Scale Summarized and Focused Browsing of Primitive Visual Content
A study of local scale in images demonstrates that image features reside in different scales. Based on this observation a framework for the classification of features with respect to scale is proposed, linearly combining the visual impression of features at different scales. The proposed framework and a derived methodology are applied to typical feature extraction tasks, and in the generic case of estimating multiple scale feature distributions, as a tool for the identification of images of similar visual content. A possible formulation of queries for retrieving images by primitive visual content, taking scale into account, is also discussed.
KeywordsImage Retrieval Feature Detection Scale Space Coarse Scale Identi Cation
Unable to display preview. Download preview PDF.
- 3.J. Puzicha et al. Empirical evaluation of dissimilarity measures for color and texture. In Proceedings of the International Conference on Computer Vision, 1999.Google Scholar
- 6.T. Lindeberg. Scale-Space Theory in Computer Vision. The Kluwer International Series in Engineering and Computer Science. Kluwer Academic Publishers, Boston, USA, 1994.Google Scholar
- 7.De Valois R. and De Valois K. Spatial Vision. Oxford Science Publications, Oxford, 1988.Google Scholar
- 10.S. Sarkar and K.L. Boyer. Perceptual organization in computer vision: A review and a proposal for a classificatory structure. SMC, 23:382–399, 1993.Google Scholar
- 12.J. Weickert, S. Ishikawa, and A. Imiya. On the history of Gaussian scale-space axiomatics. In Jon Sporring, Mads Nielsen, Luc Florack, and Peter Johansen, editors, Gaussian Scale-Space Theory, chapter 4, pages 45–59. Kluwer Academic Publishers, Dordrecht, The Netherlands, 1997.Google Scholar