Textile defect classification using discriminative wavelet frames

The classification of defects is highly demanded for automated inspection of textile products. In this paper, a new method for textile defect classification is proposed by using discriminative wavelet frames. Multiscale texture properties of textile image are characterized by its wavelet frames representation. For a better description of the latent structure of textile image, wavelet frames adapted to textile are generated rather than using standard ones. Based on discriminative feature extraction (DFE) method, the wavelet frames and the back-end classifier are simultaneously designed with the common objective of minimizing classification errors. The proposed method has been evaluated on the classification of 466 defect samples containing eight classes of textile defects, and 434 nondefect samples. In comparison with standard wavelet frames, the designed discriminative wavelet frames has been shown to largely improve the classification performance, where 95.8% classification accuracy was achieved.

[1]  Martin Vetterli,et al.  Oversampled filter banks , 1998, IEEE Trans. Signal Process..

[2]  Dominik R. Rohrmus.  Invariant web defect detection and classification system , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[3]  Biing-Hwang Juang,et al.  Discriminative learning for minimum error classification [pattern recognition] , 1992, IEEE Trans. Signal Process..

[4]  M. Mufti,et al.  Automated fault detection and identification using a fuzzy-wavelet analysis technique , 1995, Conference Record AUTOTESTCON '95. 'Systems Readiness: Test Technology for the 21st Century'.

[5]  Dragana Brzakovic,et al.  Designing a defect classification system: A case study , 1996, Pattern Recognit..

[6]  J. L. Dorrity,et al.  On-line defect detection for weaving systems , 1996, 1996 IEEE Annual Textile, Fiber and Film Industry Technical Conference.

[7]  Xuezhi Yang,et al.  Fabric defect classification using wavelet frames and minimum classification error training , 2002, Conference Record of the 2002 IEEE Industry Applications Conference. 37th IAS Annual Meeting (Cat. No.02CH37344).

[8]  P. P. Vaidyanathan,et al.  The role of lossless systems in modern digital signal processing: a tutorial , 1989 .

[9]  Muid Ur-Rahman Mufti,et al.  Fault detection and identification using fuzzy wavelets , 1995 .

[10]  A. S. Tolba,et al.  A self-organizing feature map for automated visual inspection of textile products , 1997 .

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

[12]  Biing-Hwang Juang,et al.  An application of discriminative feature extraction to filter-bank-based speech recognition , 2001, IEEE Trans. Speech Audio Process..

[13]  Thanos Stouraitis,et al.  Defect detection and classification on web textile fabric using multiresolution decomposition and neural networks , 1999, ICECS'99. Proceedings of ICECS '99. 6th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.99EX357).

[14]  S. Mallat.  A wavelet tour of signal processing , 1998 .