22 March 1999 Symmetry recognition in images
Author Affiliations +
Abstract
This paper is concerned with the problem of separation of data, by a Neural based computer recognition system. To this end certain types of data which are 'tricky' are studied in order to see if they can be separated (i.e. classified) by a neural network or by a Kohonen based classifier. It is shown that there exist data which cannot simply be separated by a nearest distance classifier and yet can be treated well by a neural network, these correspond to the symmetry problem in images.
© (1999) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kumar Eswaran, Kumar Eswaran, "Symmetry recognition in images", Proc. SPIE 3722, Applications and Science of Computational Intelligence II, (22 March 1999); doi: 10.1117/12.342899; https://doi.org/10.1117/12.342899
PROCEEDINGS
9 PAGES


SHARE
RELATED CONTENT

Impact of noise on an optoelectronic neural network
Proceedings of SPIE (September 15 1992)
Symmetry recognition in images
Proceedings of SPIE (July 18 1999)
Design rules of multilayer perceptrons
Proceedings of SPIE (June 30 1992)

Back to Top