Content Based Medical Image Retrieval Based on BEMD: use of Generalized Gaussian Density to model BIMFs coefficients

In this paper, we address the problem of medical diagnosis aid through content based image retrieval methods (CBIR). We propose to characterize images without extracting local features, by using global information extracted from the image Bidimensional Empirical Mode Decomposition (BEMD). This method decompose image into a set of functions named Bidimensional Intrinsic Mode Functions (BIMF) and a residue. The generalized Gaussian density function (GGD) is used for modelling the coefficients derived from each BIMF, and to measure similarity between images we compute the similarity between GGDs by using the Kullback–Leibler Divergence (KLD). Retrieval efficiency is given for different databases including a diabetic retinopathy, mammography and a face database. Results are promising: the retrieval efficiency is higher than 95% for some cases.