Copula-based statistical models for multicomponent image retrieval using a Bayesian copula selection

In this paper, we are interested in multicomponent image indexing in the wavelet transform (WT) domain. In this respect, the joint distribution of the WT coefficients through all the channels is modeled by a parametric copula-based model. The parameters of this model are considered as the salient signatures of the image content. The relevance of this model is based on a reliable choice of both the appropriate marginal distributions and the copula density reflecting the cross-component correlation. The contribution of this work consists in proposing a Bayesian framework to select the copula family reflecting the best the inter-component dependence. Besides, a scalable organization of the features database is carried out in order to enable a coarse-to-fine resolution retrieval procedure suitable for progressive telebrowsing applications. Experimental results indicate that our new approach improves the retrieval performances achieved by conventionalworks for which the copula family selection generally relies on guesswork and testing of multiple hypothesis.