Analysis of Multiresolution Image Denoising Schemes Using Generalized{gaussian Priors

In this paper, we investigate various connections between wavelet shrinkage methods in image processing and Bayesian estimation using Generalized Gaus-sian priors. We present fundamental properties of the shrinkage rules implied by Generalized Gaussian and other heavy{tailed priors. This allows us to show a simple relationship between diierentiability of the log{ prior at zero and the sparsity of the estimates, as well as an equivalence between universal thresholding schemes and Bayesian estimation using a certain Generalized Gaussian prior.