CLASSIFYING TEXTILE FAULTS WITH A BACKPROPAGATION NEURAL-NETWORK USING POWER SPECTRA

Authors
CHEN PW LIANG TC YAU HF SUN WL WANG NC LIN HC LIEN RC
Citation
Pw. Chen et al., CLASSIFYING TEXTILE FAULTS WITH A BACKPROPAGATION NEURAL-NETWORK USING POWER SPECTRA, Textile research journal, 68(2), 1998, pp. 121-126
Citations number
5
Categorie Soggetti
Materiales Science, Textiles
Journal title
Textile research journal → ACNP
ISSN journal
00405175
Volume
68
Issue
2
Year of publication
1998
Pages
121 - 126
Database
ISI
SICI code
0040-5175(1998)68:2<121:CTFWAB>2.0.ZU;2-2
Abstract
A real-time system designed to detect and classify textile defects is presented. The system starts with an analysis of the optical Fourier t ransform of sample textiles. We also use a back-propagation neural net work to help detect and classify defects. Experimental results show th at the system is able to detect and classify nine out of the twelve ki nds of defects in its data base.