22 October 1993 Logic neural network-based segmentation system with variable-sensitivity characteristics
Author Affiliations +
Proceedings Volume 2094, Visual Communications and Image Processing '93; (1993); doi: 10.1117/12.157993
Event: Visual Communications and Image Processing '93, 1993, Cambridge, MA, United States
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.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Devesh Patel, G. Tambouratzis, T. John Stonham, "Logic neural network-based segmentation system with variable-sensitivity characteristics", Proc. SPIE 2094, Visual Communications and Image Processing '93, (22 October 1993); doi: 10.1117/12.157993; https://doi.org/10.1117/12.157993
PROCEEDINGS
8 PAGES


SHARE
KEYWORDS
Image segmentation

Neural networks

Image processing

Logic

Composites

Image filtering

Retina

RELATED CONTENT


Back to Top