Share Email Print

Proceedings Paper

Logic neural network-based segmentation system with variable-sensitivity characteristics
Author(s): Devesh Patel; G. Tambouratzis; T. John Stonham
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A logic artificial neural network paradigm is used to cluster texture spectra in feature space to achieve image segmentation. The features are grouped such that they represent regions of textural homogeneity on the image. These are extracted from small local areas on the image. The strategy results in a feature spectrum transformation of the image. The logic neural network is characterized by short training and operating times compared to the analogue neural networks. The network runs in an unsupervised mode, which excludes the need for external supervision during operation. The variable-sensitive characteristics of the network are illustrated with the aid of natural texture image composites.

Paper Details

Date Published: 22 October 1993
PDF: 8 pages
Proc. SPIE 2094, Visual Communications and Image Processing '93, (22 October 1993); doi: 10.1117/12.157993
Show Author Affiliations
Devesh Patel, Univ. of London (United Kingdom)
G. Tambouratzis, Brunel Univ. (United Kingdom)
T. John Stonham, Brunel Univ. (United Kingdom)

Published in SPIE Proceedings Vol. 2094:
Visual Communications and Image Processing '93
Barry G. Haskell; Hsueh-Ming Hang, Editor(s)

© SPIE. Terms of Use
Back to Top