Advertisement

A Generic Model for Perception-Action Systems. Analysis of a Knowledge-Based Prototype

  • D. Hernández-Sosa
  • J. Lorenzo-Navarro
  • M. Hernández-Tejera
  • J. Cabrera-Gámez
  • A. Falcón-Martel
  • J. Méndez-Rodríguez
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1542)

Abstract

In this paper we propose a general layered model for the design of perception-action system. We discuss some desirable properties such a system must support to meet the severe constrains imposed by the expected behaviour of reactive systems. SVEX, a knowledge-based multilevel system, is used as a test prototype to implement and evaluate those considerations.

Additionally two aspects of the system are analyzed in detail in order to prove the benefits of the design criteria used in SVEX. These aspects refer to learning and distribution of computations. Finally, the results of some SVEX applications are shown.

Keywords

Execution Time Source Image Feature Subset Pixel Level Initial Partition 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aloimonos J., Weis I., “ActiveVision”, Int. Journal of Computer Vision, 2, (1988), 333–356.Google Scholar
  2. 2.
    Bajcsi R., “ActivePerception”, Proc. of the IEEE, 76, 8, (1988), 996–1005.Google Scholar
  3. 3.
    Blum A. L., Langley P., “Selection of relevant features and examples in machine learning”, Artificial Intelligence, 97:245–271, 1997.MATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Buchanan B., “Can Machine Learning Offer Anything to Expert Systems?”, Machine Learning, 4, pp. 251–254, 1989.Google Scholar
  5. 5.
    Cabrera J., “Sistema Basado en Conocimiento para Segmentación de Imágenes. Desarrollos y Aplicaciones”, Doctoral Dissertation, Universidad de Las Palmas de Gran Canaria, 1994.Google Scholar
  6. 6.
    Cabrera J., Hernández F.M., Falcón A., Méndez J., “Contributions to the symbolic processing of segments in computer vision”, Mathware and Soft Computing, III(3):403–413, 1996.Google Scholar
  7. 7.
    Cohn D., Atlas L., Ladner R., “Improving Generalization with Active Learning”, Machine Learning, 15, pp. 201–221, 1994.Google Scholar
  8. 8.
    Devijver P. A., Kittler J., Pattern Recognition: A Statistical Approach. Prentice-Hall, Englewood Cliffs, New Jersey, 1982.Google Scholar
  9. 9.
    Dubois D., Prade H., Yager R. R., Introduction in Readings in Fuzzy Sets for Intelligent Systems, Morgan Kaufmann Pub., (1993), 1–20.Google Scholar
  10. 10.
    Duda R., Hart P., Pattern Classification and Scene Analysis, Wiley, 1973.Google Scholar
  11. 11.
    Fukunaga K., Introduction to Statistical Pattern Recognition. Academic Press Inc., 2nd edition, 1990.Google Scholar
  12. 12.
    Geist A., PVM: Parallel Virtual Machine-A Users’ Guide and Tutorial for Net-worked Parallel Computing, The MIT Press, 1994.Google Scholar
  13. 13.
    Gordon J., Shortliffe E.H., “The Dempster-Shafer Theory of Evidence”, in Rule-Based Expert Systems, Buchanan and Shortliffe (Eds.), (1984), 272–292.Google Scholar
  14. 14.
    Koller D., Sahami M., “Toward optimal feature selection”, Proc. of the 13th Int. Conf. on Machine Learning, pages 284–292. Morgan Kaufmann, 1996.Google Scholar
  15. 15.
    Krisnapuram R., Keller J.M., “Fuzzy Set Theoretic Approach to Computer Vision: An Overview”, in Fuzzy Logic Technology and Applications, IEEE Tech. Activities Board, (1994), 25–32.Google Scholar
  16. 16.
    Hernández D., Cabrera J., “Distribution of Image Processing Application on a Heterogeneous Workstation Network. Modeling, Load-balancing and Experimental Results”, SPIE-97 Parallel on Distributed Methods for Image Processing, vol. 3166, pp. 170–179, July 1997, San Diego.Google Scholar
  17. 17.
    Huntsberger T.L., Rangarajan C., Jayaramamurthy S.N., “Representation of Uncertainty in Computer Vision using Fuzzy Sets”, IEEE Trans. Comput., 35, 2, (1986), 145–156.CrossRefGoogle Scholar
  18. 18.
    Lee. S., Kil R. M., “Multilayer Feedforward Potential Function Network”, Proc. of 2nd. Int. Conf. on Neural Networks, vol I, pp. 161–171, 1988.Google Scholar
  19. 19.
    Lorenzo J., Hernández M., Méndez J., “An information theory-based measure to assess feature subsets”, Preprints of the VII National Symposium on Pattern Recognition and Image Analysis (AERFAI’97), volume 2, pages 38–39, 1997.Google Scholar
  20. 20.
    Lorenzo J., Hernández M., J. Méndez. “A measure based on information theory for attribute selection”, (IBERAMIA-98) 6th Ibero-American Conference on Artificial Intelligence, Lisbon, Portugal, Lectures Notes in Artificial Intelligence, Springer Verlag, October 1998.Google Scholar
  21. 21.
    Méndez J., Falcón A., Hernández F.M., Cabrera J., “A Development Tool for Computer Vision Systems at Pixel Level”, Cybernetics & Systems, 25, 2, (1994), 289–316.CrossRefGoogle Scholar
  22. 22.
    Munro D., “Performance of Multiprocessor Communications Networks”, Doctoral Dissertation, Dep. of Electronics, University of York, 1994.Google Scholar
  23. 23.
    Niemann H., Brünig H., Salzbrunn R., Schröder S., “A Knowledge-Based Vision System for Industrial Applications”, Machine Vision and Applications, 3, (1990), 201–229.CrossRefGoogle Scholar
  24. 24.
    Pennington R., “Distributed and Heterogeneous Computing”, Cluster Computing Lecture Series, Pittsburg Supercomputing Center 1995.Google Scholar
  25. 25.
    Poggio T., Girosi F., “Networks for approximation and learning”, Proceedings of the IEEE, 78:1481–1487, 1990.CrossRefGoogle Scholar
  26. 26.
    Quinlan J.R., “Induction of decision trees”, Machine Learning, 1:81–106, 1986.Google Scholar
  27. 27.
    Renals S., Rohwer R., “Phoneme Classification Experiments using Radial Basis Functions”, Proc. Int. Conf. on Neural NetworksI, pp. 416–467, 1989.Google Scholar
  28. 28.
    Rosenblatt F., “On the Convergence of Reinforcement Procedures in Simple Perceptrons”, Cornell Aeronautical Report VG-1196-G-4, Buffalo, NY, 1960.Google Scholar
  29. 29.
    Risemann E.M., Hanson A.R., “A Methodology for the Development of General Knowledge-Based Vision Systems”, in Vision, Brain and Cooperative Computation, MIT Press, Cambridge Mass., (1987), 285–328.Google Scholar
  30. 30.
    Rumelhart D. E., Hinton G. E., Willians R. J., “Learning Representations by Back-Propagating Errors”, Nature, 323, pp. 533–536, 1986.CrossRefGoogle Scholar
  31. 31.
    Vincent L., Soille P., “Watersheds in Digital Spaces: An efficient algorithm based on immersion simulations”. IEEE Trans. on Pattern Anal. and Mach. Intell., Vol 13, n 6, pp. 583–598, 1991.CrossRefGoogle Scholar
  32. 32.
    Wilson R., Spann M., Image Segmentation and Uncertainty, Research Studies Press Ltd., 1988.Google Scholar
  33. 33.
    Zadeh L.A., “PRUF-A meaning representation language for natural languages”, in Fuzzy Reasoning and its Applications, Academic Press, London, (1981), 1–39.Google Scholar
  34. 34.
    Zadeh L.A., “Commonsense Knowledge Representation based on Fuzzy Logic”, IEEE Computer, 16, 10, (1983), 61–65.Google Scholar
  35. 35.
    Zhang B., “Accelerated Learning by Active Example Selection”, International Journal of Neural Networks, vol. 5(1), pp. 67–75, 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • D. Hernández-Sosa
    • 1
  • J. Lorenzo-Navarro
    • 1
  • M. Hernández-Tejera
    • 1
  • J. Cabrera-Gámez
    • 1
  • A. Falcón-Martel
    • 1
  • J. Méndez-Rodríguez
    • 1
  1. 1.Grupo de Inteligencia Artificial y Sistemas Dpto. Informática y Sistemas Campus de TafiraUniversidad de Las Palmas de Gran CanariaLas Palmas de Gran CanariaSpain

Personalised recommendations