A novel statistical model for content-based stereo image retrieval in the complex wavelet domain

This paper presents a new stereo image (SI) retrieval method based on a statistical model of complex wavelet coefficients subbands. In this context, a Gaussian copula-based multivariate model is used to capture the dependence between complex wavelet coefficients of both left and right images, and a non-Gaussian univariate model is used to characterize the statistical behavior of the disparity map. Thanks to its flexibility, the copula tool allows us to choose several marginal densities while keeping the multivariate properties. Features are extracted by estimating parameters for both multivariate and univariate models. Finally, a weighted Jeffrey divergence (JD) is used as a similarity measurement between the underlying models. Experimental results on a stereo image database demonstrate the performance of the proposed method in terms of the retrieval rates as well as the computational time.