Abstract
Morphological neural networks are rooted in mathematical morphology (MM). Several constructive learning algorithms for morphological neural networks have been proposed during the last decade. SinceMMcan be conducted very generally in the complete lattice setting, MNNs are closely related to other lattice-based neurocomputing models.
This paper reviews and analyzes some important types of constructive morphological neural networks including their learning algorithms from the latticetheoretical perspective of mathematical morphology. In particular, we present an improved version of the learning algorithm for the morphological perceptron (MP). Moreover, we incorporate competitive nodes into the two variants of the MP and introduce an approach for training these models. Finally, we compare the performance of several constructive morphological models and of conventional multi-layer perceptrons in some classification problems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Araújo, R.A., Madeiro, R., 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)
Armstrong, W.W., Thomas, M.M.: Adaptive Logic Networks. In: Fiesler, E., Beale, R. (eds.) Handbook of Neural Computation, vol. C1.8, pp. 1–14. IOP Publishing, Oxford University Press, Oxford United Kingdom (1997)
Araújo, R.A., Madeiro, F., Pessoa, L.F.C.: Modular morphological neural network training via adaptive genetic algorithm for design translation invariant operators. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Toulouse, France (May 2006)
Banon, G., Barrera, J.: Decomposition of Mappings between Complete Lattices by Mathematical Morphology, Part 1, General Lattices. Signal Processing 30(3), 299–327 (1993)
Birkhoff, G.: Lattice Theory, 3rd edn. American Mathematical Society, Providence (1993)
Asuncion, A., Newman, D.J.: UCI Repository of machine learning databases, University of California, Irvine, CA, School of Information and Computer Sciences (2007), http://www.ics.uci.edu/~mlearn/MLRepository.html
Braga-Neto, U., Goutsias, J.: Supremal multiscale signal analysis. SIAM Journal of Mathematical Analysis 36(1), 94–120 (2004)
Carpenter, G.A., Grossberg, S.: ART 3: Hierarchical search using chemical transmitters in self-organizing pattern recognition architectures. In: Neural Networks, vol. 3, pp. 129–152 (1990)
Carré, B.: An algebra for network routing problems J. Inst. Math. Appl. 7, 273–294 (1971)
Coskun, N., Yildirim, T.: The effects of training algorithms in MLP network on image classification. Neural Networks 2, 1223–1226 (2003)
Cuninghame-Green, R.: Minimax Algebra and Applications. In: Hawkes, P. (ed.) Advances in Imaging and Electron Physics, vol. 90, pp. 1–121. Academic Press, New York (1995)
Cuninghame-Green, R., Meijer, P.F.J.: An Algebra for Piecewise-Linear Minimax Problems. Discrete Applied Mathematics 2(4), 267–286 (1980)
Cuninghame-Green, R.: Minimax Algebra: Lecture Notes in Economics and Mathematical Systems, vol. 166. Springer, New York (1979)
Davey, B.A., Priestley, H.A.: Introduction to lattices and order. Cambridge University Press, Cambridge (2002)
Gader, P.D., Khabou, M., Koldobsky, A.: Morphological Regularization Neural Networks. Pattern Recognition, Special Issue on Mathematical Morphology and Its Applications 33(6), 935–945 (2000)
Giffler, B.: Mathematical solution of production planning and scheduling problems. IBM ASDD, Tech. Rep (1960)
Graña, M., Gallego, J., Torrealdea, F.J., D’Anjou, A.: On the application of associative morphological memories to hyperspectral image analysis. In: Mira, J., Álvarez, J.R. (eds.) IWANN 2003. LNCS, vol. 2687, pp. 567–574. Springer, Heidelberg (2003)
Grätzer, G.A.: Lattice theory: first concepts and distributive lattices. W. H. Freeman, San Francisco (1971)
Haralick, R.M., Shapiro, L.G.: Computer and Robot Vision, vol. 1. Addison-Wesley, New York (1992)
Haralick, R.M., Sternberg, S.R., Zhuang, X.: Image Analysis Using Mathematical Morphology: Part I. IEEE Transactions on Pattern Analysis and Machine Intelligence 9(4), 532–550 (1987)
Heijmans, H.: Morphological Image Operators. Academic Press, New York (1994)
Hocaoglu, A.K., Gader, P.D.: Domain learning using Choquet integral-based morphological shared weight neural networks. Image and Vision Computing 21(7), 663–673 (2003)
Kaburlasos, V.G., Athanasiadis, I.N., Mitkas, P.A.: Fuzzy lattice reasoning (FLR) classifier and its application for ambient ozone estimation. International Journal of aproximate reasoning 45(1), 152–188 (2003)
Kaburlasos, V.G., Petridis, V.: Fuzzy lattice neurocomputing (FLN) models. Neural Networks 13, 1145–1170 (2000)
Khabou, M.A., Gader, P.D.: Automatic target detection using entropy optimized shared-weight neural networks. IEEE Transactions on Neural Networks 11(1), 186–193 (2000)
Kim, C.: Segmenting a low-depth-of-field image using morphological filters and region merging. IEEE Transactions on Image Processing 14(10), 1503–1511 (2005)
Kwok, J.T.: Moderating the Outputs of Support Vector Machine Classifiers. IEEE Transactions on Neural Networks 10(5), 1018–1031 (1999)
Matheron, G., Random Sets and Integral Geometry. Wiley, New York, (1975).
Monteiro, A.S., Sussner, P.: A Brief Review and Comparison of Feedforward Morphological Neural Networks with Applications to Classification. In: Kůrková, V., Neruda, R., Koutník, J. (eds.) ICANN 2008,, Part II. LNCS, vol. 5164, pp. 783–792. Springer, Heidelberg (2008)
Pessoa, L.F.C., Maragos, P.: Neural networks with hybrid morphological/rank/linear nodes: a unifying framework with applications to handwritten character recognition. Pattern Recognition 33, 945–960 (2000)
Petridis, V., Kaburlasos, V.G.: Fuzzy lattice neural network (FLNN): a hybrid model for learning. IEEE Transactions on Neural Networks 9(5), 877–890 (1998)
Pitas, I., Venetsanopoulos, A.N.: Morphological Shape Decomposition. IEEE Transactions on Pattern Analysis and Machine Intelligence 12(1), 38–45 (1990)
Porter, R., Harvey, N., Perkins, S., Theiler, J., Brumby, S., Bloch, J., Gokhale, M., Szymanski, J.: Optimizing digital hardware perceptrons for multispectral image classification. Journal of Mathematical Imaging and Vision 19(2), 133–150 (2003)
Raducanu, B., Graña, M., Albizuri, X.F.: Morphological Scale Spaces and Associative Morphological Memories: Results on Robustness and Practical Applications. Journal of Mathematical Imaging and Vision 19(2), 113–131 (2003)
Ripley, B.D.: Pattern Recognition and Neural Networks. Cambridge University Press, Cambridge (1996)
Ripley, B.D.: Datasets for Pattern Recognition and Neural Networks, Cambridge, United Kingdom (1996), http://www.stats.ox.ac.uk/pub/PRNN/
Ritter, G.X., Iancu, L., Urcid, G.: Morphological perceptrons with dendritic structure. In: The 12th IEEE International Conference, Fuzzy Systems, May 2003, vol. 2, pp. 1296–1301 (2003)
Ritter, G.X., Urcid, G.: Lattice Algebra Approach to Single-Neuron Computation. IEEE Transactions on Neural Networks 14(2), 282–295 (2003)
Ritter, G.X., Wilson, J.N.: Handbook of Computer Vision Algorithms in Image Algebra, 2nd edn. CRC Press, Boca Raton (2001)
Ritter, G.X., Sussner, P.: Morphological Perceptrons Intelligent Systems and Semiotics, Gaithersburg, Maryland (1997)
Ritter, G.X., Wilson, J.N., Davidson, J.L.: Image Algebra: An Overview. Computer Vision, Graphics, and Image Processing 49(3), 297–331 (1990)
Ronse, C.: Why Mathematical Morphology Needs Complete Lattices. Signal Processing 21(2), 129–154 (1990)
Segev, I.: Dendritic processing. In: Arbib, M.A. (ed.) The handbook of brain theory and neural networks, MIT Press, Cambridge (1998)
Serra, J.: Image Analysis and Mathematical Morphology. In: Theoretical Advances, vol. 2, Academic Press, New York (1998)
Serra, J.: Image Analysis and Mathematical Morphology. Academic Press, London (1982)
Khabou, M.A., Gader, P.D., Keller, J.M.: LADAR target detection using morphological shared-weight neural networks. Machine Vision and Applications 11(6), 300–305 (2000)
Sobania, A., Evans, J.P.O.: Morphological corner detector using paired triangular structuring elements. Pattern Recognition 38(7), 1087–1098 (2005)
Soille, P.: Morphological Image Analysis. Springer, Berlin (1999)
Sousa, R.P., Pessoa, L.F.C., Carvalho, J.M.: Designing translation invariant operations via neural network training. In: Proceedings of the IEE International Conference on Image Processing, Vancouver, Canada, pp. 908–911 (2000)
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. Studies in Computational Intelligence, vol. 67, pp. 149–173. Springer, Heidelberg (2007)
Sussner, P., Valle, M.E.: Gray Scale Morphological Associative Memories. IEEE Transactions on Neural Networks 17(3), 559–570 (2006)
Sussner, P., Valle, M.E.: Implicative Fuzzy Associative Memories. IEEE Transactions on Fuzzy Systems 14(6), 793–807 (2006)
Sussner, P., Grana, M.: Guest Editorial: Special Issue on Morphological Neural Networks. Journal of Mathematical Imaging and Vision 19(2), 79–80 (2003)
Sussner, P.: Morphological Perceptron Learning. In: Proceedings of IEEE ISIC/CIRA/ISAS Joint Conference, Gaithersburg, MD, September 1998, pp. 477–482 (1998)
Valle, M.E., Sussner, P.: A General Framework for Fuzzy Morphological Associative Memories. Fuzzy Sets and Systems 159(7), 747–768 (2008)
Zadeh, L.A.: Fuzzy Sets. Information and Control 8(3), 338–353 (1965)
Zimmermann, U.: Linear amd Combinatorial Optimization of Ordered Algebraic Structures. North-Holland, Amsterdam (1981)
Yu, A.J., Giese, M.A., Poggio, T.: Biophysiologically Plausible Implementations of the Maximum Operation. Neural Computation 14(12), 2857–2881 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Sussner, P., Esmi, E.L. (2009). Constructive Morphological Neural Networks: Some Theoretical Aspects and Experimental Results in Classification. In: Franco, L., Elizondo, D.A., Jerez, J.M. (eds) Constructive Neural Networks. Studies in Computational Intelligence, vol 258. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04512-7_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-04512-7_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04511-0
Online ISBN: 978-3-642-04512-7
eBook Packages: EngineeringEngineering (R0)