Abstract
Many well-known fuzzy associative memory (FAM) models can be viewed as (fuzzy) morphological neural networks (MNNs) because they perform an operation of (fuzzy) mathematical morphology at every node, possibly followed by the application of an activation function. The vast majority of these FAMs represent distributive models given by single-layer matrix memories. Although the Kosko subsethood FAM (KS-FAM) can also be classified as a fuzzy morphological associative memory (FMAM), the KS-FAM constitutes a two-layer non-distributive model.
In this paper, we prove several theorems concerning the conditions of perfect recall, the absolute storage capacity, and the output patterns produced by the KS-FAM. In addition, we propose a normalization strategy for the training and recall phases of the KS-FAM. We employ this strategy to compare the error correction capabilities of the KS-FAM and other fuzzy and gray-scale associative memories in terms of some experimental results concerning gray-scale image reconstruction. Finally, we apply the KS-FAM to the task of vision-based self-localization in robotics.
Similar content being viewed by others
References
Araújo, R.A., Ferreira, T.A.E.: A morphological-rank-linear evolutionary method for stock market prediction. Inf. Sci. (2010, in press). doi:10.1016/j.ins.2009.07.007
Araújo, R.A., Madeiro, F., Sousa, R.P., Pessoa, L.F.C., Ferreira, T.A.E.: An evolutionary morphological approach for financial time series forecasting. In: Proceedings of the IEEE Congress on Evolutionary Computation, Vancouver, Canada, pp. 2467–2474 (2006)
Baczynski, M., Jayaram, B.: Fuzzy implications. In: Studies in Fuzziness and Soft Computing. Springer, Berlin (2008)
Banon, G.J.F., Barrera, J.: Decomposition of mappings between complete lattices by mathematical morphology. Part 1. General lattices. Signal Process. 30(3), 299–327 (1993)
Bargiela, A., Pedrycz, W.: Granular Computing: An Introduction. Kluwer Academic, Dordrecht (2003)
Belohlávek, R.: Fuzzy logical bidirectional associative memory. Inf. Sci. 128(1–2), 91–103 (2000)
Birkhoff, G.: Lattice Theory. American Mathematical Society, Providence (1993)
Cuninghame-Green, R.: Minimax Algebra. Lecture Notes in Economics and Mathematical Systems, vol. 166. Springer, New York (1979)
Cuninghame-Green, R.: Minimax algebra and applications. In: Hawkes, P. (ed.) Advances in Imaging and Electron Physics, pp. 1–121. Academic Press, San Diego (1995)
Davidson, J.L.: Foundation and applications of lattice transforms in image processing. In: Hawkes, P. (ed.) Advances in Electronics and Electron Physics, vol. 84, pp. 61–130. Academic Press, San Diego (1992)
Davidson, J.L., Hummer, F.: Morphology, neural networks: an introduction with applications. Circuits Syst. Signal Process. 12(2), 177–210 (1993)
Deng, T.Q., Heijmans, H.J.A.M.: Grey-scale morphology based on fuzzy logic. J. Math. Imaging Vis. 16(2), 155–171 (2002)
Esmi, E.L., Sussner, P.: A fuzzy associative memory based on Kosko’s subsethood measure. In: Proceedings of the 2010 IEEE World Congress on Computational Intelligence (IJCNN), Barcelona, Spain, pp. 144–151 (2010)
Fuller, R.: Introduction to Neuro-Fuzzy Systems. Springer, New York (2000)
Gader, P.D., Khabou, M., Koldobsky, A.: Morphological regularization neural networks. Pattern Recognit. 33(6), 935–945 (2000). Special Issue on Mathematical Morphology and Its Applications
Graña, M., Savio, A.M., Garcia-Sebastian, M., Fernandez, E.: A lattice computing approach for on-line fMRI analysis. Image Vis. Comput. 28(7), 1155–1161 (2010)
Graña, M., Chyzhyk, D., Garcia-Sebastian, M., Hernandez, C.: Lattice independent component analysis for functional magnetic resonance imaging. Inf. Sci. 181(10), 1910–1929 (2011)
Grätzer, G.A.: Lattice Theory: First Concepts and Distributive Lattices. Freeman, New York (1971)
Hassoun, M.H., Watta, P.B.: The Hamming associative memory and its relation to the exponential capacity DAM. IEEE Int. Conf. Neural Netw. 1, 583–587 (1996)
Heijmans, H.J.A.M.: Morphological Image Operators. Academic Press, San Diego (1994)
Højen-Sørensen, P., Winther, O., Hansen, L.K.: Mean-field approaches to independent component analysis. Neural Comput. 14(4), 889–918 (2002)
Image Database for Simulations Concerning Vision-Based Self-Localization in Mobile Robotics. Available at http://www.ehu.es/ccwintco/index.php/Pioneer. Computational Intelligence Group, University of the Basque Country, San Sebastián, Spain
Internet Site of the Math. Imaging and Comp. Intelligence Group. http://www.milab.ime.unicamp.br, Dept. of Applied Math., University of Campinas
Jones, S.D., Andresen, C., Crowley, J.L.: Appearance based process for visual navigation. In: Proceedings of the 1997 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 1997), vol. 2, pp. 551–557 (1997)
Junbo, F., Fan, J., Yan, S.: A learning rule for fuzzy associative memories. In: Proceedings of the IEEE International Joint Conference on Neural Networks, vol. 7, pp. 4273–4277 (1994)
Kaburlasos, V.G.: FINs: lattice theoretic tools for improving prediction of sugar production from populations of measurements. IEEE Trans. Syst. Man Cybern., Part B, Cybern. 34(2), 1017–1030 (2004)
Kaburlasos, V.G.: Towards a Unified Modeling and Knowledge-Representation Based on Lattice Theory: Computational Intelligence and Soft Computing Applications. Studies in Computational Intelligence. Springer, New York (2006)
Kaburlasos, V.G., Papadakis, S.E.: A granular extension of the fuzzy-ARTMAP (FAM) neural classifier based on fuzzy lattice reasoning (FLR). Neurocomputing 72(10–12), 2067–2078 (2009)
Kaburlasos, V.G., Petridis, V.: Fuzzy lattice neurocomputing (FLN) models. Neural Netw. 13(10), 1145–1170 (2000)
Kaburlasos, V.G., Athanasiadis, I.N., Mitkas, P.A.: Fuzzy lattice reasoning (FLR) classifier and its application for ambient ozone estimation. Int. J. Approx. Reason. 45(1), 152–188 (2007)
Khabou, M.A., Gader, P.D., Shi, H.: Entropy optimized morphological shared-weight neural networks. Opt. Eng. 38(2), 263–273 (1999)
Khabou, M.A., Gader, P.D., Keller, J.M.: LADAR target detection using morphological shared-weight neural networks. Mach. Vis. Appl. 11(6), 300–305 (2000)
Kohonen, T.: Self-Organization and Associative Memory. Springer, Berlin (1984)
Kong, S.-G., Kosko, B.: Adaptive fuzzy systems for backing up a truck-and-trailer. IEEE Trans. Neural Netw. 3(2), 211–223 (1992)
Kosko, B.: Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to Machine Intelligence. Prentice Hall, New York (1992)
Krose, B.J.A., Vlassis, N., Bunschoten, R., Motomura, Y.: A probabilistic model for appearance-based robot localization. Image Vis. Comput. 6(19), 381–391 (2001)
Lippmann, R.P.: An introduction to computing with neural nets. IEEE Trans. Acoust. Speech Signal Process. ASSP-4, 4–22 (1987)
Liu, P.: The fuzzy associative memory of max-min fuzzy neural networks with threshold. Fuzzy Sets Syst. 107, 147–157 (1999)
Liu, H., Xiong, S., Fang, Z.: FL-GrCCA: a granular computing classification algorithm based on fuzzy lattices. Comput. Math. Appl. 61, 138–147 (2011)
Matheron, G.: Random Sets and Integral Geometry. Wiley, New York (1975)
Molgedey, L., Schuster, H.G.: Separation of a mixture of independent signals using time delayed correlations. Phys. Rev. Lett. 72, 3634–3637 (1994)
Nachtegael, M., Kerre, E.E.: Connections between binary, gray-scale and fuzzy mathematical morphologies. Fuzzy Sets Syst. 124(1), 73–85 (2001)
Pessoa, L.F.C., Maragos, P.: Neural networks with hybrid morphological/rank/linear nodes: a unifying framework with applications to handwritten character recognition. Pattern Recognit. 33, 945–960 (2000)
Petridis, V., Kaburlasos, V.G.: Fuzzy lattice neural network (FLNN): a hybrid model for learning. IEEE Trans. Neural Netw. 9(5), 877–890 (1998)
Raducanu, B., Graña, M., Sussner, P.: Morphological neural networks for vision based self-localization. In: Proceedings of the 2001 IEEE International Conference on Robotics and Automation (ICRA 2001), vol. 2, pp. 2059–2064 (2001)
Ritter, G.X., Sussner, P.: An introduction to morphological neural networks. In: Proceedings of the 13th International Conference on Pattern Recognition, Vienna, Austria, pp. 709–717 (1996)
Ritter, G.X., Sussner, P., Diaz de Leon, J.L.: Morphological associative memories. IEEE Trans. Neural Netw. 9(2), 281–293 (1998)
Ronse, C.: Why mathematical morphology needs complete lattices. Signal Process. 21(2), 129–154 (1990)
Serra, J.: Image Analysis and Mathematical Morphology. Academic Press, San Diego (1982)
Serra, J.: Image Analysis and Mathematical Morphology. Theoretical Advances, vol. 2. Academic Press, San Diego (1988)
Soille, P.: Morphological Image Analysis. Springer, Berlin (1999)
Sussner, P.: Generalizing operations of binary morphological autoassociative memories using fuzzy set theory. J. Math. Imaging Vis. 9(2), 81–93 (2003)
Sussner, P.: Associative morphological memories based on variations of the kernel and dual kernel methods. Neural Netw. 16(5), 625–632 (2003)
Sussner, P., Esmi, E.L.: An Introduction to the Kosko subsethood FAM. In: Proc. of the 5th Int. Conf. on Hybrid Artificial Intelligence Systems. Lecture Notes in Computer Science, vol. 6077, pp. 343–350. Springer, Berlin (2010)
Sussner, P., Esmi, E.L.: Morphological perceptrons with competitive learning: lattice-theoretical framework and constructive learning algorithm. Inf. Sci. 181(10), 1929–1950 (2011)
Sussner, P., Valle, M.E.: Implicative fuzzy associative memories. IEEE Trans. Fuzzy Syst. 14(6), 793–807 (2006)
Sussner, P., Valle, M.E.: Grayscale morphological associative memories. IEEE Trans. Neural Netw. 17(3), 559–570 (2006)
Sussner, P., Valle, M.E.: Morphological and certain fuzzy morphological associative memories with applications in classification and prediction. In: Kaburlasos, V.G., Ritter, G.X. (eds.) Computational Intelligence Based on Lattice Theory, vol. SCI-67, pp. 149–173. Springer, Berlin (2007)
Sussner, P., Valle, M.E.: Fuzzy associative memories and their relationship to mathematical morphology. In: Pedrycz, W., Skowron, A., Kreinovich, V. (eds.) Handbook of Granular Computing. Wiley, New York (2008), Chap. 33
Sussner, P., Valle, M.E.: Classification of fuzzy mathematical morphologies based on concepts of inclusion measure and duality. J. Math. Imaging Vis. 32(2), 139–159 (2008)
Tanaka, G., Aihara, K.: Complex-valued multistate associative memory with nonlinear multilevel functions for gray-level image reconstruction. In: IEEE International Joint Conference on Neural Networks, pp. 3086–3092 (2008)
Valle, M.E., Sussner, P.: A general framework for fuzzy morphological associative memories. Fuzzy Sets Syst. 159(7), 747–768 (2008)
Valle, M.E., Sussner, P.: Storage and recall capabilities of fuzzy morphological associative memories with adjunction-based learning. Neural Netw. 24(1), 75–90 (2011)
Villaverde, I., D’Anjou, A., Graña, M.: Morphological neural networks and vision based simultaneous localization and mapping. Integr. Comput.-Aided Eng. 14(4), 355–363 (2007)
Villaverde, I., Fernandez-Gauna, B., Zulueta, E.: Lattice independent component analysis for mobile robot localization. In: Proc. of the 5th Int. Conf. on Hybrid Artificial Intelligence Systems. Lecture Notes in Computer Science, vol. 6077, pp. 335–342. Springer, Berlin (2010)
Zhang, B.-L., Zhang, H., Ge, S.S.: Face recognition by applying wavelet subband representation and kernel associative memory. IEEE Trans. Neural Netw. 15(1), 166–177 (2004)
Zivkovic, Z., Bakker, B., Krose, B.J.A.: Hierarchical map building using visual landmarks and geometric constraints. In: Proceedings of the 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2005), pp. 2480–2485 (2005)
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was partially supported by CNPq under grant no. 309608/2009-0 and by FAPESP under grant no. 2009/16284-2.
Rights and permissions
About this article
Cite this article
Sussner, P., Esmi, E.L., Villaverde, I. et al. The Kosko Subsethood Fuzzy Associative Memory (KS-FAM): Mathematical Background and Applications in Computer Vision. J Math Imaging Vis 42, 134–149 (2012). https://doi.org/10.1007/s10851-011-0292-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-011-0292-0