Similarity-based image retrieval considering artifacts by self-organizing map with refractoriness

ABSTRACT

In this paper, we propose a similarity-based image retrieval considering artifacts by self-organizing map with refractoriness. In the self-organizing map with refractoriness, the plural neurons in the Map Layer corresponding to the input can fire sequentially because of the refractoriness. The proposed image retrieval system considering artifacts using the self-organizing map with refractoriness makes use of this property in order to retrieve plural similar images. In this image retrieval system, as the image feature, not only color information but also spectrum and keywords are employed. We carried out a series of computer experiments and confirmed that the effectiveness of the proposed system.

References

1. D. E. Rumelhart, J. L. McClelland and the PDP Research Group: Parallel Distributed Processing, -- Explorations in the Microstructure of Cognition, Vol.1 : Foundations, The MIT Press, 1986.
2. T. Kohonen: Self-Organizing Maps, Springer, 1994.
3. J. J. Hopfield : "Neural networks and physical systems with emergent collective computational abilities," Proceedings of the National Academy of Science USA, Vol.79, pp.2554-2558, 1982.
4. B. Kosko: "Bidirectional associative memory," IEEE Transactions on Systems, Man and Cybernetics, Vol.18, No.1, pp.49-60, 1988.
5. Y. Osana: "Improved chaotic associative memory using distributed patterns for image retrieval," Proceedings of IEEE International Joint Conference on Neural Networks, Portland, 2003.
6. S. Kosuge and Y. Osana: "Chaotic associative memory using distributed patterns for image retrieval by shape information," Proceedings of IEEE International Joint Conference on Neural Networks, Budapest, 2004.
7. S. Kosuge and Y. Osana: "Chaotic associative memory using internal patterns for image retrieval by color and shape information," Proceedings of IEEE International Joint Conference on Neural Networks, Montreal, 2005
8. J. T. Laaksonen, J. M. Koskela, S. P. Laakso and E. Oja: "PicSOM-- content-based image retrieval with self-organizing maps," Pattern Recognition Letters, Vol.21, No.13-14, pp.1199-1207, 2000.
9. K. Kuroda and M. Hagiwara: "An image retrieval system by impression words and specific object names -- IRIS --", Neurocomputing, Vol.43, pp.259-276, 2002.
10. T. Hayashi and M. Hagiwara: "Image query by impression words -- the IQI system," IEEE Transactions on Consumer Electronics, Vol.44, No.2, pp.347-352, 1998.
11. H. Mogami, M. Otake, N. Kouno and Y. Osana : "Self-organizing map with refractoriness and its application to image retrieval," Proceedings of IEEE International Joint Conference on Neural Networks, Vancouver, 2006.
12. K. Nagashima, M. Nakada and Y. Osana: "Similarity-based image retrieval by self-organizing map with refractoriness," Proceedings of IEEE International Joint Conference on Neural Networks, Orlando, 2007.
13. Y. Osana and M. Hagiwara: "Separation of superimposed pattern and many-to-many associations by chaotic neural networks," Proceedings of IEEE International Joint Conference on Neural Networks, Anchorage, Vol.1, pp.514-519, 1998.
14. J. T. Huang and M. Hagiwara: "A multi-winners self-organizing neural network," IEEE International Conference on System Man and Cybernetics, pp.2499-2504, 1997.
15. H. Tanimizu and Y. Osana: "Similarity-based image retrieval from plural key images by self-organizing map with refractoriness," Proceedings of IEEE and INNS International Joint Conference on Neural Networks, Hong Kong, 2008.