Back to Volume
Paper: Deconvolution by the Multiscale Maximum Entropy Method
Volume: 101, Astronomical Data Analysis Software and Systems V
Page: 191
Authors: Starck, Jean-Luc; Pantin, Eric
Abstract: In 1994, to overcome the difficulties encountered by the Maximum Entropy Method (MEM) to restore images containing both high and low frequencies, Bontekoe et al. introduced the Pyramid Maximum Entropy Deconvolution. However, this method presents several drawbacks such as parameters estimation (model, alpha). Following these ideas, we propose the Multiscale Maximum Entropy Method which is based on the concept of multiscale entropy derived from the wavelet decomposition of a signal into different frequencies bands. It leads to a method which is flux conservative, and the use of a multiresolution support solves the problem of MEM to chose the alpha parameter, i.e., relative weight between the goodness-of-fit and the entropy.
Back to Volume