Share Email Print

Proceedings Paper

Real-time vision system for defect detection and neural classification of web textile fabric
Author(s): Panagiotis Mitropoulos; Christos Koulamas; Radovan D. Stojanovic; Stavros Koubias; George D. Papadopoulos; George Karayanis
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A real-time pilot system for defect detection and classification of web textile fabric is presented in this paper. The general hardware and software platform, developed for solving this problem, is presented and a powerful novel method for defect detection is proposed. This method gives good results in the detection of low contrast defects under real industrial conditions, where the presence of many types of noise is an inevitable phenomenon. For the defect classification an artificial neural network, trained by using a back-propagation algorithm, is implemented. Using a reduced number of possible defect classes, the system gives consistent and repeatable results with sufficient speed.

Paper Details

Date Published: 8 March 1999
PDF: 11 pages
Proc. SPIE 3652, Machine Vision Applications in Industrial Inspection VII, (8 March 1999); doi: 10.1117/12.341126
Show Author Affiliations
Panagiotis Mitropoulos, Univ. of Patras (Greece)
Christos Koulamas, Univ. of Patras (Greece)
Radovan D. Stojanovic, Univ. of Patras (Greece)
Stavros Koubias, Univ. of Patras (Greece)
George D. Papadopoulos, Univ. of Patras (Greece)
George Karayanis, Univ. of Patras (Greece)

Published in SPIE Proceedings Vol. 3652:
Machine Vision Applications in Industrial Inspection VII
Kenneth W. Tobin; Ning S. Chang, Editor(s)

© SPIE. Terms of Use
Back to Top