Multifractal image denoising
Jacques Lévy Véhel, Bertrand Guilheneuf · 1997
We present a new method for image denoising based on singularity analysis. The image is characterized via its multifractal spectrum, which mode yields the most frequent Holder exponent. Using 2-microlocal analysis, we define an operator that shifts the spectrum so that the transformed image has almost sure Holder exponent a little above 2. This manipulation leads to a smooth image while preserving the relative strength of the singularities (as, for instance, edges or textures) in the signal. Experimental results on Radar images are presented. Keywords : multifractal analysis, denoising, 2microlocalisation, wavelets, Radar imaging. 1 Introduction There has been a tremendous amount of work dedicated to image restoration [2, 5, 4, 3] in recent years. In classical methods, one aims at filtering the noisy data, in order to obtain a signal which is as close as possible (in a predefined sense) to the unknown original one by making assumptions on the noise model. However, the perturbation of...