Abstract
The “neocognitron” was first proposed as a hierarchical neural network model for the mechanism of visual pattern recognition in the brain. It is capable of deformation-resistant pattern recognition. Various experiments have demonstrated its powerful ability to recognize visual patterns. For example, the authors have designed several systems which recognize hand-written characters, such as, a system recognizing ten numerals, and a system recognizing alphanumeric characters. This paper also discusses recent advances in the neocognitron. The network has been modified to have an architecture closer to that of the real biological brain, and a new learning algorithm has been introduced.
The “selective attention model” has not only forward but also backward connections in a hierarchical network. It has the ability to segment patterns, as well as the function of recognizing them. The principles of this selective attention model can be extended to be used for several applications: for example, the recognition and segmentation of connected characters in cursive handwriting of English words, and the recognition of Chinese characters.
Preview
Unable to display preview. Download preview PDF.
References
K. Fukushima: “Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position”. Biological Cybernetics 36[4], 193–202 (April 1980).
K. Fukushima, S. Miyake: “Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position”. Pattern Recognition 15[6], 455–469 (1982).
K. Fukushima: “Neocognitron: A hierarchical neural network capable of visual pattern recognition”. Neural Networks 1[2], 119–130 (1988).
K. Fukushima, N. Wake: “Handwritten alphanumeric character recognition by the neocognitron”. IEEE Trans. on Neural Networks 2[3], 355–365 (May 1991).
N. Wake, K. Fukushima: “Improved learning method for the neocognitron”, (in Japanese). IEICE Transactions, D-II (Inst. Electronics, Information, Commun. Engineers, Japan) J75-D-II, to appear (1992).
K. Fukushima, N. Wake: “Improved neocognitron with bend-detecting cells”. IJCNN'92-Baltimore, Baltimore, MD, U.S.A., Vol. IV, 190–195 (June 1992).
K. Fukushima, N. Wake: “An improved learning algorithm for the neocognitron”. In I. Aleksander, J. Taylor (eds.): Artificial Neural Networks, 2, Amsterdam: North-Holland, 1992, pp. 497–505.
K. Fukushima: “A feature extractor for curvilinear patterns: A design suggested by the mammalian visual system”. Kybernetik 7[4], 153–160 (Sept. 1970).
K. Fukushima: “A feature extractor for a pattern recognizer — A design suggested by the visual system”, (in Japanese). NHK Technical Journal 23[5], 351–367 (Sept. 1971).
K. Fukushima: “A neural network model for selective attention in visual pattern recognition”. Biological Cybernetics 55[1], 5–15 (Oct. 1986).
K. Fukushima: “A neural network model for selective attention in visual pattern recognition and associative recall”. Applied Optics 26[23], 4985–4992 (Dec. 1987).
K. Fukushima: “A neural network for visual pattern recognition”. Computer (IEEE Computer Society) 21[3], 65–75 (March 1988).
K. Fukushima: “Neural network models for visual pattern recognition”. In R. Eckmiller, G. Hartmann, G. Hauske (eds.): Parallel Processing in Neural Systems and Computers, Amsterdam: North-Holland, 1990, pp. 351–356.
K. Fukushima, T. Imagawa, E. Ashida: “Character recognition with selective attention”. IJCNN-91-Seattle, Seattle, WA, U.S.A., pp. I-593–I-598 (1991).
T. Imagawa, K. Fukushima: “Character recognition in cursive handwriting with the mechanism of selective attention”, (in Japanese). Trans. IEICE J74-D-II[12] 1768–1775 (Dec. 1991).
K. Fukushima, T. Imagawa: “Recognition and segmentation of connected characters with selective attention”. Neural Networks 5, in print (1992).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fukushima, K. (1992). Visual pattern recognition with neural networks. In: Nakamura, A., Nivat, M., Saoudi, A., Wang, P.S.P., Inoue, K. (eds) Parallel Image Analysis. ICPIA 1992. Lecture Notes in Computer Science, vol 654. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56346-6_26
Download citation
DOI: https://doi.org/10.1007/3-540-56346-6_26
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56346-4
Online ISBN: 978-3-540-47538-5
eBook Packages: Springer Book Archive