Abstract
A neural network consisting of a gallery of independent subnetworks is developed for associative memory which stores and recalls gray scale images. Each original image is encoded by a unique stable state of one of neural recurrent subnetworks. Comparing to Amari-Hopfield associative memory, our solution has no spurious states, is less sensitive to noise, and its network complexity is significantly lower. Computer simulations confirm that associative recall in this system for images of natural scenes is very robust. Colored additive and multiplicative noise with standard deviation up to σ=2 can be removed perfectly from normalized image. The same observations are valid for spiky noise distributed on up to 70% of image area. Even if we remove up to 95% pixels from the original image in deterministic or random way, still the network performs the correct association.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
T. Kohonen, “Correlation matrix memories”, IEEE Transactions on Computers, Vol. C-21, pp. 353–359, 1972.
T. Kohonen, “Self-Organization and Associative Memory”, Springer-Verlag: New York, 1988.
S. Amari, “Learning patterns and pattern sequences by self-organizing nets of threshold elements”, IEEE Transactions on Computers, Vol. C-21, pp. 1197–1206, 1972.
S. Amari, “Neural theory of association and concept formation”, Biological Cybernetics, Vol. 26, pp. 175–185, 1977.
J. J. Hopfield, “Neural networks and physical systems with emergent collective computational abilities”, Proc. Natl. Acad. Sci. USA, Biophysics, Vol. 79, pp. 2554–2558, 1982.
A. Cichocki and R. Unbehauen, Neural Networks for Optimization and Signal Processing, John Wiley & Sons Ltd.: Chichester 1993.
M. H. Hassoun (ed), Associative Neural Memories: Theory and Implementation, Oxford University Press: Oxford 1993.
M. H. Hassoun, Fundamentals of Artificial Neural Networks, The MIT Press: Cambridge 1995.
W. Skarbek and A. Cichocki, “Image associative memory by recurrent neural subnetworks”, FRP RIKEN, ABS Laboratory — internal report, January 1996.
A. Jacquin, “Image coding based on a fractal theory of iterated contractive image transformations”, IEEE Transactions on Image Processing, Vol. 1, pp. 18–30, 1992.
Y. Fisher (ed), Fractal Image Compression — Theory and Application, Springer-Verlag: New York 1995.
W. Skarbek and A. Cichocki, “Gray scale image representation by recurrent vector neural networks”, Proc. 1995 Int. Symp. on Nonlinear Theory and its Applications (Las Vegas), Vol. 1, pp. 555–558, Research Society of Nonlinear Theory and its Applications, Tokyo, Japan, 1995.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Skarbek, W., Cichocki, A. Robust image association by recurrent neural subnetworks. Neural Process Lett 3, 131–138 (1996). https://doi.org/10.1007/BF00420282
Issue Date:
DOI: https://doi.org/10.1007/BF00420282