A New Algorithm for Training Multi-layered Morphological Networks

  • Ricardo Barrón
  • Humberto Sossa
  • Benjamín Cruz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4756)


In this work we present an algorithm for training an associative memory based on the so-called multi-layered morphological perceptron with maximal support neighborhoods. We compare the proposal with the original one by performing some experiments with real images. We show the superiority of the new one. We also give formal conditions for correct classification. We show that the proposal can be applied to the case of gray-level images and not only binary images.


Associative memories Morphological neural networks maximal support neighborhoods 


  1. 1.
    Bishop, C.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford England (1995)Google Scholar
  2. 2.
    Rossenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review 65, 386–408 (1958)CrossRefGoogle Scholar
  3. 3.
    Rossenblatt, F.: Principles of Neurodinamics: Perceptrons and the theory of brain mechanism, Spartians Books, Washington D.C (1962)Google Scholar
  4. 4.
    Ritter, G.X., et al.: An introduction to morphological Neural Networks. In: Proceedings of the 13International Conference on Pattern Recognition, pp. 709–717 (1996)Google Scholar
  5. 5.
    Ritter, G.X., et al.: Morphological associative memories. IEEE Transactions on Neural Networks C-9, 281–293 (1998)CrossRefGoogle Scholar
  6. 6.
    Ritter, G.X.: Morphological Perceptrons. ISAS’97, Intelligent Systems and Semiotics, Gaithersburg, Maryland (1997)Google Scholar
  7. 7.
    Ritter, G.X.: A new auto-associative memory based on lattice algebra. In: Proc. 9CIARP 2004, La Havana, Cuba pp. 148–155 (2004)Google Scholar
  8. 8.
    Kishan, M., et al.: Elements of Artificial Neural Networks. The MIT Press, Cambridge, Massachusetts, London, England (1997)zbMATHGoogle Scholar
  9. 9.
    Pessoa, L.F.C., et al.: Morphological/Rank Neural Networks and their adaptative optimal image processing. IEEE International Conference on Acoustic, Speech, and Signal Processing 6, 3399–3402 (1996)Google Scholar
  10. 10.
    Hu, M.K.: Pattern recognition by moments invariants. Proceeding of the IRE 49, 1428 (1961)Google Scholar
  11. 11.
    Hu, M.K.: Visual pattern recognition by moments invariants, IRE Transactions on Information Theory, 179–187 (1962)Google Scholar
  12. 12.
    Sussner, P.: Morphological Perceptron Learning. In: Proceedings of the 1998 International Symposium on Intelligent Systems and Semiotics, pp. 477-482, Gaithersburg, Maryland (1998)Google Scholar
  13. 13.
    Barron, R., et al.: New Improved Algorithm for the training of a Morphological Associative Memory, Research in Computer Science. Special Issue: Neural Networks and Associative Memories 21, 49–59 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Ricardo Barrón
    • 1
  • Humberto Sossa
    • 1
  • Benjamín Cruz
    • 1
  1. 1.Centro de Investigación en Computación-IPN Av. Juan de Dios Bátiz esquina con Miguel Othón de Mendizábal Mexico City, 07738Mexico

Personalised recommendations