Image inspection of knitted fabric defects using wavelet packets

Image inspection by wavelet packets and a neural network classifier is presented for non-defect and six kinds of defects in knitted fabrics. The types of defect include a hole, set mark (coarse), dropped stitch, oil stain, streak, and tight end. In this study, wavelet packet decomposition of a sample image is carried out based on the best-basis wavelet packet tree with three resolution levels. The lowest-two entropy among all sub-band images and the standard deviation for the original image are selected as feature inputs of the neural network classifier. These textural features are shown in seven groups, which are separately distributed in the feature space. We gathered a total of 112 experimental samples, with 16 samples in each of the seven aforementioned categories. The results demonstrate that with the three features, 56 test samples are correctly inspected. However, the lack of one of the three features yields wrong classification of some samples. Therefore, the three features selected are definitely suitable for recognition of our knitted fabric defects and also are the smallest number of features required to give accurate inspection.

[1]  Guizhong Liu,et al.  Wavelet packet image coding algorithm combined with the actual coding costs , 2003 .

[2]  Chi-Man Pun,et al.  Texture classification using dominant wavelet packet energy features , 2000, 4th IEEE Southwest Symposium on Image Analysis and Interpretation.

[3]  Jeng-Jong Lin,et al.  Applying an Artificial Neural Network to Pattern Recognition in Fabric Defects , 1995 .

[4]  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).

[5]  Gary G. Yen,et al.  Wavelet packet feature extraction for vibration monitoring , 2000, IEEE Trans. Ind. Electron..

[6]  I. Tsai,et al.  Fabric Inspection Based on Best Wavelet Packet Bases , 2000 .

[7]  Shengqi Guan.  Fabric defect detection based on fusion technology of multiple algorithm , 2010, 2010 2nd International Conference on Signal Processing Systems.

[8]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  I. Tsai,et al.  Automatic Inspection of Fabric Defects Using an Artificial Neural Network Technique , 1996 .

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

[11]  Sungshin Kim,et al.  Wavelet analysis to fabric defects detection in weaving processes , 1999, ISIE '99. Proceedings of the IEEE International Symposium on Industrial Electronics (Cat. No.99TH8465).

[12]  G..  A Theory for Multiresolution Signal Decomposition : The Wavelet Representation , 2004 .

[13]  G. Pang,et al.  Identification of surface defects in textured materials using wavelet packets , 2001, Conference Record of the 2001 IEEE Industry Applications Conference. 36th IAS Annual Meeting (Cat. No.01CH37248).

[14]  Kuo-Chin Fan,et al.  Fabric Classification Based on Recognition Using a Neural Network and Dimensionality Reduction , 1998 .

[15]  I.-S. Tsai,et al.  The Inspection of Fabric Defects by Using Wavelet Transform , 2000 .

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

[17]  Yuan Yan Tang,et al.  Feature Extraction of Radar Multiple-Target Echoes Using Wavelet Packet Transform with the Best Bases , 2003, Int. J. Pattern Recognit. Artif. Intell..

[18]  Pei-Wen Chen,et al.  Classifying Textile Faults with a Back-Propagation Neural Network Using Power Spectra , 1998 .

[19]  Chi-Man Pun,et al.  Rotation-invariant texture classification using a two-stage wavelet packet feature approach , 2001 .

[20]  Chong-Ho Choi,et al.  Surface Defect Inspection of Cold Rolled Strips with Features Based on Adaptive Wavelet Packets , 1997 .