Machine learning paradigms for pattern recognition and image understanding

Authors: Caelli, Terry¹; Bischof, Walter F.²

Source: Spatial Vision, Volume 10, Number 1, 1996 , pp. 87-103(17)

Buy & download fulltext article:

Price: $35.00 plus tax (Refund Policy)

Abstract:

In this paper some issues are considered related to the encoding of spatial information and associated perceptual learning algorithms which, it is claimed, are necessary for robust pattern and object recognition in multi-object (natural) scenes. The types of learning requirements within a 'recognition-by-parts' paradigm are contrasted with findings from alternative models.

Document Type: Research article

DOI: http://dx.doi.org/10.1163/156856896X00079

Affiliations: 1: Department of Computer Science, Curtin University of Technology, GPO Box U1987, Perth, WA 6001, Australia 2: Department of Psychology, University of Alberta, Edmonton, Alberta, T6G 2E9, Canada

Publication date: 1996-01-01

More about this publication?