Abstract
Pattern recognition and pattern autoassociation are related but not identical tasks attributed to intelligent systems. In pattern recognition, a system is supposed to identify a class Ci, i = 1, ... , K, where an object belongs to, giving the object’s features x which were previously measured and delivered to the system. In autoassociation, an associative memory reconstructs the original pattern x when distorted or incomplete version x’ is presented to the system [1, 8, 2, 3]. Usually such a system is trained to store many original patterns which can be considered as representatives of pattern classes.
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
Amari, S.: Learning patterns and pattern sequences by self-organizing nets of threshold elements, IEEE Transactions on Computers C-21, 1197–1206 (1972).
Amari, S.: Neural theory of association and concept formation, Biological Cybernetics 26, 175–185 (1977).
Hassoun, M.H. (ed.): Associative Neural Memories: Theory and Implementation. Oxford University Press 1993.
Hotelling, H.: Analysis of a complex of statistical variables into principal components, Journal of Educational Psychology 24, 417–441 (1933).
Jacquin, A.: Image coding based on a fractal theory of iterated contractive image transformations, IEEE Transactions on Image Processing 1, 18–30 (1992).
Jain, A.K.: Fundamentals of Digital Image Processing. Prentice-Hall 1989.
Fisher, Y. (ed.): Fractal Image Compression - Theory and Application. Springer Verlag 1995.
Kohonen, T.:, Correlation matrix memories, IEEE Transactions on Computers C-21, 353–359 (1972).
Kohonen, T.: Self-Organization and Associative Memory. Springer Verlag 1988.
Oja, E.: Principal components, minor components, and linear neural networks, Neural Networks 5, 927–935 (1992).
Skarbek, W., Ghuwar, M., Ignasiak, K.: Character classification by projections into KLT subspaces, Proc. of 8th Portuguese Conference on Pattern Recognition RECPAD’96, Guimaraes, 223–226 (1996).
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer-Verlag/Wien
About this paper
Cite this paper
Skarbek, W. (1997). Associative memory for images by recurrent neural subnetworks. In: Solina, F., Kropatsch, W.G., Klette, R., Bajcsy, R. (eds) Advances in Computer Vision. Advances in Computing Science. Springer, Vienna. https://doi.org/10.1007/978-3-7091-6867-7_5
Download citation
DOI: https://doi.org/10.1007/978-3-7091-6867-7_5
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-83022-2
Online ISBN: 978-3-7091-6867-7
eBook Packages: Springer Book Archive