The Underlying Formal Model of Algorithmic Lateral Inhibition in Motion Detection

  • José Mira
  • Ana E. Delgado
  • Antonio Fernández-Caballero
  • María T. López
  • Miguel A. Fernández
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4528)


Many researchers have explored the relationship between recurrent neural networks and finite state machines. Finite state machines constitute the best characterized computational model, whereas artificial neural networks have become a very successful tool for modeling and problem solving. Recently, the neurally-inspired algorithmic lateral inhibition (ALI) method and its application to the motion detection task have been introduced. The article shows how to implement the tasks directly related to ALI in motion detection by means of a formal model described as finite state machines. Automata modeling is the first step towards real-time implementation by FPGAs and programming of ”intelligent” camera processors.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fernández-Caballero, A., Mira, J., Fernández, M.A., López, M.T.: Segmentation from motion of non-rigid objects by neuronal lateral interaction. Pattern Recognition Letters 22(14), 1517–1524 (2001)CrossRefzbMATHGoogle Scholar
  2. 2.
    Fernández-Caballero, A., Mira, J., Delgado, A.E., Fernández, M.A.: Lateral interaction in accumulative computation: A model for motion detection. Neurocomputing 50C, 341–364 (2003)CrossRefGoogle Scholar
  3. 3.
    Fernández-Caballero, A., Fernández, M.A., Mira, J., Delgado, A.E.: Spatio-temporal shape building from image sequences using lateral interaction in accumulative computation. Pattern Recognition 36(5), 1131–1142 (2003)CrossRefzbMATHGoogle Scholar
  4. 4.
    Fernández-Caballero, A., Mira, J., Fernández, M.A., Delgado, A.E.: On motion detection through a multi-layer neural network architecture. Neural Networks 16(2), 205–222 (2003)CrossRefGoogle Scholar
  5. 5.
    Mira, J., Delgado, A.E., Fernández-Caballero, A., Fernández, M.A.: Knowledge modelling for the motion detection task: The lateral inhibition method. Expert Systems with Applications 7(2), 169–185 (2004)CrossRefGoogle Scholar
  6. 6.
    López, M.T., Fernández-Caballero, A., Fernández, M.A., Mira, J., Delgado, A.E.: Visual surveillance by dynamic visual attention method. Pattern Recognition 39(11), 2194–2211 (2006)CrossRefGoogle Scholar
  7. 7.
    López, M.T., Fernández-Caballero, A., Fernández, M.A., Mira, J., Delgado, A.E.: Motion features to enhance scene segmentation in active visual attention. Pattern Recognition Letters 27(5), 469–478 (2006)CrossRefGoogle Scholar
  8. 8.
    Ñeco, R.P., Forcada, M.L.: Asynchronous translations with recurrent neural nets. In: Proceedings of the International Conference on Neural Networks, ICNN’97, vol. 4, pp. 2535–2540 (1997)Google Scholar
  9. 9.
    McCulloch, W.S., Pitts, W.H.: A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics 5, 115–133 (1943)CrossRefMathSciNetzbMATHGoogle Scholar
  10. 10.
    Kleene, S.C.: Representation of events in nerve nets and finite automata. In: Automata Studies, Princeton University Press, Princeton (1956)Google Scholar
  11. 11.
    Minsky, M.L.: Computation: Finite and Infinite Machines. Prentice-Hall, Englewood Cliffs (1967)zbMATHGoogle Scholar
  12. 12.
    Carrasco, R.C., Oncina, J., Forcada, M.L.: Efficient encoding of finite automata in discrete-time recurrent neural networks. In: Proceedings of the Ninth International Conference on Artificial Neural Networks, ICANN’99, vol. 2, pp. 673–677 (1999)Google Scholar
  13. 13.
    Forcada, M.L., Carrasco, R.C.: Finite-state computation in analog neural networks: Steps towards biologically plausible models? In: Wermter, S., Austin, J., Willshaw, D. (eds.) Emergent Neural Computational Architectures Based on Neuroscience. LNCS (LNAI), vol. 2036, pp. 480–486. Springer, Heidelberg (2001)Google Scholar
  14. 14.
    Prat, F., Casacuberta, F., Castro, M.J.: Machine translation with grammar association: Combining neural networks and finite state models. In: Proceedings of the Second Workshop on Natural Language Processing and Neural Networks, pp. 53–60 (2001)Google Scholar
  15. 15.
    Sun, G.Z., Giles, C.L., Chen, H.H.: The Neural Network Pushdown Automaton: Architecture, Dynamics and Training. In: Giles, C.L., Gori, M. (eds.) IIASS-EMFCSC-School 1997. LNCS (LNAI), vol. 1387, pp. 296–345. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  16. 16.
    Cleeremans, A., Servan-Schreiber, D., McClelland, J.L.: Finite state automata and simple recurrent networks. Neural Computation 1(3), 372–381 (1989)CrossRefGoogle Scholar
  17. 17.
    Giles, C.L., Miller, C.B., Chen, D., Chen, H.H., Sun, G.Z., Lee, Y.C.: Learning and extracted finite state automata with second-order recurrent neural networks. Neural Computation 4(3), 393–405 (1992)CrossRefGoogle Scholar
  18. 18.
    Manolios, P., Fanelli, R.: First order recurrent neural networks and deterministic finite state automata. Neural Computation 6(6), 1154–1172 (1994)CrossRefGoogle Scholar
  19. 19.
    Gori, M., Maggini, M., Martinelli, E., Soda, G.: Inductive inference from noisy examples using the hybrid finite state filter. IEEE Transactions on Neural Networks 9(3), 571–575 (1998)CrossRefGoogle Scholar
  20. 20.
    Bensaali, F., Amira, A.: Accelerating colour space conversion on reconfigurable hardware. Image and Vision Computing 23, 935–942 (2005)CrossRefGoogle Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • José Mira
    • 1
  • Ana E. Delgado
    • 1
  • Antonio Fernández-Caballero
    • 2
  • María T. López
    • 2
  • Miguel A. Fernández
    • 2
  1. 1.Universidad Nacional de Educación a Distancia, E.T.S.I. Informática, 28040 - MadridSpain
  2. 2.Universidad de Castilla-La Mancha, Instituto de Investigación en Informática (I3A) and, Escuela Politécnica Superior de Albacete, 02071 - AlbaceteSpain

Personalised recommendations