Share Email Print
cover

Proceedings Paper

New bidirectional neural network and application to binary image recognition
Author(s): Shengwei Zhang; Anthony G. Constantinides; Lihe Zou
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

A new bidirectional neural network is proposed based on convex projection theory. The neurons in the network are divided into two classes clamped and floating neurons. For clamped neurons their states are preassigned to some fixed values and provide the network stimulus. For floating neurons their states change in accordance to those of other neurons and provide the network response. Steady state solutions under synchronous operation are presented in a closed-form formula. An adaptive learning algorithm is discussed which does not need matrix inverse computation and thus saves much learning time. Experiments in storing and retrieving binary images are carried out on a data base composed of 26 uppercase and lower-case English characters.

Paper Details

Date Published: 1 September 1990
PDF: 8 pages
Proc. SPIE 1360, Visual Communications and Image Processing '90: Fifth in a Series, (1 September 1990); doi: 10.1117/12.24104
Show Author Affiliations
Shengwei Zhang, Imperial College of Science and Technology (United Kingdom)
Anthony G. Constantinides, Imperial College of Science and Technology (United Kingdom)
Lihe Zou, Xian Jiaotong Univ. (China)


Published in SPIE Proceedings Vol. 1360:
Visual Communications and Image Processing '90: Fifth in a Series
Murat Kunt, Editor(s)

© SPIE. Terms of Use
Back to Top