Statistical modelling for image retrieval using a biological model of the perceptive colour space

Natural image retrieval is a main challenge for image indexing. In this domain, colour information is one of the most important features. We propose a perceptive colour space based on a biological model of the retina. In this space, a model of Gaussian mixture appears very efficient for colour distribution. Two strategies are presented, retrieval by maximum likelihood (i) on the global chromatic distribution, (ii) on the local spatio-chromatic distribution.

[1]  J. Hérault,et al.  Variability in color discrimination data explained by a generic model with nonlinear and adaptive processing , 2001 .

[2]  J. Cohen,et al.  Color Science: Concepts and Methods, Quantitative Data and Formulas , 1968 .

[3]  Joachim M. Buhmann,et al.  Empirical evaluation of dissimilarity measures for color and texture , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[4]  G. Wyszecki,et al.  Color Science Concepts and Methods , 1982 .

[5]  D. L. Macadam.  Visual Sensitivities to Color Differences in Daylight , 1942 .

[6]  Hayit Greenspan,et al.  A Continuous Probabilistic Framework for Image Matching , 2001, Comput. Vis. Image Underst..

[7]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[8]  Gérard Govaert,et al.  Assessing a Mixture Model for Clustering with the Integrated Completed Likelihood , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Christophe Biernacki,et al.  Indexation et appariement d'images par modèle de mélange gaussien des couleurs , 1999 .

[10]  Glenn Healey,et al.  COLOR IN COMPUTER VISION: RECENT PROGRESS , 1999 .

[11]  Jitendra Malik,et al.  Blobworld: Image Segmentation Using Expectation-Maximization and Its Application to Image Querying , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Aude Oliva,et al.  Classification of scene photographs from local orientations features , 2000, Pattern Recognit. Lett..