Abstract
Median associative memories (MED-AMs) are a special type of associative memory based on the median operator. This type of associative model has been applied to the restoration of gray scale images and provides better performance than other models, such as morphological associative memories, when the patterns are altered with mixed noise. Despite of his power, MED-AMs have not been applied in problems involving true-color patterns. In this paper we describe how a median hetero-associative memory (MED-HAM) could be applied in problems that involve true-color patterns. A complete study of the behavior of this associative model in the restoration of true-color images is performed using a benchmark of 14400 images altered by different type of noises. Furthermore, we describe how this model can be applied to an image categorization problem.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Steinbuch, K.: Die Lernmatrix. Kybernetik 1, 26–45 (1961)
Anderson, J.A.: A simple neural network generating an interactive memory. Math. Biosci. 14, 197–220 (1972)
Kohonen, T.: Correlation matrix memories. IEEE Trans. on Comp. 21, 353–359 (1972)
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. 79, 2554–2558 (1982)
Sussner, P.: Generalizing operations of binary auto-associative morphological memories using fuzzy set theory. J. Math. Imaging Vis. 19, 81–93 (2003)
Ritter, G.X., et al.: Reconstruction of patterns from noisy inputs using morphological associative memories. J. Math. Imaging Vis. 19, 95–111 (2003)
Kosko, B.: Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to Machine Intelligence. Prentice- Hall, Englewood Cliffs (1992)
Ritter, G.X., Sussner, P., Diaz de Leon, J.L.: Morphological associative memories. IEEE Trans. Neural Networks 9, 281–293 (1998)
Sussner, P., Valle, M.: Gray-Scale Morphological Associative Memories. IEEE Trans. on Neural Netw. 17, 559–570 (2006)
Vazquez, R.A., Sossa, H.: A new associative memory with dynamical synapses. Neural Processing Letters 28(3), 189–207 (2008)
Vazquez, R.A., Sossa, H.: A Bidirectional Heteroassociative Memory for True Color Patterns. Neural Processing Letters 28(3), 131–153 (2008)
Sossa, H., Barron, R., Vazquez, R.A.: New associative memories to recall real-valued patterns. In: Sanfeliu, A., Martínez Trinidad, J.F., Carrasco Ochoa, J.A. (eds.) CIARP 2004. LNCS, vol. 3287, pp. 195–202. Springer, Heidelberg (2004)
Chung, F.-L., Lee, T.: On fuzzy associative memory with multiple-rule storage capacity. IEEE Trans. Fuzzy Syst. 4(4), 375–384 (1996)
Susner, P., Valle, M.E.: Implicative fuzzy associative memory. IEEE Trans. on Fuzzy Systems 14(6), 793–807 (2006)
Sossa, H., Vazquez, R.A.: Flower and Animals Database, http://roberto.a.vazquez.googlepages.com
Ritter, G.X., Urcid, G.: Learning in Lattice Neural Networks that Employ Dedritic Computing. In: Kaburlasos, V.G., Ritter, G.X. (eds.) Computational Intelligence based on Lattice Theory, vol. 67, pp. 25–44 (2007)
Vazquez, R.A., Sossa, H.: Behavior of morphological associative memories with true-color image patterns. Neurocomputing 73, 225–244 (2009)
Vazquez, R.A., Sossa, H.: Associative memories applied to image categorization. In: Martínez-Trinidad, J.F., Carrasco Ochoa, J.A., Kittler, J. (eds.) CIARP 2006. LNCS, vol. 4225, pp. 549–558. Springer, Heidelberg (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vázquez, R.A., Sossa, H. (2010). Median Hetero-Associative Memories Applied to the Categorization of True-Color Patterns. In: Corchado, E., Graña Romay, M., Manhaes Savio, A. (eds) Hybrid Artificial Intelligence Systems. HAIS 2010. Lecture Notes in Computer Science(), vol 6077. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-13803-4_52
Download citation
DOI: https://doi.org/10.1007/978-3-642-13803-4_52
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-13802-7
Online ISBN: 978-3-642-13803-4
eBook Packages: Computer ScienceComputer Science (R0)