Fuzzy Gated Neural Networks in Pattern Recognition

  • Zhi-Qiang Liu
  • Venketachalam Chandrasekaran
Part of the Computer Science Workbench book series (WORKBENCH)


Pattern recognition is important in virtually all intelligent systems, in particular, in human centered systems, one major development is the intelligent servant modules (ISMs) that can react and interact with humans. To effectively respond to human’s request ISMs must be able to recognize gestures, voice patterns, facial features and so on. Making systems to achieve such capabilities is a challenging task due to uncertainties which arise from incomplete or imprecise knowledge of what is being perceived together with data corruption due to inherent noise in sensors. Furthermore, the recognition system must be able to generalize from the “seen” samples to “unseen” patterns that are from the same population. In addition, the system will have to reject “unknown” patterns or to update the knowledge base, in some instances, to alert the user.


Input Pattern Texture Image Range Image Class Node Winning Node 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    V. Chandrasekaran, M. Palaniswami, and T.M. Caelli, “Spatiotemporal feature map using gated neuronal architecture,” IEEE Transactions on Neural Networks, Vol.6, No.5, pp.1119–1131, September 1995.CrossRefGoogle Scholar
  2. [2]
    T. Kohonen, “The self-organizing map,” Proceedings of IEEE, Vol.78, No.9, pp.1464–1480, September 1990.CrossRefGoogle Scholar
  3. [3]
    V. Chandrasekaran, M. Palaniswami, and T.M. Caelli, “Pattern recognition by topology free spatio-temporal feature map,” Proceedings of the International Conference on Systems, Man, and Cybernetics, Vol.2, pp.1136–1149, October 1995.Google Scholar
  4. [4]
    V. Chandrasekaran, Z.Q. Liu, and M. Palaniswami, “Fuzzy gated neuronal architecture for pattern recognition,” Proceedings of the International Conference on Neural Networks, Vol.4, pp.1622–1627, November 1995.Google Scholar
  5. [5]
    C. Koch and I. Segev, (Eds.), Methods in Neuronal Modeling: From Synapses to Networks, MIT Press, Cambridge, MA, 1989.Google Scholar
  6. [6]
    W.S. McCulloch and W.H. Pitts, “A logical calculus of the ideas imminent in nervous activity,” Bulletin Math. Biophy., No.5, pp.115–133, 1943.MathSciNetMATHCrossRefGoogle Scholar
  7. [7]
    F. Rosenblatt, “The perceptron: A probabilistic model for information storage and organization in the brain,” Psychol. Rev., Vol.65, pp.386–408, 1958.MathSciNetCrossRefGoogle Scholar
  8. [8]
    B. Widrow, “Adaline and madaline-1963,” IEEE First International Conference on Neural Networks, 1987, Vol.1, pp.143–157.Google Scholar
  9. [9]
    M.N. Oguztoreli, G.M. Steil, and T.M. Caelli, “Underlying neural computations for some visual phenomena,” Biological Cybernetics, No.60, pp.89–106, 1988.Google Scholar
  10. [10]
    J.M. Zurada, Introduction to Artificial Neural Systems, West Publisching, 1992.Google Scholar
  11. [11]
    S.C. Lee and E.T. Lee, “Fuzzy neural networks,” Mathematical Biosciences, Vol.23, pp.151–177, 1975.MathSciNetMATHCrossRefGoogle Scholar
  12. [12]
    Y.C. Lee, G. Doolen, H.H. Chen, G.Z. Sun, T. Maxwell, Y. Lee, and C.L. Giles, “Machine learning using higher order correlation network,” Physica D, pp.276–306, 1986.Google Scholar
  13. [13]
    V. Chandrasekaran, M. Palaniswami, and T.M. Caelli, “An extended self-organizing map with gated neurons,” Proceedings of the IEEE International Conference on Neural Networks, Vol.III, pp.1474–1479, March 1993.Google Scholar
  14. [14]
    V. Chandrasekaran, M. Palaniswami, and T.M. Caelli, “Performance evaluation of spatia-temporal feature maps with gated neuronal architecture,” Proceedings of the World Congress on Neural Networks, Vol.IV pp.112–118, July 1993.Google Scholar
  15. [15]
    H.K. Kwan and Y.L. Cai, “A fuzzy neural network and its application to pattern recognition,” IEEE Transactions on Fuzzy Systems, Vol.2, No.3, pp.185–193, August 1994.CrossRefGoogle Scholar
  16. [16]
    V. Chandrasekaran, Gated Neural Networks for Three Dimensional Object Recognition Systems, PhD thesis, The University of Melbourne, Parkville, Vic-3052, Australia, 1995.Google Scholar
  17. [17]
    K. Laws, Textured Image Segmentation, PhD thesis, University of Southern California, USA, 1980.Google Scholar
  18. [18]
    N. Yokoya and M.D. Levine, “Range image segmentation based on differential geometry: A hybrid approach,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.11, No.6, pp.643–649, June 1989.CrossRefGoogle Scholar
  19. [19]
    V. Chandrasekaran, M. Palaniswami, and T.M. Caeili, “Range image segmentation by dynamic neural network architecture,” Pattern Recognition, Vol.29, No.2, pp.315–329, 1996.CrossRefGoogle Scholar
  20. [20]
    V. Chandrasekaran and Z.Q. Liu, “Robust face image retrieval by fuzzy gated neuronal architecture,” Proceedings of the International Conference on Neural Information Processing, Vol.1, pp.432–437,September 1996.Google Scholar
  21. [21]
    H. Sawai P. Haffner, A. Waibel and K. Shikano, “Fast backpropagation learning methods for large phonemic neural networks,” Proceedings of the European Conference on Speech Commur,ication and Technology, Paris, pp.553–556, 1989.Google Scholar
  22. [22]
    V. Chandrasekaran, Z.Q. Liu, and T.M. Caeili, “On the use of fuzzy gated neural networks for pattern recognition in a noisy environment,” Proceedings of the International Conference on Control, Automation, Robotics and Vision, Vol.1, pp.645–649, December 1995.Google Scholar

Copyright information

© Springer-Verlag Tokyo 2000

Authors and Affiliations

  • Zhi-Qiang Liu
  • Venketachalam Chandrasekaran

There are no affiliations available

Personalised recommendations