Fabric inspection based on best wavelet packet bases

Authors
Citation
Mc. Hu et Is. Tsai, Fabric inspection based on best wavelet packet bases, TEXT RES J, 70(8), 2000, pp. 662-670
Citations number
14
Language
INGLESE
art.tipo
Article
Categorie Soggetti
Material Science & Engineering
Journal title
TEXTILE RESEARCH JOURNAL
ISSN journal
0040-5175 → ACNP
Volume
70
Issue
8
Year of publication
2000
Pages
662 - 670
Database
ISI
SICI code
0040-5175(200008)70:8<662:FIBOBW>2.0.ZU;2-C
Abstract
In this study, we use best wavelet packet bases and an artificial neural ne twork (ANN) to inspect four kinds of fabric defects. Multiresolution repres entation of an image using wavelet transform is a new and effective approac h for analyzing image information content. In this study, we find the value s and positions for the smallest-six entropy in a wavelet packet best tree that acts as the feature parameters of the ANN for identifying fabric defec ts. We explore three basic considerations of the classification rate of fab ric defect inspection comprising wavelets with various maximum vanishing mo ments, different numbers of resolution levels, and differently scaled fabri c images. The results show that the total classification rate for a wavelet function with a maximum vanishing moment of four and three resolution leve ls can reach 100%, and differently scaled fabric images have no obvious eff ect on the classification rate.