19 July 1999 Symmetry recognition in images
Author Affiliations +
Proceedings Volume 3749, 18th Congress of the International Commission for Optics; (1999) https://doi.org/10.1117/12.354993
Event: ICO XVIII 18th Congress of the International Commission for Optics, 1999, San Francisco, CA, United States
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. In this paper the question that is posed and answered is: `If we are given a set of binary images, is it possible to devise an algorithm which will enable the computer to automatically recognize those images which have an inherent symmetry or near-symmetry?' It is demonstrated that a neural based algorithm can be trained to do the job efficaciously.
© (1999) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kumar Eswaran, "Symmetry recognition in images", Proc. SPIE 3749, 18th Congress of the International Commission for Optics, (19 July 1999); doi: 10.1117/12.354993; https://doi.org/10.1117/12.354993
PROCEEDINGS
2 PAGES


SHARE
RELATED CONTENT

Implementation of adaptive logic networks on an FPGA board
Proceedings of SPIE (October 08 1998)
Symmetry recognition in images
Proceedings of SPIE (March 22 1999)
Diagnosis of hepatitis by use of neural network learning
Proceedings of SPIE (March 02 1994)
Image Algebra And Its Relationship To Neural Networks
Proceedings of SPIE (August 30 1989)
Image algebra networks for pattern classification
Proceedings of SPIE (June 30 1994)

Back to Top