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.
Chapter PDF
Similar content being viewed by others
Keywords
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
Murase, H., Nayar, S.: Visual Learning and Recognition of 3D Objects from Appearance. International Journal of Computer Vision 14-1, 5–24 (1995)
Hassoun, M.: Fundamentals of Artificial Neural Networks. MIT Press, Cambridge (1995)
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)
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)
DeMers, D., Cottell, G.: Non-linear dimensionality reduction. Advances in Neural Information Processing Systems 5, 550–587 (1992)
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)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yokoi, T., Ohyama, W., Wakabayashi, T., Kimura, F. (2004). Eigenspace Method by Autoassociative Networks for Object Recognition. In: Fred, A., Caelli, T.M., Duin, R.P.W., Campilho, A.C., de Ridder, D. (eds) Structural, Syntactic, and Statistical Pattern Recognition. SSPR /SPR 2004. Lecture Notes in Computer Science, vol 3138. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-27868-9_9
Download citation
DOI: https://doi.org/10.1007/978-3-540-27868-9_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22570-6
Online ISBN: 978-3-540-27868-9
eBook Packages: Springer Book Archive
