Pattern recognition system with top-down process of mental rotation
A new model which can recognize rotated, distorted, scaled, shifted and noised patterns is proposed. The model is constructed based on psychological experiments in a mental rotation. The model has two types of processes: (i) one is a bottom-up process in which pattern recognition is realized by means of a rotation-invariant neocognitron and a standard neocognitron and (ii) the other is a top-down process in which a mental rotation is executed by means of a model of associative recall in visual pattern recognition. In computer simulations, it is shown that the model can recognize rotated patterns without training those patterns.
Keywordsrotation-invariant neocognitron rotated pattern mental rotation top-down process pattern recognition
Unable to display preview. Download preview PDF.
- 2.M. B. Reid, L. Spirkovska, and E. Ochoa, “Rapid training of higher order neural networks for invariant pattern recognition,” Proc. Int. Joint Conf. Neural Networks, Vol. 1, pp. 689–692, 1989.Google Scholar
- 4.S. Satoh, J. Kuroiwa, H. Aso and S. Miyake, “Recognition of rotated patterns using neocognitron,” Proc. Int. Conf. Neural Information Processing, Vol. 1, pp. 112–116, 1997. http://www.aso.ecei.tohoku.ac.jptshun/postscript/iconip97.ps.gzGoogle Scholar
- 5.S. Satoh, J. Kuroiwa, H. Aso and S. Miyake, “A rotation-invariant Neocognitron (in Japanese),” IEICE Trans., Vol.J81-DII, 1998.Google Scholar
- 9.K. Fukushima and N. Wake, “An improved learning algorithm for the neocognitron,” Proc. of the Int. Conf. on Artificial Neural Networks, pp. 4–7 (1992).Google Scholar
- 10.S. Satoh, J. Kuroiwa, H. Aso and S. Miyake, “Recognition of hand-written patterns by rotation-invariant neocognitron,” Proc. Int. Conf. Neural Information Processing, Vol. 1, pp. 295–299, 1998. http://www.aso.ecei.tohoku.ac.jpshun/postscript/iconip98.ps.gzurlGoogle Scholar