Abstract
In this paper, we present a novel associative memory approach for pattern recognition termed as Distributed Hierarchical Graph Neuron (DHGN). DHGN is a scalable, distributed, and one-shot learning pattern recognition algorithm which uses graph representations for pattern matching without increasing the computation complexity of the algorithm. We have successfully tested this algorithm for character patterns with structural and random distortions. The pattern recognition process is completed in one-shot and within a fixed number of steps.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Tou, J.T., Gonzalez, R.C.: Pattern Recognition Principles. In: Kalaba, R. (ed.) Applied Mathematics and Computation, Addison-Wesley Publishing Co., Reading, Massachussets (1974)
Sussner, P., Valle, M.E.: Gray-Scale Morphological Associative Memories. IEEE Transactions on Neural Networks 17, 559–570 (2006)
Leimer, J.J.: Design Factors in the Developmentof an Optical Character Recognition Machine. IEEE Transactions on Information Theory, 167–171 (1962)
Casasent, D.: Coherent Optical Pattern Recognition. In: Proceedings of the IEEE (1979)
Smagt, P.V.D.: A comparative study of neural network algorithms applied to optical character recognition. In: International conference on Industrial and engineering applications of artificial intelligence and expert systems, ACM Press, Charleston, South Carolina, United States (1990)
Khan, A.I.: A Peer-to-Peer Associative Memory Network for Intelligent Information Systems. In: The Proceedings of The Thirteenth Australasian Conference on Information Systems, Melbourne, Australia (2002)
Khan, A.I., Mihailescu, P.: Parallel Pattern Recognition Computations within a Wireless Sensor Network. In: ICPR 2004. Proceedings of the 17th International Conference on Pattern Recognition, IEEE Computer Society, Cambridge, United Kingdom (2004)
Khan, A.I., Amin, A.H.M.: An On-line Scheme for Threat Detection Within Mobile Ad Hoc Networks. In: Yang, L.T., et al. (eds.) Mobile Intelligence: Mobile Computing and Computational Intelligence, John Wiley & Sons, England (in print, 2007)
Baqer, M., Khan, A.I., Baig, Z.A.: Implementing a graph neuron array for pattern recognition within unstructured wireless sensor networks. In: Proceedings of EUC Workshops (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Khan, A.I., Amin, A.H.M. (2007). One Shot Associative Memory Method for Distorted Pattern Recognition. In: Orgun, M.A., Thornton, J. (eds) AI 2007: Advances in Artificial Intelligence. AI 2007. Lecture Notes in Computer Science(), vol 4830. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76928-6_79
Download citation
DOI: https://doi.org/10.1007/978-3-540-76928-6_79
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76926-2
Online ISBN: 978-3-540-76928-6
eBook Packages: Computer ScienceComputer Science (R0)