Abstract
A rotation-invariant neocognitron was proposed by authors for recognition of rotated patterns. In this paper, we propose a new network in order to reduce the number of cells for the same purpose. The new network is based on the rotation-invariant neocognitron in its structure and based on an idea of hypothesis and its verification in its process. In the proposed model the following two processes are executed: 1) making a hypothesis of an angular shift of an input supported by an associative recall network and 2) verification of the hypothesis realized by mental rotation of the input. Computer simulations show that 1) the new network needs less cells than the original rotation-invariant neocognitron and 2) the difference of recognition rates between the proposed network and the original network is very little.
This work was supported by JSPS Research Fellowships for Young Scientists.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
M. Fukumi, S. Omatsu and Y. Nishikawa: “Rotation-invariant neural pattern recognition system estimating a rotation angle,” IEEE Trans. Neural Network, 8, 3, 569–581, 1997.
B. Widrow, R. G. Winter and R. A. Baxter, “Layered neural nets for pattern recognition,” IEEE Trans. Acoust, Speech, Signal Processing, ASSP-36, 1109–1118, 1988.
S. Kageyu, N. Ohnishi, and N. Sugie, “Augmented multilayer perceptron for rotation-and-scale invariant hand written numeral recognition,” Proc. Int. J. Conf. Neural Networks, 1, 54–59, 1991.
M. B. Reid, L. Spirkovska and E. Ochoa, “Rapid training of higher-oder neural networks for invariant pattern recognition,” Proc. Int. J. Conf. Neural Networks, 1, 689–692, 1989.
K. Fukushima: “Neocognitron: A hierarchical neural network capable of visual pattern recognition,” Neural Networks, 6, 119–130, 1988.
S. Satoh, J. Kuroiwa, H. Aso and S. Miyake, “A rotation-invariant neocognitron,” Systems and computers in Japan, 30, 4, 31–40, 1999.
S. Satoh, J. Kuroiwa, H. Aso and S. Miyake: “Recognition of rotated patterns using neocognitron,” Proc. of the fourth inter. conf. neural information processing, 1, 112–116, 1997.
J. Basak and S. K. Pal: “Psycop —a psychologically motivated connectionist system for object perception,” IEEE Trans. Neural Networks, 6, 6, 1337–1354, 1995.
S. Satoh, H. Aso, S. Miyake and J. Kuroiwa, “Pattern recognition system with topdown process of mental rotation,” Proc. of the fifth Intern. Work-Conf. Artificial and Natural Neural networks, 1, 816–825, 1999.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Satoh, S., Miyake, S., Aso, H. (2001). Neocognitron-Type Network for Recognizing Rotated and Shifted Patterns with Reduction of Resources. In: Mira, J., Prieto, A. (eds) Connectionist Models of Neurons, Learning Processes, and Artificial Intelligence. IWANN 2001. Lecture Notes in Computer Science, vol 2084. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45720-8_25
Download citation
DOI: https://doi.org/10.1007/3-540-45720-8_25
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42235-8
Online ISBN: 978-3-540-45720-6
eBook Packages: Springer Book Archive