Abstract
A novel computational neural network is proposed here for the recognition of character pattern. This neural network is able to recognize deformed characters. Our neural network model is capable of matching patterns by Euclidean distance instead of Hamming distance as in the Hamming net (Lippman, 1987) and to incorporate contextual information. The network requires only local connections amongst the neurons. This makes it particularly attractive for practical applications.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Carpenter, G.A. and Grossberg, S. (1987) "A Massively Parallel Architecture for a Self-Organizing Neural Pattern Recognition Machine", Computer Vision, Graphics, and Image Processing, Vol.37, 1987, pp54–115.
Fukushima, K. and Miyake, S. (1982) "Neocognitron: A New Algorithm for Pattern Recognition Tolerant of Deformation and Shifts in Position", Pattern Recognition, Vol.15, No.6, 1982, pp455–469.
Graf, H.P., Jackel, L.D., and Hubbard, W.E. (1988) "VLSI Implementation of a Neural Network Model", IEEE Computer, March 1988, pp41–51.
Hinton, G.E. and Anderson, J.A. (eds) (1981) Parallel Models of Associative Memory, Lawrence Erlbaum Associates: Hillsdale,N.J.
Hopfield, J.J. (1982) "Neural networks and physical systems with emergent collective computational abilities", Proc. Natl. Acad. Sci. USA, vol.79, pp2554–2558, Apr. 1982.
Hopfield, J.J. (1984) "Neurons with graded response have collective computational properties like those of two-state neurons", Proc. Natl. Acad. Sci. USA, vol.81, pp3088–3092, May, 1984.
Hopfield, J.J and Tank, D.W. (1986) "Computing with Neural Circuits: A Model", Science, Vol.233, No.4767, pp625–633, Aug.1986.
Kohonen, T. (1977) Associative Memory: A system-theoretic approach, Springer-Verlag, New York.
Kohonen, T. (1988) "The ‘Neural’ Phonetic Typewriter", IEEE Computer, March 1988, pp11–24.
Lippman, R.P. (1987) "An Introduction to Computing with Neural Nets", IEEE ASSP Magazine, April 1987, pp4–22.
Minsky, M. and Papert, S. (1969) Perceptrons: An approach to computational geometry, MIT Press: Cambridge,MASS.
Psaltis, D. and Farhat, N (1985) "Optical information processing based on an associative-memory model of neural nets with thresholding feedback", Optical Letters, Vol.10, No.2, pp98–100, Feb. 1985.
Rumelhart, D.E. and McClelland, J.L. (eds) (1986) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol.1 and Vol.2, Bradford Books, Cambridge, MA.
Sivilotti, M. et al. (1985) "A novel associative memory implemented using collective computation", Chapel-Hill Conf. on VLSI, Chapel Hill, North Carolina, pp329–342, 1985.
Special Issue on Connectionist Models (1985) Cognitive Science, Vol.9, No.1, Ablex: Norwood,NJ.
Stiles,G.S. and Denq,D-L. (1987) "A Quantitative Comparison of the Performance of Three Discrete Distributed Associative Memory", IEEE Trans. Computer, Vol.C-36, No.3, March 1987.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fang, L., Wilson, W.H. (1990). Character pattern recognition on a computational neural network. In: Barter, C.J., Brooks, M.J. (eds) AI '88. AI 1988. Lecture Notes in Computer Science, vol 406. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-52062-7_94
Download citation
DOI: https://doi.org/10.1007/3-540-52062-7_94
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-52062-7
Online ISBN: 978-3-540-46875-2
eBook Packages: Springer Book Archive