Abstract
This paper proposes a neural network model that has an ability to restore the missing portions of partly occluded patterns. It is a multi-layered hierarchical neural network, in which visual information is processed by interaction of bottom-up and top-down signals. Occluded parts of a pattern are reconstructed mainly by feedback signals from the highest stage of the network, while the unoccluded parts are reproduced mainly by signals from lower stages. The model does not use a simple template matching method. It can restore even deformed versions of learned patterns.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
K. Fukushima: “Recognition of partly occluded patterns: a neural network model”, Biological Cybernetics, 84[4], pp. 251–259 (2001).
K. Fukushima: “Neocognitron: a hierarchical neural network capable of visual pattern recognition”, Neural Networks, 1[2], pp. 119–130 (1988).
K. Fukushima: “Neural network model for selective attention in visual pattern recognition and associative recall”, Applied Optics, 26[23], pp. 4985–4992 (Dec. 1987).
K. Fukushima: “Use of top-down signals for restoring partly occluded patterns”, IJCNN’02, Honolulu, Hawaii, USA, pp. 17–22 (May 2002).
K. Fukushima: “Neocognitron for handwritten digit recognition”, Neurocomputing, 51, pp. 161–180 (April 2003).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fukushima, K. (2003). Restoring Partly Occluded Patterns: A Neural Network Model with Backward Paths. In: Kaynak, O., Alpaydin, E., Oja, E., Xu, L. (eds) Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003. ICANN ICONIP 2003 2003. Lecture Notes in Computer Science, vol 2714. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44989-2_47
Download citation
DOI: https://doi.org/10.1007/3-540-44989-2_47
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40408-8
Online ISBN: 978-3-540-44989-8
eBook Packages: Springer Book Archive