Share Email Print

Proceedings Paper

Image texture segmentation using a neural network
Author(s): Mohammed R. Sayeh; Ragu Athinarayanan; Pushpuak Dhali
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper we use a neural network called the Lyapunov associative memory (LYAM) system to segment image texture into different categories or clusters. The LYAM system is constructed by a set of ordinary differential equations which are simulated on a digital computer. The clustering can be achieved by using a single tuning parameter in the simplest model. Pattern classes are represented by the stable equilibrium states of the system. Design of the system is based on synthesizing two local energy functions, namely, the learning and recall energy functions. Before the implementation of the segmentation process, a Gauss-Markov random field (GMRF) model is applied to the raw image. This application suitably reduces the image data and prepares the texture information for the neural network process. We give a simple image example illustrating the capability of the technique. The GMRF-generated features are also used for a clustering, based on the Euclidean distance.

Paper Details

Date Published: 2 September 1992
PDF: 8 pages
Proc. SPIE 1779, Optical Design and Processing Technologies and Applications, (2 September 1992); doi: 10.1117/12.140961
Show Author Affiliations
Mohammed R. Sayeh, Southern Illinois Univ./Carbondale (United States)
Ragu Athinarayanan, Southern Illinois Univ./Carbondale (United States)
Pushpuak Dhali, Southern Illinois Univ./Carbondale (United States)

Published in SPIE Proceedings Vol. 1779:
Optical Design and Processing Technologies and Applications
Robert J. Heaston, Editor(s)

© SPIE. Terms of Use
Back to Top