Publications:Using Labelled and Unlabelled Data to Train a Multilayer Perceptron for Colour Classification in Graphic Arts

From ISLAB/CAISR

Do not edit this section

Keep all hand-made modifications below

Title Using Labelled and Unlabelled Data to Train a Multilayer Perceptron for Colour Classification in Graphic Arts
Author Antanas Verikas and Adas Gelzinis and Kerstin Malmqvist
Year 1999
PublicationType Conference Paper
Journal
HostPublication Multiple approaches to intelligent systems : 12th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems IEA/AIE-99, Cairo, Egypt, May 31 - June 3, 1999. Proceedings
Conference 12th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems IEA/AIE -99, Cairo, Egypt, May 31 - June 3, 1999
DOI http://dx.doi.org/10.1007/978-3-540-48765-4_59
Diva url http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:300237
Abstract This paper presents an approach to using both labelled and unlabelled data to train a multi-layer perceptron. The unlabelled data are iteratively pre-processed by a perceptron being trained to obtain the soft class label estimates. It is demonstrated that substantial gains in classification performance may be achieved from the use of the approach when the labelled data do not adequately represent the entire class distributions. The experimental investigations performed have shown that the approach proposed may be successfully used to train networks for colour classification in graphic arts.