Abstract
Even the identical image is perceived differently by human beings depending on the shape of occluding objects. This paper proposes a neural network model that has an ability to recognize and restore partly occluded patterns in a similar way as our perception. 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 restored 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 recognize and restore even deformed versions of learned patterns.
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
Fukushima, K.: Recognition of partly occluded patterns: a neural network model. Biological Cybernetics 84(4), 251–259 (2001)
Fukushima, K.: Neural network model for selective attention in visual pattern recognition andasso ciative recall. Applied Optics 26(3), 4985–4992 (1987)
Fukushima, K.: Use of top-down signals for restoring partly occluded patterns. In: IJCNN 2002, Honolulu, Hawaii, USA, May 2002, pp. 17–22 (2002)
Fukushima, K.: Restoring Partly Occluded Patterns: A Neural Network Model with Backward Paths. In: Kaynak, O., Alpaydın, E., Oja, E., Xu, L. (eds.) ICANN 2003 and ICONIP 2003. LNCS, vol. 2714. Springer, Heidelberg (2003) (in press)
Fukushima, K.: Neocognitron: a hierarchical neural network capable of visual pattern recognition. Neural Networks 1(2), 119–130 (1988)
Fukushima, K.: Neocognitron for handwritten digit recognition. Neurocomputing 51, 161–180 (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). Neural Network Model Restoring Partly Occluded Patterns. In: Palade, V., Howlett, R.J., Jain, L. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2003. Lecture Notes in Computer Science(), vol 2774. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45226-3_19
Download citation
DOI: https://doi.org/10.1007/978-3-540-45226-3_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40804-8
Online ISBN: 978-3-540-45226-3
eBook Packages: Springer Book Archive