Advertisement

Pattern recognition using neural network based on multi-valued neurons

  • Igor N. Aizenberg
  • Naum N. Aizenberg
Images
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1607)

Abstract

Multi-valued neurons are the neural processing elements with complex-valued weights, huge functionality (it is possible to implement on the single neuron arbitrary mapping described by partial defined multiple-valued function), quickly converged learning algorithms. Such features of the multi-valued neurons may be used for solution of the different kinds of problems.

Neural network with multi-valued neurons for image recognition will be considered in the paper. Such a network analyzes the spectral coefficients corresponding to low frequencies. Simulation results are presented on the example of face recognition.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    N.N.Aizenberg, Yu.L.Ivaskiv Multiple-Valued Threshold Logic. Kiev: Naukova Dumka, 1977 (in Russian)Google Scholar
  2. 2.
    N.N.Aizenberg, I.N.Aizenberg “CNN based on multi-valued neuron as a model of associative memory for gray-scale images”, Proc. of the 2-d IEEE International Workshop on Cellular Neural Networks and their Applications, Munich, 1992, pp. 36–41.Google Scholar
  3. 3.
    N.N.Aizenberg, I.N.Aizenberg, G.A.Krivosheev “Multi-Valued Neurons: Learning, Networks, Application to Image Recognition and Extrapolation of Temporal Series”, Lecture Notes in Computer Science, Vol.930, (J.Mira, F.Sandoval—Eds.), Springer-Verlag, 1995, pp.389–395.Google Scholar
  4. 4.
    N.N.Aizenberg, I.N.Aizenberg, G.A.Krivosheev “Multi-Valued Neurons: Mathematical model, Networks, Application to Pattern Recognition”, Proc. of the 13 Int.Conf. on Pattern Recognition, Vienna, August 25–30, 1996, Track D, IEEE Computer Soc. Press, pp. 185–189, 1996.Google Scholar
  5. 5.
    I.N.Aizenberg., N.N.Aizenberg “Universal binary and multi-valued neurons paradigm: conception, learning, applications”, Lecture Notes in Computer Science, Vol. 1240 (J.Mira, R.Moreno-Diaz, J.Cabestany—Eds.), Springer-Verlag, 1997, pp. 463–472.Google Scholar
  6. 6.
    I.N.Aizenberg, N.N.Aizenberg “Application of the neural networks based on multi-valued neurons in image processing and recognition”, SPIE Proceedings, Vol. 3307, 1998, pp. 88–97.Google Scholar
  7. 7.
    S.Jankowski, A.Lozowski, M.Zurada “Complex-Valued Multistate Neural Associative Memory”, IEEE Trans. on Neural Networks, Vol. 7, pp. 1491–1496, 1996.CrossRefGoogle Scholar
  8. 8.
    N.Petkov, P.Kruizinga, T.Lourens “Motivated Approach to Face Recognition”, Lecture Notes in Computer Science, Vol. 686, (J.Mira, F.Sandoval—Eds.), Springer, pp.68–77, 1993.Google Scholar
  9. 9.
    S.Lawrence, C. Lee Giles, Ah Chung Tsoi and A.D.Back “Face Rocognition: A Convolutional Neural-Network Approach”, IEEE Trans. on Neural Networks, Vol. 8, pp. 98–113, 1997.CrossRefGoogle Scholar
  10. 10.
    R.Foltyniewicz “Automatic Face Recognition via Wavelets and Mathematical Morphology”, Proc. of the 13 Int.Conf. on Pattern Recognition, Vienna, August 25–30, 1996, Track B, IEEE Computer Soc. Press, pp. 13–17, 1996.Google Scholar
  11. 11.
    N.Ahmed, K.R.Rao “Orthogonal Transforms for Digital Signal Processing”, Springer, 1975.Google Scholar
  12. 12.
    A.V.Oppenheim and S.J.Lim “The importance of phase in signals”, Proc. IEEE, Vol. 69, pp. 529–541, 1981.CrossRefGoogle Scholar
  13. 13.
    M.Turk and A.Petland “Eigenfaces for Recognition”, Journal of Cognitive Neuroscience, Vol. 3, 1991.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Igor N. Aizenberg
    • 1
    • 2
    • 3
  • Naum N. Aizenberg
    • 1
    • 2
    • 3
  1. 1.Department of CyberneticsUniversity of Uzhgorod(Ukraine)
  2. 2.Scientific advisors to the company Neural Networks Technologies Ltd.(Israel)
  3. 3.UzhgorodUkraine

Personalised recommendations