Title: Size invariant shape recognition by modulated competitive neural circuit

Authors: Lai Si Wu, Lakhmi Jain

Addresses: Knowledge-Based Intelligent Engineering Systems Center, University of South Australia, Adelaide, Mawson Lakes S.A. 5095, Australia. ' Knowledge-Based Intelligent Engineering Systems Center, University of South Australia, Adelaide, Mawson Lakes S.A. 5095, Australia

Abstract: This paper addresses the problem of size invariant shape recognition based on scale transformation within a modulated competition neural layer. In this paper we discuss the advantages of the application of a neural network to pattern recognition and study how the traditional automatic target recognition can fail to recognise a known pattern due to either a size change or background clutter and distortion. The model construction is based on neurophysiology experiments on vision systems. The Neural Circuit Simulation studies undertaken demonstrate the effectiveness of the proposed model in recognising 2D objects in non-ideal visual conditions.

Keywords: ART neural networks; size invariant shape recognition; scale transformation; modulated competition neural layer; ICT; pattern recognition; automatic target recognition; neurophysiology; vision systems; neural circuit simulation; object recognition.

DOI: 10.1504/IJICT.2007.013319

International Journal of Information and Communication Technology, 2007 Vol.1 No.1, pp.76 - 88

Published online: 20 Apr 2007 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article