Fabric Defect Classification Based on Local Region Features and SVM

Abstract:

The big differences of the texture and shapes in the same type and certain similarities among heterogeneous types result in the difficult classification of fabric defects. Compared with traditional global statistical method, we put up a new solution, which makes use of the fabric defect local region features to keep the defect property and defect classification by Support Vector Machines (SVM). Based on small-samples learning machine of SVM, we obtain a good performance of less computational load and high recognition rate.

• Periodical: Applied Mechanics and Materials (Volumes 182-183)
• Pages: 634-638
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.182-183.634
• Online since: June 2012
• Authors: Yi Hong Li, Zhao Yang Lu, Jing Li, Ling Ling Cui
• Keywords: Fabric Defect, Feature Extraction, Gabor, Support Vector Machine (SVM)

References

[1] S. Kim, M. H. Lee, and K. B. Woo, Wavelet analysis to defects detection in weaving processes, in Proc. IEEE Int. Symp. Industrial Electronics, vol. 3, July 1999, p.1406–1409.

[2] K. Srinivasan, P. H. Dastoor, P. Radhakrishnaiah, and S. Jayaraman. FDAS: A knowledge-based framework for analysis of defects in woven textile structures, J. Textile Inst., pt. 1, vol. 83, no. 3, 1992, pp.431-448.

DOI: 10.1080/00405009208631217

[3] Ajay Kumar. Computer-Vision-Based Fabric Defect Detection：A Survey[J]. IEEE Transactions on Industrial Electronics, 2008, 55 (1): 348-363.

DOI: 10.1109/tie.1930.896476

[4] G. Cicirelli, E. Stella, M. Nitti, A. Distante, neural network based defect inspection from images, Proceedings of Fourth LASTED International Conference Signal Prodessing, Pattern Recognition and Applications. Innsbruck, Austria. 14-16.

[5] W.K. Wong, C.W.M. Yuen, D.D. Fan, L.K. Chan, E.H.K. Fung, Stitching defect detection and classification using wavelet transform and BP 3 neural network. Expert Systems with Applications, 26 March (2008).

DOI: 10.1016/j.eswa.2008.02.066

[6] Liu Wanchun, Luo Shuanghua, ZHU Yuwen, XIE Shibin, Fabric Defect Classification Based on Cluster Analysis and Support Vector Machine, Transact ions of Beijing Institute of Techno logy, Aug. 2004: 0687-04.

[7] B. Scholkopf, K. K. Sung, C. J. C. Burges, F. Girosi,P. Niyogi, T. Poggio, and V. Vapnik, Comparing support vector machines with gaussian kernels to radial basis function classifiers, IEEE Transactions on Signal Processing, vol. 45, no. 11, 1997, p.2758.

DOI: 10.1109/78.650102

[8] Ajay Kumar, Grantham K. H. Pang, Defect Detection in Textured Materials Using Gabor Filters, IEEE transactions on industry applications, vol. 38, no. 2, march/april 2002: 425-16.

DOI: 10.1109/28.993164

[9] Hao Liu, Jiuqiang Han, Defect Detection in Textiles Using Optimal Gabor Wavelet Filter, Proceedings of the 6th World Congress on Intelligent Control and Automation, June 21 - 23, 2006, Dalian, China: 10005-3.

DOI: 10.1109/wcica.2006.1713955

[10] D Gabor. Theory of Communication[J]. Journal of the Institution of Electrical Engineers. 1946, 93: 429-457.

[11] Liu Wanchun, Luo Shuanghua, Xie shibing. Fabric defect classification based on cluster analysis. and support vector machine. Transactions of beijing institute of technology. Vol. 24. No. 8, Aug. 2004: 0687-4.

[12] Zhen Hou and John´e M. Parker, Texture Defect Detection Using Support Vector Machines with Adaptive Gabor Wavelet Features, Proceedings of the Seventh IEEE Workshop on Applications of Computer Vision a b c d a b c d Fig 1 Defect preprocessing; a Cracked ends，Bamboo pick, Mispick, Broken hole; b filtrate Gabor wavelet ; c thresholded image; d separating defect image.

DOI: 10.1109/acvmot.2005.115