Automated defect detection system using wavelet packet frame and Gaussian mixture model.

This paper proposes an approach for automated defect detection in homogeneous textiles using texture analysis. The texture features are extracted by the wavelet packet frame decomposition followed by the Karhunen-Loève transform. The texture feature vector for each pixel is used as an input to a Gaussian mixture model that determines whether or not each pixel is defective. The parameters of the Gaussian mixture model are estimated with nondefective textile images in supervised defect detection. An approach for unsupervised defect detection is also presented that can identify the heterogeneous subblocks on the basis of the Kullback-Leibler divergence between two Gaussian mixtures. The proposed method was evaluated on 25 different homogeneous textile image pairs, one of each pair with a defect and the other with no defect, and was compared with existing methods using texture analysis. The experimental results yielded visually good segmentation and an excellent detection rate with a low false alarm rate for both supervised and unsupervised defect detection. This confirms the validity of the proposed approach for automated defect detection and localization.

[1]  Mohammed Bennamoun,et al.  Optimal Gabor filters for textile flaw detection , 2002, Pattern Recognit..

[2]  Josiane Zerubia,et al.  Texture analysis using probabilistic models of the unimodal and multimodal statistics of adaptive wavelet packet coefficients , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Wei-Chung Lin,et al.  Metal surface inspection using image processing techniques , 1984, IEEE Transactions on Systems, Man, and Cybernetics.

[4]  Anil K. Jain,et al.  Unsupervised texture segmentation using Gabor filters , 1990, 1990 IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings.

[5]  Harsh Potlapalli,et al.  Image Analysis of Mispicks in Woven Fabric , 1995 .

[6]  Cheng-Lung Tseng,et al.  A self-growing probabilistic decision-based neural network with automatic data clustering , 2004, Neurocomputing.

[7]  Jun S. Huang,et al.  A transformation invariant matching algorithm for handwritten chinese character recognition , 1990, Pattern Recognit..

[8]  Grantham K. H. Pang,et al.  Discriminative fabric defect detection using adaptive wavelets , 2002 .

[9]  Jian Fan,et al.  Texture Classification by Wavelet Packet Signatures , 1993, MVA.

[10]  Bugao Xu,et al.  Identifying Fabric Structures with Fast Fourier Transform Techniques , 1996 .

[11]  Ajay Kumar,et al.  Defect detection in textured materials using optimized filters , 2002, IEEE Trans. Syst. Man Cybern. Part B.

[12]  Ajay Kumar,et al.  Defect detection in textured materials using Gabor filters , 2000, Conference Record of the 2000 IEEE Industry Applications Conference. Thirty-Fifth IAS Annual Meeting and World Conference on Industrial Applications of Electrical Energy (Cat. No.00CH37129).

[13]  Hazem M. Abbas,et al.  Automated vision system for localizing structural defects in textile fabrics , 2005, Pattern Recognit. Lett..

[14]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[15]  Shiri Gordon,et al.  An efficient image similarity measure based on approximations of KL-divergence between two gaussian mixtures , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[16]  Errol J. Wood,et al.  Applying Fourier and Associated Transforms to Pattern Characterization in Textiles , 1990 .

[17]  Michael Unser,et al.  Texture classification and segmentation using wavelet frames , 1995, IEEE Trans. Image Process..

[18]  Eleftherios Kayafas,et al.  A computer vision approach for textile quality control , 2001, Comput. Animat. Virtual Worlds.

[19]  C.-C. Jay Kuo,et al.  Texture analysis and classification with tree-structured wavelet transform , 1993, IEEE Trans. Image Process..

[20]  Mausumi Acharyya,et al.  An adaptive approach to unsupervised texture segmentation using M-Band wavelet transform , 2001, Signal Process..

[21]  Mohammed Bennamoun,et al.  Suitability Analysis of Techniques for Flaw Detection in Textiles using Texture Analysis , 2000, Pattern Analysis & Applications.

[22]  Chi-Ho Chan,et al.  Fabric defect detection by Fourier analysis , 1999, Conference Record of the 1999 IEEE Industry Applications Conference. Thirty-Forth IAS Annual Meeting (Cat. No.99CH36370).

[23]  Paul Scheunders,et al.  Statistical texture characterization from discrete wavelet representations , 1999, IEEE Trans. Image Process..

[24]  Tae Jin Kang,et al.  Texture classification and segmentation using wavelet packet frame and Gaussian mixture model , 2007, Pattern Recognit..

[25]  Man-Wai Mak,et al.  Gaussian Mixture Models and Probabilistic Decision-Based Neural Networks for Pattern Classification: A Comparative Study , 1999, Neural Computing & Applications.

[26]  Zhigang Fan,et al.  Automated Inspection of Textile Fabrics Using Textural Models , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  Chun-Shien Lu,et al.  Unsupervised texture segmentation via wavelet transform , 1997, Pattern Recognit..

[28]  Jaume Escofet,et al.  Detection of local defects in textile webs using Gabor filters , 1998 .