Advertisement

Eigenspace Method by Autoassociative Networks for Object Recognition

  • Takamasa Yokoi
  • Wataru Ohyama
  • Tetsushi Wakabayashi
  • Fumitaka Kimura
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3138)

Abstract

This paper studies on a new eignespace method which employs autoassociative networks for object recognition. Five layered autoassociative network is available to obtain a manifold on the minimum square error hypersurface which approximates a distribution of learning sample. Recognition experiments were performed to show that the manifold of rotating object is obtained by learning and the objects, such as a mouse and a stapler, are correctly recognized by the autoassociative networks. It is also shown that the accuracy of approximating closed manifold and the accuracy of recognition are improved by emploing multiple autoassociative networks each of which is trained by a partition of the learning sample.The property and the advantage of the five layered autoassociative network are demonstrated by a comparative study with the nearest neighbor method and the eigenspace method.

Keywords

Object Recognition Input Pattern Closed Manifold Neighbor Method Learning Sample 
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.

References

  1. 1.
    Murase, H., Nayar, S.: Visual Learning and Recognition of 3D Objects from Appearance. International Journal of Computer Vision 14-1, 5–24 (1995)CrossRefGoogle Scholar
  2. 2.
    Hassoun, M.: Fundamentals of Artificial Neural Networks. MIT Press, Cambridge (1995)zbMATHGoogle Scholar
  3. 3.
    Cottrell, G., Munro, P., Zipser, D.: Image compression by back-propagation: An example of extensional programing. Models of Cognition: A Review of Cognitive Science 1, 208–240 (1989)Google Scholar
  4. 4.
    Cottrell, G., Munro, P., Zipser, D.: Learning internal representations from gray-scale images: An example of extensional programing. In: Ninth Annual Conference of the Cognitive Science Society, pp. 462–473 (1987)Google Scholar
  5. 5.
    DeMers, D., Cottell, G.: Non-linear dimensionality reduction. Advances in Neural Information Processing Systems 5, 550–587 (1992)Google Scholar
  6. 6.
    Kimura, F., Inoue, S., Wakabayashi, T., Tsuruoka, S., Miyake, Y.: Handwritten Numeral Recognition using Autoassociative Neural Networks. In: Proc. 14th International Conference on Pattern Recognition, vol. 1, pp. 166–171 (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Takamasa Yokoi
    • 1
  • Wataru Ohyama
    • 1
  • Tetsushi Wakabayashi
    • 1
  • Fumitaka Kimura
    • 1
  1. 1.Faculty of EngineeringMie UniversityTsuJapan

Personalised recommendations