Automatic recognition of bidimensional models learned by grammatical inference in outdoor scenes

  • Alberto Sanfeliu
  • Miguel Sainz
Learning Methodologies
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1121)


Automatic generation of models from a set of positive and negative samples and a-priori knowledge (if available) is a crucial issue for pattern recognition applications. Grammatical inference can play an important role in this issue since it is one of the methodologies that can be used to generate the set of model classes, where each class consists on the rules to generate the models. In this paper we present the recognition methodology to identify models in a outdoor scenes generated through a grammatical inference process. We will summarize how the set of model classes are generated and will explain the recognition process. An example of traffic sign identification will be shown.


  1. [1]
    R. Alquezar and A. Sanfeliu, “Augmented regular expressions: a formalism to describe, recognize and learn a class of contextsensitive languages”, Research Report LSI-95-17-R, Universität Politecnica de Cataluyna, Barcelona (1995).Google Scholar
  2. [2]
    R. Alquezar and A. Sanfeliu, “An algebraic framework to represent finite-state machines in single-layer recurrent neural networks”, Neural Computation, 7, Sept.(1995).Google Scholar
  3. [3]
    K.S. Fu, Syntactic Pattern Recognition and Applications, Prentice-Hall, New York, (1982).Google Scholar
  4. [4]
    H.Bunke and A. Sanfeliu, Syntatic and Structural Pattern Recognition: Theory and Applications, World Scientific, (1990).Google Scholar
  5. [5]
    V.I. Levensthein, “Binary codes capable of correcting deletions, insertions and reservals”, Sov. Phys. Dokl, 10 (8), 707–10, Feb (1966).Google Scholar
  6. [6]
    W. Lei and N.M. Nasrabadi, “Invariant object recognition on neural network of cascaded RCE nets”, Int. Journal of Pattern Recognition and Artificial Intelligence, Vol. 7, No.4, pp 815–829, (1993).Google Scholar
  7. [7]
    L. Miclet, “Grammatical inference,” in Syntatic and Structural Pattern Recognition: Theory and Applications, H.Bunke and A.Sanfeliu, Eds., World Scientific, 1990.Google Scholar
  8. [8]
    H. Murase and S.K. Nayar, “Learning object models from apearance”, Proc. of AAAI, Washington D.C., July 1993.Google Scholar
  9. [9]
    H. Murase and S.K. Nayar, “Visual learning and recognition of 3D objects from appearance”, International Journal of Computer Vision, Vol. 14, No. 1, pp 5–24, January, 1995.Google Scholar
  10. [10]
    D.E. Rumelhart, G.E. Hinton and R.J. Williams, “Learning internal representations by error propagation”, in D.E. Rumelhart & J.L. McClelland (eds.) Parallel Distributed Processing: Explorations in Microstructure of Cognition Volo 1: Foundations, MIT Press (1986).Google Scholar
  11. [11]
    A. Sanfeliu and R. Alquezar, “Active Grammatical Inference: a new learning methodology”, in Shape and Structure in Pattern Recognition, D. Dori and A. Bruckstein (eds.), World Scientific Pub., Singapore (1995).Google Scholar
  12. [12]
    A. Sanfeliu and M.Sainz, “Aprendizaje automatico de modelos en vision por computador”, Proceedings of the XVI Jornadas de Automatica, San Sebastian, 27–29 Sept, (1995).Google Scholar
  13. [13]
    M. Sainz and A. Sanfeliu, “A first approach to learn the model of traffic signs using connectionist and syntactic methods”, Proceedings of the VI Simposium de Reconocimiento de Formas y Analisis de Imagenes, Cordoba, 3–6 April (1995).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Alberto Sanfeliu
    • 1
  • Miguel Sainz
    • 2
  1. 1.Instituto de Robotica e Informatica IndustrialUniversidad Politécnica de Catalunya - CSICBarcelona
  2. 2.Instituto de CibernéticaUniversidad Politécnica de Catalunya - CSICBarcelona

Personalised recommendations