Abstract
A system which combines the descriptional power of symbolic representations with the parallel and distributed processing model of cellular automata and the speed and robustness of connectionist symbol processing is described. Following a cellular automata based approach, the aim of the system is to transform initial symbolic descriptions of patterns to corresponding object level descriptions in order to identify patterns in complex or noisy scenes. A learning algorithm based on a hierarchical structural analysis is used to learn symbolic descriptions of objects. The underlying symbolic processing engine of the system is a neural based associative memory (AURA) which enables the system to operate in high speed. In addition, the use of distributed representations allow both efficient inter-cellular communications and compact storage of rules.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Bunke, H.: Structural and syntactic pattern recognition. In: Chen, C.H., Pau, L.F., Wang, P.S.P. (eds.) Handbook of Pattern Recognition & Computer Vision, pp. 163–209. World Scientific, Singapore (1993)
Tombre, K.: Structural and syntactic methods in line drawing analysis: To which extend do they work? In: Perner, P., Rosenfeld, A., Wang, P. (eds.) SSPR 1996. LNCS, vol. 1121, pp. 310–321. Springer, Heidelberg (1996)
Tanaka, E.: Theoretical aspects of syntactic pattern recognition. Pattern Recognition 28(7), 1053–1061 (1995)
Preston, K., Duff, M. (eds.): Modern Cellular Automata: Theory and Applications. Plenum Press, New York (1984)
Wolfram, S.: Computation theory of cellular automata. Communications in Mathematical Physics 57, 15–57 (1984)
Wolfram, S.: Statistical mechanics of cellular automata. Reviews of Modern Physics 55(3), 601–643 (1983)
Burks, A.W. (ed.): Essays on Cellular Automata. University of Illinois Press, US (1970)
Richards, F.C., Thomas, P.M., Packard, N.H.: Extracting cellular automaton rules directly from experimental data. Physica D 45, 189–202 (1990)
Takai, Y., Ecchu, K., Takai, K.: A cellular automaton model of particle motions and its applications. Visual Computer 11 (1995)
Pierre, T., Milgram, M.: New and effcient cellular algorithms for image processing. CVGIP: Image Understanding 55(3), 261–274 (1992)
Duff, M.J.B., Fountain, T.J. (eds.): Cellular Logic Image Processing. Academic Press, London (1986)
Orovas, C.: Cellular Associative Neural Networks for Pattern Recognition. PhD thesis, University of York (1999) (copies are available)
Paun, G., Salomaa, A. (eds.): New Trends in Formal Languages. LNCS, vol. 1218. Springer, Heidelberg (1997)
Csuhaj-Varju, E., Salomaa, A.: Networks of parallel language processors. In: Paun and Salomaa [13], pp. 299–318
Kohonen, T.: Content-Addressable Memories. Springer, Heidelberg (1980)
Austin, J.: Associative memory. In: Fiesler, E., Beale, R. (eds.) Handbook of Neural Computation. Oxford University Press, Oxford (1996)
Hinton, G.E. (ed.): Connectionist Symbol Processing. MIT/Elsevier (1990)
Sun, R., Bookman, L.A. (eds.): Computational architectures integrating neural and symbolic processing. Kluwer Academic Publishers, Dordrecht (1995)
Austin, J., Lees, K.: A neural architecture for fast rule matching. In: Proceedings of the Artificial Neural Networks and Expert Systems Conference, Dunedin, New Zealand (December 1995)
Willshaw, D.J., Buneman, O.P., Longuet-Higgins, H.C.: Non-holographic associative memory. Nature 222(7), 960–962 (1969)
Casasent, D., Telfer, B.: High capacity pattern recognition associative processors. Neural Networks 5, 687–698 (1992)
Austin, J., Stonham, T.J.: Distributed associative memory for use in scene analysis. Image and Vision Computing 5(4), 251–261 (1987)
Kennedy, J., Austin, J.: A parallel architecture for binary neural networks. In: Proceedings of the 6th International Conference on Microelectronics for Neural Networks, Evolutionary & Fuzzy Systems (MICRONEURO 1997), Dresden, September 1997, pp. 225–232 (1997)
Rozenberg, G., Salomma, A. (eds.): Handbook of Formal Languages, vol. I-II-III. Springer, Heidelberg (1997)
Orovas, C., Austin, J.: A cellular system for pattern recognition using associative neural networks. In: 5th IEEE International Workshop on Cellular Neural Networks and their Applications, London, April 1998, pp. 143–148 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Orovas, C., Austin, J. (2000). A Cellular Neural Associative Array for Symbolic Vision. In: Wermter, S., Sun, R. (eds) Hybrid Neural Systems. Hybrid Neural Systems 1998. Lecture Notes in Computer Science(), vol 1778. Springer, Berlin, Heidelberg. https://doi.org/10.1007/10719871_26
Download citation
DOI: https://doi.org/10.1007/10719871_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67305-7
Online ISBN: 978-3-540-46417-4
eBook Packages: Springer Book Archive