pp. 178-182,1999.
[20] R. Meylani, A. Ertuzun, and A. Ercil.Texture Defect Detection Using the Adaptive Two-dimensional Lattice Filter[C]. Proceedings of IEEE International Conference on Image Processing, vol. 3, pp. 165-168,1996.
[21]S. Ozdemir, A. Ercil.Markov random fields and Karhunen-Loeve transforms for defect inspection of textile products [C].IEEE Conference on Emerging Technologies and Factory Automation, Vol.2, pp.697-703,1996.
[22]C. H. Chan and G. Pang.Fabric defect detection by Fourier analysis [J].IEEE Transactions on Industrial Application, vol. 36, no. 5, pp.1267-1276,2000.
[23]C. Ciamberlini, F. Francini, P. Sansoni, and B.Tiribilli.Defect detection in textured materials by optical filtering with structured detectors and self adaptable masks [J].Optical Engineering, vol. 35, no. 3, pp.838-844, 1996.
[24]D. M. Tsai and C. Y. Hsieh.Automated Surface Inspection for Directional textures [J]. Image and Vision Computing, vol. 18, pp. 49-62, 1999.
[25]YuNan Gong.Study on image analysis of fabric defects.Ph.D. dissertation [D].China Textile University, Shanghai, China, 1999.
[26]J. Escofet, R. Navarro, and M. S. Millan.Detection of local defects in textile webs using Gabor filters [J]. Optical Engineering, vol. 37, no. 8, pp.2297-2307, 1998.
[27]A. Kumar and G. Pang.Defect detection in textured materials using Gabor filters [C]. Proceedings of IEEE International Conference on Industry Application, vol. 2, pp.1041-1047, 2000.
[28]H.Sari-Sarraf and J.S.Goddard.Vision system for on-loom fabricinspection[J].IEEE Transactions on Industrial Applications,vol.35,no.6,pp.1252-1259,1999.
[29]M.Mufti.Fault Detection and Identification Using Fuzzy Wavelets[D].Ph.D.Thesis,School of Electrical and Computer Engineering,Georgia Institute of Technology,1995.
[30]J.L.Dorrity and G.Vachtsevanos.On-line Defect Detection For Weaving Systems [C].Proceedings of IEEE Technical Conference on Textile,Fiber and Film Industry,pp.1-6,1996.
[31]S.Kim,M.H.Lee and K.B.Woo,Wavelet analysis to fabric defects detection in weaving processes[C].Proceedings of IEEE International Symposium on Industrial Electronics,vol.3,pp.1406-14.09,1999.
[32]G.Lambert and F.Bock.Wavelet methods for texture defect detection[C].Proceedings of IEEE International Conference on Image Processing,vol.3,pp.201-204,1997.
[33]W.J.Jasper,S.J.Garnier and H.Potlapalli.Texture characterization and defect detection using adaptive wavelets[J].Optical Engineering,vol.35,no.11,pp.3140-3149,1996.
[34]朱述龙,张占睦遥感图像获取与分析[M].北京:科学出版社.2000.
[35]赵鹏,曹军,浦昭邦等.基于图像融合的运动目标轮廓提取新方法团.光电子.激光,2005,16(8):973-977
[36]刘振华,毛士艺,袁运能.SAR图像组合分割算法[J].电子学报,2003,31(6):833-836.
[37]TianB,Sh aikhM A,Azimi-SadjadiM R,etal.A Study of Cloud Classification With Neural Network s Using Spectral and Textural Features[J].IEEE Trans.Neural Networks,1999,10(1):138-151.
[38]TianL F,Slaughter D C.Environmentally,adaptive segmentation algorithm for outdoor image segmentation[J],Computers and Electronics in Agriculture,1998,21(3):153-168.
[39]Marques J S,Jorge P M.Visual inspection of a combustion process in a thermoelecirc plant[J].IEEE Trans.Signal Processing,2000,80(13):1577-1589.
[40]Zhang Y,Brady M,Smith S.Segmentation of brain MR images through a hidden MarkovRandom field model and the e xpectation-maximization algorithm[J].IEEE Trans.Medical Imaging,2001,20(1):45-57.
[41]沈晶,杨学志[J].一种新的基于纹理分水岭的纺织品缺陷检测方法[J].中国图像图形学报,已录用
[42]章毓晋.图像分割[M].北京:科学出版社,2001,1-7
[43]沈兰荪,王爱民.图像分割的分级性研究[J].北京工业大学学报,2000,26(3):33-38
[44]W.Y.Ma and B.S.Manjunath.Edgeflow:A technique for boundary detection and image segmentation[J].IEEE Trans.Image Processing,2000,vol.9,no.8
[45]H. T. Nguyen, M. Worring, and R. van den Boomgaard.Watersnakes: Energy-driven watershed segmentation [J]. IEEE Trans. Pattern Anal. Machine Intell, 2003, vol. 25, no. 3
[46]R. Adams and L. Bischof.Seeded region growing [J]. IEEE Trans.Pattern Anal. Machine Intell, 1994, vol. 16, no. 6
[47]T. F. Cootes, C. J. Taylor, D. H. Cooper, and J. Graham.Active shape models - their training and application[J].Computer Vision and Image Understanding, 1995, vol. 61, no. 1, pp. 38-59
[48]M. Kass, A. Witkin, and D. Terzopoulos. Snakes: Active contour models[J]. Int'1 J. Computer Vision, 1987, vol. 1, no. 4, pp, 321-331
[49]P. Hill, C. Canagarajah and D. Bull. Image segmentation using a texture gradient-based watershed transform [J]. IEEE Trans. Image Process, vol. 12, no. 12, pp. 1618-1633, Dec. 2003.
[50]P. Hill, C. Canagarajah, and D. Bull.Texture gradient based watersheds egmentation [C]. Proc.Int. Conf. Acoustics, Speech and Signal Processing, vol. 4, pp. 3381-3384, 2002.
[51]A. K. Jain and F. Farrokhnia, "Unsupervised texture segmentation using Gabor filters," Pattern Recognit., vol. 23, pp. 1167-1186,1991.
[52]W. E. Higgins, T. P. Weldon, and D. F. Dunn. Gabor filter design for multiple texture segmentation [J]. Opt. Eng., vol. 35, no. 10, pp.2852-2863, Oct. 1996.
[53]N.W. Campbell and B. T. Thomas.Automatic selection for Gabor filters for pixel classification[J]. in Proc. 6th Int. Conf. Image Processing and its Applications, 1997, pp. 761-765.
[54]S. Mallat.A wavelet tour of signal processing [M]. Academic Press, 2nd ed., San Diego, 1999.
[55]A. Laine and J. Fan. Frame representations for texture segmentation [J]. IEEE Transactions on Image Processing, vol. 5, no. 5, pp. 771-780, May, 1996.
[56]Z. Cvetkovic and M. Vetterli.Discrete-time wavelet extrema representation: design and consistent reconstruction [J]. IEEE Transactions on Signal Processing, vol. 3, pp. 681-693,1995.
[57]Z. Cvetkovic and M. Vetterli. Oversampled filter banks [J].IEEE Transactions on Signal Processing, vol. 46, no. 5, pp. 1245-1255, Mar. 1998.
[58]M. Unser. Texture classification and segmentation using wavelet frames [J].IEEE Transactions on Image Processing, 4(11), 1549-1560 (1995).
[59]S. Mallat and S. Zhong. Characterization of signals from multiscale edges [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 7, pp. 710-732, July,1992.
[60]S.Mallat and W.L.Hwang.Singularity detection and processing withwavelets[J].IEEE Transactions on Information Theory,vol.38,no.2,pp.617-643,Mar.,1992.
[61]J.Canny.A computational approach to edge detection[J].IEEE Trans.Pattern Anal.Machine Intell.,Vol.8,pp.269-285,Nov.1986.
[62]张文炬,苏清祖.基于小波分析的多通道信息融合技术的研究[J].振动、测试与诊断,2002,(02):102-106
[63]潘泉,于昕,程咏梅,张洪才.信息融合理论的基本方法与进展[J].自动化学报,2003,(04):601-615
[64]Vincent L,Soille P.Watersheds in digital spaces:all eficient algorithm based on immersion simulations[J].IEEE Trans on Pattern Analysis and Machine Intelligence,1991,13(6):583-598
[65]Sonka M,Hlavac V,Boyle R.Image Processing,Analysis,and Machine Vision[M].2~(nd) ed.Books/Cole Publishing,pp.506-507,1999
[66]S.Kothainachiar,R.S.D.Wahita Banu,A.Saravanan,Unsupervised Morphological Segmentation for Textured and Non-Textured Images,GVIP[J],2006,09,6(02):33-39
[67]J.S.Lee.Digital image enhancement and noise filtering by use of local statistics[J].IEEE Trans.Pattern Anal.Mach.Intell.,vol.PAMI-2,pp.165-168,1980.
[68]D.T.Kuan,A.Sawchuk,T.Strand and P.Chavel.Adaptive restoration of images with speckle[J].IEEE Trans.ASSP,Vol.35,no.3,pp.373-383,March 1987.
[69]V.S.Frost,J.A.Stiles,K.S.Shanmugan and J.C.Holtzman.A model for radar images and its application to adaptive digital filtering of multiplicative noise[J].IEEE Trans.Pattern Anal.Math.Intell.,vol.4,no.2,pp.157-166,March 1982.
[70]A.Lopes,E.Nezry,R.Touzi and H.Laur.Maximum a posteriori speckle filtering and first order texture models in SAR images[C].Proc.IGARSS,vol.3,pp.2409-2412,1990.
[71]A.Lopes,R.Touzi and E.Nezry.Adaptive speckle filters and Scene heterogeneity[J].IEEE Trans.Geosci Remote Sensing,vol.28,no.6,pp.992-1000,1990.
[72]J.S.Lee.Refined filtering of image noise using local statistics[J].Computer Graphic and Image Processing,vol.15,pp.380-389,1981.
[73]Y.Yu and S.T.Acton.Speckle reducing anisotropic diffusion[J].IEEE Trans.Image Processing,vol.11,no.11,pp.1260-1270,2002.
[74]K.Krissian,C.F.Westin,R.Kikinis and K.G.Vosburgh.Oriented speckle reducing anisotropic diffusion[J].IEEE Trans.Image Processing,vol.16,no.5,pp.1412-1424,2007.
[75]H.Xie,L.E.Pierce and F.T.Ulaby.SAR speckle reduction using wavelet denoising and markov random field modeling[J].IEEE Trans.Geosci Remote Sensing,vol.40,no.10,pp.2196-2211,2002.
[76]Y.Dong,A.K.Milne and B.C.Forster.Toward edge sharpening:a SAR speckle filtering algorithm[J].IEEE Trans.Geosci Remote Sensing,vol.39,no.4,pp.851-863,2001.
[77]M.Walessa and M.Datcu.Model-based despeckling and information extraction from SAR images[J].IEEE Trans.Geosci Remote Sensing,vol.38,no.6,pp.2258-2269,2000.
[78]H.Li,W.Hong,Y.Wu and H.Tai.Texture-preserving despeckling of SAR images using evidence framework[C].IEEE.Geosci Remote Lett,vol.4,no.4,pp.537-541,2007.
[79]A.Buades,B.Coll and J.M.Morel.Image denoising by non-local averaging[C].Proc.IEEE Int'l Conf.Acoustics,Speech and Signal Processing,vol.2,pp.25-28,2005.
[80]A.Buades,B.Coll and J.M.Morel.A review of image denoising algorithm,with a new one[J].Multiscale Modeling and Simulation,vol.4,no.2,pp.490-530,2005.
[81]H.Xie,E.P.Leland and F.T.Ulaby.Statistical properties of logarithmically transformed speekle[J].IEEE Trans.Geosci Remote Sensing,vol.40,no.3,pp.721-727,2002.
[82]P.Coupe,P.Yger,S.Prima,P.Hellier,C.Kervrann and C.Barillot.An optimized blockwise non local means denoising filter for 3D magnetic resonance images[J].IEEE Trans.Medical Imaging,vol.27,no.4,pp.425-441,2008.
[83]李军宏,潘泉,陈玉春等.基于Radon变换的纹理图像多尺度不变量分析算法[J].中国图象图形学报,2005,10(9):1117-1123
[84]Besag J.Spatial interaction and the statistical analysts of lattice sy stems[J].Journal of the Royal Statistical Society,1974,Series B,192-236.
[85]Besag J.On the statistical analysis of dirty pictures[J].Journal of the Royal Statistical Society,1986,Series B,68:259-302.
[86]S.Z.Li.Markov random field modeling in computer vision[M].Springer,New York,2001.
[87]Geman S,Geman D.Stochastic relaxation.Gibbs distribution and the Bayesian restoration of images[J].IEEE Trans.Pattern and Machine Intelligence,1984,6:721-741.
[88]Dempster A P.Maximum Likelihood From Incomplete Datavia The EM Algorithm[J].J.Roy.Statis.So c,1997,B 39(1):1-38
[89]Bilmes J A.A gentle tutorial of the EM algorithm and its application to parameter Estimation or Gaussian mixture and hidden Markov models[J].http://ssli.ee.washington.edu/people/bilmes/mypapers/em.ps.gz,1998.
[90]Redner R A,Walker HF.Mixture density,maximum likelihood and the EM algorithm [J].SIAM Review,1984,26(2):195-239
[91]S.Geman and D.Geman.Stochastic relaxation,Gibbs distributions and the Bayesian restoration of images[J].IEEE Trans.Pattern Anal.Mach.Intell.,vol.6,no.6,pp.721-741,1984.
[92]L.Wolf,Xiaolei Huang.Ian Martin and Dimitris Metaxas Patch-Based Texture Edges and Segmentation[C].Proc.of the European Conference on Computer Vision(ECCV),May 2006
[93]王鹏伟.基于多尺度理论的图像分割方法研究[D].中国科学技术大学博士论文,2007
[2] B. Nickolay, K. Schicktanz and H. Schmalfub.Automatic Fabric Inspection- Utopia or Reality? [J]. Translation of Melliand Textilberichte, vol. 1, pp.E33-E37, 1993.
[3] B. Smith.Making War on Defects [J]. IEEE Spectrum, vol. 30, no. 9, pp.43-47, 1993
[4] R. Meylani, A. Ertuzun, and A. Ercil.Texture Defect Detection Using the Adaptive Two-dimensional Lattice Filter [C].Proceedings of IEEE International Conference on Image Processing, vol. 3, pp. 165-168,1996.
[5] M. Mufti.Fault Detection and Identification Using Fuzzy Wavelets [D]. Ph. D. Thesis, School of Electrical and Computer Engineering, Georgia Institute of Technology, 1995.
[6] H. Sari-Sarraf and J. S. Goddard.Vision system for on-loom fabricinspection [J].IEEE Transactions on Industrial Applications, vol. 35, no. 6, pp. 1252-1259,1999.
[7] R. Stojanpvic, M. Panagiotis, K. Christos, K. Yorgos, K. Stavros and P. George. Real-Time Vision-Based System for Textile Fabric Inspection [J].Real-Time Imaging, vol. 7,pp.507-518,2001.
[8] C. Neubauer.Segmentation of defects in textile fabric[C].Proceedings of IEEE International Conference on Pattern Recognition, vol. 1, pp. 688-691,1992.
[9] A.L. Amet, A.Ertuzun, A.Ercil.An Efficient Method for Texture Defect Detection: Sub-band Domain Co-occurrence Matrices [J].Image and Vision Computing, vol. 18, pp543-553,2000.
[10]Y. F. Zhang and R. R. Bresee.Fabric defect detection and classification using image analysis [J].Textile Research Journal, vol. 65, no. 1, pp.1-9, 1995.
[11]C. Fernandez, S. Fernandez, P. Campoy, R.Aracil.On-line Texture Analysis for Flat Products Inspection. Neural Nets Implementation[C].Proceedings of 20th IEEE International Conference on Industrial Electronics, Control and Instrumentation, vol. 2, pp. 867-872,1994.
[12]D. Chetverikov.Detecting Defects in Texture[C].Proceedings of 9th IEEE International Conference on Pattern Recognition, vol. 1, pp.61-63, 1988.
[13] J. Escofet, R. Navarro, and M. S. Millan.Detection of local defects in textile webs using Gabor filters [J].Optical Engineering, vol. 37, no. 8, pp.2297-2307, 1998.
[14]Y. F. Zhang and R. R. Bresee.Fabric defect detection and classification using image analysis [J].Textile Research Journal, vol. 65, no. 1, pp.1-9, 1995.
[15]A.L. Amet, A.Ertuzun, A.Ercil.An Efficient Method for Texture Defect Detection: Sub-band Domain Co-occurrence Matrices [J].Image and Vision Computing, vol. 18, pp543-553, 2000.
[16]S. Ozdemir, A. Baykut, R. Meylani, A. Ercil and A.Ertuzun.Comparative Evaluation of Texture Analysis Algorithms For Defect Inspection of Textile Products [C].Proceedings of the IEEE 14th International Conference on Pattern Recognition, vol. 2, pp 173 8-1740, 1998.
[17]F. Ade, N. Lins and M. Unser.Comparison of various filter sets for defect detection in textiles[C].Proceedings of 7th International Conference in Pattern Recognition, pp.428-431,1984.
[18]P. Dewaele, P. Van Gool and A. Oosterlinck.Texture Inspection with Self-Adaptive Convolution Filters[C].Proceedings of 9th International Conference in Pattern Recognition, pp.56-60, 1988.
[19]Z. Fazekas, J. Komuves, I. Renyi and L. Surjan.Automatic Visual Assessment of Fabric Quality[C].Proceedings of IEEE International Symposium on Industrial Electronics, vol. 1, pp. 178-182,1999.
[20] R. Meylani, A. Ertuzun, and A. Ercil.Texture Defect Detection Using the Adaptive Two-dimensional Lattice Filter[C]. Proceedings of IEEE International Conference on Image Processing, vol. 3, pp. 165-168,1996.
[21]S. Ozdemir, A. Ercil.Markov random fields and Karhunen-Loeve transforms for defect inspection of textile products [C].IEEE Conference on Emerging Technologies and Factory Automation, Vol.2, pp.697-703,1996.
[22]C. H. Chan and G. Pang.Fabric defect detection by Fourier analysis [J].IEEE Transactions on Industrial Application, vol. 36, no. 5, pp.1267-1276,2000.
[23]C. Ciamberlini, F. Francini, P. Sansoni, and B.Tiribilli.Defect detection in textured materials by optical filtering with structured detectors and self adaptable masks [J].Optical Engineering, vol. 35, no. 3, pp.838-844, 1996.
[24]D. M. Tsai and C. Y. Hsieh.Automated Surface Inspection for Directional textures [J]. Image and Vision Computing, vol. 18, pp. 49-62, 1999.
[25]YuNan Gong.Study on image analysis of fabric defects.Ph.D. dissertation [D].China Textile University, Shanghai, China, 1999.
[26]J. Escofet, R. Navarro, and M. S. Millan.Detection of local defects in textile webs using Gabor filters [J]. Optical Engineering, vol. 37, no. 8, pp.2297-2307, 1998.
[27]A. Kumar and G. Pang.Defect detection in textured materials using Gabor filters [C]. Proceedings of IEEE International Conference on Industry Application, vol. 2, pp.1041-1047, 2000.
[28]H.Sari-Sarraf and J.S.Goddard.Vision system for on-loom fabricinspection[J].IEEE Transactions on Industrial Applications,vol.35,no.6,pp.1252-1259,1999.
[29]M.Mufti.Fault Detection and Identification Using Fuzzy Wavelets[D].Ph.D.Thesis,School of Electrical and Computer Engineering,Georgia Institute of Technology,1995.
[30]J.L.Dorrity and G.Vachtsevanos.On-line Defect Detection For Weaving Systems [C].Proceedings of IEEE Technical Conference on Textile,Fiber and Film Industry,pp.1-6,1996.
[31]S.Kim,M.H.Lee and K.B.Woo,Wavelet analysis to fabric defects detection in weaving processes[C].Proceedings of IEEE International Symposium on Industrial Electronics,vol.3,pp.1406-14.09,1999.
[32]G.Lambert and F.Bock.Wavelet methods for texture defect detection[C].Proceedings of IEEE International Conference on Image Processing,vol.3,pp.201-204,1997.
[33]W.J.Jasper,S.J.Garnier and H.Potlapalli.Texture characterization and defect detection using adaptive wavelets[J].Optical Engineering,vol.35,no.11,pp.3140-3149,1996.
[34]朱述龙,张占睦遥感图像获取与分析[M].北京:科学出版社.2000.
[35]赵鹏,曹军,浦昭邦等.基于图像融合的运动目标轮廓提取新方法团.光电子.激光,2005,16(8):973-977
[36]刘振华,毛士艺,袁运能.SAR图像组合分割算法[J].电子学报,2003,31(6):833-836.
[37]TianB,Sh aikhM A,Azimi-SadjadiM R,etal.A Study of Cloud Classification With Neural Network s Using Spectral and Textural Features[J].IEEE Trans.Neural Networks,1999,10(1):138-151.
[38]TianL F,Slaughter D C.Environmentally,adaptive segmentation algorithm for outdoor image segmentation[J],Computers and Electronics in Agriculture,1998,21(3):153-168.
[39]Marques J S,Jorge P M.Visual inspection of a combustion process in a thermoelecirc plant[J].IEEE Trans.Signal Processing,2000,80(13):1577-1589.
[40]Zhang Y,Brady M,Smith S.Segmentation of brain MR images through a hidden MarkovRandom field model and the e xpectation-maximization algorithm[J].IEEE Trans.Medical Imaging,2001,20(1):45-57.
[41]沈晶,杨学志[J].一种新的基于纹理分水岭的纺织品缺陷检测方法[J].中国图像图形学报,已录用
[42]章毓晋.图像分割[M].北京:科学出版社,2001,1-7
[43]沈兰荪,王爱民.图像分割的分级性研究[J].北京工业大学学报,2000,26(3):33-38
[44]W.Y.Ma and B.S.Manjunath.Edgeflow:A technique for boundary detection and image segmentation[J].IEEE Trans.Image Processing,2000,vol.9,no.8
[45]H. T. Nguyen, M. Worring, and R. van den Boomgaard.Watersnakes: Energy-driven watershed segmentation [J]. IEEE Trans. Pattern Anal. Machine Intell, 2003, vol. 25, no. 3
[46]R. Adams and L. Bischof.Seeded region growing [J]. IEEE Trans.Pattern Anal. Machine Intell, 1994, vol. 16, no. 6
[47]T. F. Cootes, C. J. Taylor, D. H. Cooper, and J. Graham.Active shape models - their training and application[J].Computer Vision and Image Understanding, 1995, vol. 61, no. 1, pp. 38-59
[48]M. Kass, A. Witkin, and D. Terzopoulos. Snakes: Active contour models[J]. Int'1 J. Computer Vision, 1987, vol. 1, no. 4, pp, 321-331
[49]P. Hill, C. Canagarajah and D. Bull. Image segmentation using a texture gradient-based watershed transform [J]. IEEE Trans. Image Process, vol. 12, no. 12, pp. 1618-1633, Dec. 2003.
[50]P. Hill, C. Canagarajah, and D. Bull.Texture gradient based watersheds egmentation [C]. Proc.Int. Conf. Acoustics, Speech and Signal Processing, vol. 4, pp. 3381-3384, 2002.
[51]A. K. Jain and F. Farrokhnia, "Unsupervised texture segmentation using Gabor filters," Pattern Recognit., vol. 23, pp. 1167-1186,1991.
[52]W. E. Higgins, T. P. Weldon, and D. F. Dunn. Gabor filter design for multiple texture segmentation [J]. Opt. Eng., vol. 35, no. 10, pp.2852-2863, Oct. 1996.
[53]N.W. Campbell and B. T. Thomas.Automatic selection for Gabor filters for pixel classification[J]. in Proc. 6th Int. Conf. Image Processing and its Applications, 1997, pp. 761-765.
[54]S. Mallat.A wavelet tour of signal processing [M]. Academic Press, 2nd ed., San Diego, 1999.
[55]A. Laine and J. Fan. Frame representations for texture segmentation [J]. IEEE Transactions on Image Processing, vol. 5, no. 5, pp. 771-780, May, 1996.
[56]Z. Cvetkovic and M. Vetterli.Discrete-time wavelet extrema representation: design and consistent reconstruction [J]. IEEE Transactions on Signal Processing, vol. 3, pp. 681-693,1995.
[57]Z. Cvetkovic and M. Vetterli. Oversampled filter banks [J].IEEE Transactions on Signal Processing, vol. 46, no. 5, pp. 1245-1255, Mar. 1998.
[58]M. Unser. Texture classification and segmentation using wavelet frames [J].IEEE Transactions on Image Processing, 4(11), 1549-1560 (1995).
[59]S. Mallat and S. Zhong. Characterization of signals from multiscale edges [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 7, pp. 710-732, July,1992.
[60]S.Mallat and W.L.Hwang.Singularity detection and processing withwavelets[J].IEEE Transactions on Information Theory,vol.38,no.2,pp.617-643,Mar.,1992.
[61]J.Canny.A computational approach to edge detection[J].IEEE Trans.Pattern Anal.Machine Intell.,Vol.8,pp.269-285,Nov.1986.
[62]张文炬,苏清祖.基于小波分析的多通道信息融合技术的研究[J].振动、测试与诊断,2002,(02):102-106
[63]潘泉,于昕,程咏梅,张洪才.信息融合理论的基本方法与进展[J].自动化学报,2003,(04):601-615
[64]Vincent L,Soille P.Watersheds in digital spaces:all eficient algorithm based on immersion simulations[J].IEEE Trans on Pattern Analysis and Machine Intelligence,1991,13(6):583-598
[65]Sonka M,Hlavac V,Boyle R.Image Processing,Analysis,and Machine Vision[M].2~(nd) ed.Books/Cole Publishing,pp.506-507,1999
[66]S.Kothainachiar,R.S.D.Wahita Banu,A.Saravanan,Unsupervised Morphological Segmentation for Textured and Non-Textured Images,GVIP[J],2006,09,6(02):33-39
[67]J.S.Lee.Digital image enhancement and noise filtering by use of local statistics[J].IEEE Trans.Pattern Anal.Mach.Intell.,vol.PAMI-2,pp.165-168,1980.
[68]D.T.Kuan,A.Sawchuk,T.Strand and P.Chavel.Adaptive restoration of images with speckle[J].IEEE Trans.ASSP,Vol.35,no.3,pp.373-383,March 1987.
[69]V.S.Frost,J.A.Stiles,K.S.Shanmugan and J.C.Holtzman.A model for radar images and its application to adaptive digital filtering of multiplicative noise[J].IEEE Trans.Pattern Anal.Math.Intell.,vol.4,no.2,pp.157-166,March 1982.
[70]A.Lopes,E.Nezry,R.Touzi and H.Laur.Maximum a posteriori speckle filtering and first order texture models in SAR images[C].Proc.IGARSS,vol.3,pp.2409-2412,1990.
[71]A.Lopes,R.Touzi and E.Nezry.Adaptive speckle filters and Scene heterogeneity[J].IEEE Trans.Geosci Remote Sensing,vol.28,no.6,pp.992-1000,1990.
[72]J.S.Lee.Refined filtering of image noise using local statistics[J].Computer Graphic and Image Processing,vol.15,pp.380-389,1981.
[73]Y.Yu and S.T.Acton.Speckle reducing anisotropic diffusion[J].IEEE Trans.Image Processing,vol.11,no.11,pp.1260-1270,2002.
[74]K.Krissian,C.F.Westin,R.Kikinis and K.G.Vosburgh.Oriented speckle reducing anisotropic diffusion[J].IEEE Trans.Image Processing,vol.16,no.5,pp.1412-1424,2007.
[75]H.Xie,L.E.Pierce and F.T.Ulaby.SAR speckle reduction using wavelet denoising and markov random field modeling[J].IEEE Trans.Geosci Remote Sensing,vol.40,no.10,pp.2196-2211,2002.
[76]Y.Dong,A.K.Milne and B.C.Forster.Toward edge sharpening:a SAR speckle filtering algorithm[J].IEEE Trans.Geosci Remote Sensing,vol.39,no.4,pp.851-863,2001.
[77]M.Walessa and M.Datcu.Model-based despeckling and information extraction from SAR images[J].IEEE Trans.Geosci Remote Sensing,vol.38,no.6,pp.2258-2269,2000.
[78]H.Li,W.Hong,Y.Wu and H.Tai.Texture-preserving despeckling of SAR images using evidence framework[C].IEEE.Geosci Remote Lett,vol.4,no.4,pp.537-541,2007.
[79]A.Buades,B.Coll and J.M.Morel.Image denoising by non-local averaging[C].Proc.IEEE Int'l Conf.Acoustics,Speech and Signal Processing,vol.2,pp.25-28,2005.
[80]A.Buades,B.Coll and J.M.Morel.A review of image denoising algorithm,with a new one[J].Multiscale Modeling and Simulation,vol.4,no.2,pp.490-530,2005.
[81]H.Xie,E.P.Leland and F.T.Ulaby.Statistical properties of logarithmically transformed speekle[J].IEEE Trans.Geosci Remote Sensing,vol.40,no.3,pp.721-727,2002.
[82]P.Coupe,P.Yger,S.Prima,P.Hellier,C.Kervrann and C.Barillot.An optimized blockwise non local means denoising filter for 3D magnetic resonance images[J].IEEE Trans.Medical Imaging,vol.27,no.4,pp.425-441,2008.
[83]李军宏,潘泉,陈玉春等.基于Radon变换的纹理图像多尺度不变量分析算法[J].中国图象图形学报,2005,10(9):1117-1123
[84]Besag J.Spatial interaction and the statistical analysts of lattice sy stems[J].Journal of the Royal Statistical Society,1974,Series B,192-236.
[85]Besag J.On the statistical analysis of dirty pictures[J].Journal of the Royal Statistical Society,1986,Series B,68:259-302.
[86]S.Z.Li.Markov random field modeling in computer vision[M].Springer,New York,2001.
[87]Geman S,Geman D.Stochastic relaxation.Gibbs distribution and the Bayesian restoration of images[J].IEEE Trans.Pattern and Machine Intelligence,1984,6:721-741.
[88]Dempster A P.Maximum Likelihood From Incomplete Datavia The EM Algorithm[J].J.Roy.Statis.So c,1997,B 39(1):1-38
[89]Bilmes J A.A gentle tutorial of the EM algorithm and its application to parameter Estimation or Gaussian mixture and hidden Markov models[J].http://ssli.ee.washington.edu/people/bilmes/mypapers/em.ps.gz,1998.
[90]Redner R A,Walker HF.Mixture density,maximum likelihood and the EM algorithm [J].SIAM Review,1984,26(2):195-239
[91]S.Geman and D.Geman.Stochastic relaxation,Gibbs distributions and the Bayesian restoration of images[J].IEEE Trans.Pattern Anal.Mach.Intell.,vol.6,no.6,pp.721-741,1984.
[92]L.Wolf,Xiaolei Huang.Ian Martin and Dimitris Metaxas Patch-Based Texture Edges and Segmentation[C].Proc.of the European Conference on Computer Vision(ECCV),May 2006
[93]王鹏伟.基于多尺度理论的图像分割方法研究[D].中国科学技术大学博士论文,2007