Abstract
This paper describes a novel massively parallel connectionist architecture for image retrieval. The proposed search engine of the system consists of associative memory nodes connected by information channels which convey symbolic messages. Symbolic information stored inside the system is obtained using gestalt feature extraction methods which capture multiple representations of images. In this paper, we summarise our feature extraction method and then we describe the connection schemata of the system, training process as well as how such a system can be utilised to capture perceptual similarity of trademark images. Finally, we present results obtained during evaluation of the system.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
[San96] Santini.S and Jain.R: Similarity matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996.
[Mic97] Turner.M and Austin.J: Matching Performance of Binary Correlation Matrix Memories. Neural Networks, 1997.
[Jim95] Austin.J, Kennedy.J, Lees.K: The Advanced Uncertain Reasoning Architecture. In Proc. Artificial Neural Networks and Expert Systems Conference, 1995.
[Bid87] Biederman. I: Recognition by components—A theory of human image understanding. Psychological Review, vol 94, no 2, pages 115–147, 1987.
[Wus91] Wuescher. D and Boyer. K.L: Robust contour decomposition using a constant curvature criterion. IEEE PAMI, vol 13, pages 41–51, 1991.
[Low87] Lowe. D.G.: Three-dimensional object recognition from single two-dimensional images. Artificial Intelligence, vol 31, pages 355–395, 1987.
[Sar94] Sarkar.S and Boyer.K: Computing perceptual organization in computer vision. World Scientific Publishers, 1994.
[Suj98] Alwis.S and Austin.J: A novel architecture for trademark image retrieval systems. In Proceedings of the challenge of image retrieval, 1998.
[Fl94] Filer. R: Symbolic reasoning in an associative neural network. In MSc Thesis, University of York, UK, 1994.
[Jim97] Turner.M and Austin.J: A neural relaxation technique for chemical graph matching. In Proceedings of the Fifth International Conference on Artificial Neural Networks, Cambridge, UK, Editor. M Niranjan, IEE Publishers, July 1997.
[Van77] Van Rijsbergen. R.J: Information retrieval. Butterwoths, London, 1979.
[Suj99] Alwis.S and Austin.J: Trademark image retrieval using multiple features. To be published in Proceedings of the challenge of image retrieval, February 1999.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Alwis, S., Austin, J. (1999). A neural network architecture for trademark image retrieval. In: Mira, J., Sánchez-Andrés, J.V. (eds) Engineering Applications of Bio-Inspired Artificial Neural Networks. IWANN 1999. Lecture Notes in Computer Science, vol 1607. Springer, Berlin, Heidelberg . https://doi.org/10.1007/BFb0100503
Download citation
DOI: https://doi.org/10.1007/BFb0100503
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66068-2
Online ISBN: 978-3-540-48772-2
eBook Packages: Springer Book Archive