Classification of surface defects on hot rolled steel using adaptive learning methods

Author

Caleb, P. ; Steuer, M.

Author_Institution

Intelligent Comput. Syst. Centre, West of England Univ., Bristol, UK

Volume

1

fYear

2000

fDate

2000

Firstpage

103

Abstract

Classification of local area surface defects on hot rolled steel is a problematic task due to the variability in manifestations of the defects grouped under the same defect label. The paper discusses the use of two adaptive computing techniques, based on supervised and unsupervised learning, with a view to establishing a basis for building reliable decision support systems for classification

Keywords

adaptive systems; automatic optical inspection; decision support systems; feature extraction; hot rolling; image classification; learning (artificial intelligence); self-organising feature maps; steel industry; adaptive computing techniques; adaptive learning methods; defect label; hot rolled steel; local area surface defects; reliable decision support systems; supervised learning; surface defect classification; unsupervised learning; Decision support systems; Feature extraction; Image processing; Image segmentation; Intelligent systems; Learning systems; Steel; Supervised learning; Unsupervised learning; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Knowledge-Based Intelligent Engineering Systems and Allied Technologies, 2000. Proceedings. Fourth International Conference on

Conference_Location

Brighton

Print_ISBN

0-7803-6400-7

Type

conf

DOI

10.1109/KES.2000.885769

Filename

885769