An Attention Based Similarity Measure for Colour Images
Much effort has been devoted to visual applications that require effective image signatures and similarity metrics. In this paper we propose an attention based similarity measure in which only very weak assumptions are imposed on the nature of the features employed. This approach generates the similarity measure on a trial and error basis; this has the significant advantage that similarity matching is based on an unrestricted competition mechanism that is not dependent upon a priori assumptions regarding the data. Efforts are expended searching for the best feature for specific region comparisons rather than expecting that a fixed feature set will perform optimally over unknown patterns. The proposed method has been tested on the BBC open news archive with promising results.
KeywordsColour Image Visual Attention Image Retrieval Retrieval Performance Similarity Match
Unable to display preview. Download preview PDF.
- 2.Fu, H., Chi, Z., Feng, D.: Attention-driven image interpretation with application to image retrieval. Pattern Recognition 39(7) (2006)Google Scholar
- 4.Treisman, A.: Preattentive processing in vision. In: Pylyshyn, Z. (ed.) Computational Processes in Human Vision: an Interdisciplinary Perspective, Ablex Publishing Corp., Norwood (1988)Google Scholar
- 6.Stentiford, F.W.M.: An attention based similarity measure with application to content based information retrieval. In: Yeung, M.M., Lienhart, R.W., Li, C.-S. (eds.) Storage and Retrieval for Media Databases, Proc SPIE, vol. 5021, pp. 221–232 (2003)Google Scholar
- 7.Stentiford, F.W.M.: Attention based similarity. Pattern Recognition (2006) (in press)Google Scholar
- 10.Multimedia Understanding through Semantics, Computation and Learning, EC 6th Framework Programme. FP6-507752 (2005), http://www.muscle-noe.org/