Content based Medical Image Retrieval: use of Generalized Gaussian Density to model BEMD's IMF.

摘要

In this paper, we address the problem of medical diagnosis aid through content based image retrieval methods. 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 Intrinsic Mode Functions (IMF) and a residue. The Generalized Gaussian Density function (GGD) is used to represent the coefficients derived from each IMF, and the Kullback-Leibler Distance (KLD) compute the similarity between GGDs. Retrieval efficiency is given for two databases : a diabetic rcti-nopathy one, and a face database. Results are promising: retrieval efficiency is higher than 85% for some cases.