Yin, H. and Allinson, N. M. (1994) Unsupervised segmentation of textured images using a hierarchical neural structure. Electronics letters, 30 (22). pp. 1842-1843. ISSN 0013-5194

PDF 00329976.pdf - Whole Document Restricted to Repository staff only Download (236Kb) | Request a copy

Abstract

A hierarchical learning structure, combining a randomly-placed local window, a self-organising map and a local-voting scheme, has been developed for the unsupervised segmentation of textured images, which are modelled by Markov random fields. The system learns to progressively estimate model parameters, and hence classify the various textured regions. A globally correct segregation has consistently been obtained during extensive experiments on both synthetic and natural textured images.

Item Type:	Article
Additional Information:	A hierarchical learning structure, combining a randomly-placed local window, a self-organising map and a local-voting scheme, has been developed for the unsupervised segmentation of textured images, which are modelled by Markov random fields. The system learns to progressively estimate model parameters, and hence classify the various textured regions. A globally correct segregation has consistently been obtained during extensive experiments on both synthetic and natural textured images.
Keywords:	neural networks, segmentation
Subjects:	G Mathematical and Computer Sciences > G730 Neural Computing
Divisions:	College of Sciences > Faculty of Science > Lincoln School of Computer Science
Depositing User:	Tammie Farley
Date Deposited:	20 Apr 2012 14:01
Last Modified:	13 Mar 2013 09:06
URI:	http://eprints.lincoln.ac.uk/id/eprint/5074

Actions (login required)

View Item