Defect detection and classification on web textile fabric using multiresolution decomposition and neural networks

Yorgos A. Karayiannis, Radovan Stojanovic, Panagiotis Mitropoulos, Christos Koulamas, Thanos Stouraitis, Stavros Koubias, George Papadopoulos

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

52 Scopus citations

Abstract

In this paper a pilot system for defect detection and classification of web textile fabric in real-time is presented. The general hardware and software platform, developed for solving this problem, is presented while a powerful novel method for defect detection after multiresolution decomposition of the fabric images is proposed. This method gives good results in the detection of low contrast defects under real industrial conditions, where many types of noise are present. An artificial neural network, trained by a back-propagation algorithm, performs the defect classification in categories.

Original languageBritish English
Title of host publicationProceedings of ICECS 1999 - 6th IEEE International Conference on Electronics, Circuits and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages765-768
Number of pages4
ISBN (Electronic)0780356829
DOIs
StatePublished - 1999
Event6th IEEE International Conference on Electronics, Circuits and Systems, ICECS 1999 - Pafos, Cyprus
Duration: 5 Sep 19998 Sep 1999

Publication series

NameProceedings of the IEEE International Conference on Electronics, Circuits, and Systems
Volume2

Conference

Conference6th IEEE International Conference on Electronics, Circuits and Systems, ICECS 1999
Country/TerritoryCyprus
CityPafos
Period5/09/998/09/99

Fingerprint

Dive into the research topics of 'Defect detection and classification on web textile fabric using multiresolution decomposition and neural networks'. Together they form a unique fingerprint.

Cite this