Classification of surface defects on hot rolled steel using adaptive learning methods
Praminda Caleb-Solly, M. D. Steuer · 2002
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.