A real-time system designed to detect and classify textile defects is presented. The system starts with an analysis of the optical Fourier transform of sample textiles. We also use a back-propagation neural network to help detect and classify defects. Exper imental results show that the system is able to detect and classify nine out of the twelve kinds of defects in its data base.
Get full access to this article
View all access options for this article.
References
1.
Freeman, James A., and Skapura, David M. , "Neural Networks—Alogorithms, Applications, and Programming Techniques," Addison Wesley, NY, 1991, pp. 89-125.
2.
Ribolzi, S., Merckle, J., and Gresser, J., Real-Time Fault Detection on Textiles Using Opto-electronic Processing , Textile Res. J.63 (2), 61-71 (1993).
3.
The Math Works, Inc., Neural Network Toolbox for use with MATLAB, pp. 5-1-5-38, 1995.
4.
Wood, Errol J. , Applying Fourier and AssociatedTransforms to Pattern Characterization in Textiles , Textile Res. J.60 (4), 212-220 (1990).
5.
Wood, Errol J. , and Hodgson, Robert M., Carpet Texture Measurement Using Image Analysis, Textile Res. J.59, 1-12 (1989).
