Fuzzy pattern recognition and classification of animal fibers

L.X. Kong, F.H. She, S. Nahavandi, A.Z. Kouzani
Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference (Cat. No. 01TH8569)  
Several techniques, including chemical and physical approaches, have been previously developed to differentiate between animal fibers. Since all animal fibers are comprised of essentially the same keratin, they cannot be effectively distinguished by existing physical or chemical technique. In this paper, a fuzzy neural pattern recognition system is developed to classify two typical animal fibersmohair and merino. Two multilayer networks are used with the unsupervised network being used for
more » ... being used for automatic feature extraction while the supervised network serving as the classifier based on the information extracted from unsupervised network. It is found that this hybrid network can accurately classify the two fibers and the accuracy improves with the increase in the features being extracted from the unsupervised network. 0-7803-7@78-3/Ol/$lO.Ml (C)zoOl IEJ3E.
doi:10.1109/nafips.2001.944750 fatcat:pjvrbke6jrdrpprogdcjasamiu