Abstract
This paper describes a neural network architecture that has been developed to perform deformation tolerant object recognition from grey-scale images. It uses a form of deformable template matching, generating new templates in a self-organising manner. The results demonstrate the network's ability to build classes when no suitable classes are available. The amount of deformation allowed within a class can be controlled to allow the network to be applied to a wide range of applications. Results are presented for a set of generated images which allow the effects of the selection of the major network parameters to be shown.
Similar content being viewed by others
References
A.K. Jain, Y. Zhong and S. Lakshmanan. “Objectmatching using deformable templates”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 18, No. 3, pp. 267–278, March 1996.
K. Fukushima and S. Miyake, “Neocognitron: a newalgorithm for pattern recognition tolerant of deformations and shifts in position”, Pattern Recognition, Vol. 15, No. 6, pp. 455–469, 1987.
S. Gazula and M.R. Kabuka, “Design of supervisedclassifiers using boolean neural networks”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 17, No. 12, pp. 1239–1246, December 1995.
B. Hussain and M.R. Kabuka, “A novelfeature recognition neural network and its application to character recognition”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 16, No. 1, pp. 98–106, 1994.
G.A. Carpenter and S. Grossberg, “The ART of adaptive pattern recognition by a self-organizing neural network”, Computer, Vol. 21, pp. 77–88, 1988.
D.S. Banarse and A.W.G. Duller, “Deformationinvariant pattern classification for recognising hand gestures”, in Proceedings of the 1996 IEEE International Conference on Neural Networks, pp. 1812–1816, IEEE Press, 1996.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Banarse, D., Duller, A. Vision Experiments with Neural Deformable Template Matching. Neural Processing Letters 5, 41–49 (1997). https://doi.org/10.1023/A:1009661908220
Issue Date:
DOI: https://doi.org/10.1023/A:1009661908220