A model adaptive method is proposed for restoring blurred and noise corrupted images. The generalized p-Gaussian family of probability density functions is used as the approximating parametric noise model. Distribution shape parameters are estimated from the image, and the resulting maximum likelihood optimization problem is solved. An iterative algorithm for data-directed restoration is presen...

In this paper, some existing methods for estimating the shape parameter α of generalized Gaussian distribution (GGD) and their main features are summarized and compared with each other theoretically and practically. Some problems for the existing methods are put forward and some suggestions are also given for the further study on this problem.

 In this paper, we consider a flexible skew-generalized normal distribution. This distribution is denoted by $FSGN(/lambda _1, /lambda _2 /theta)$. It contains the normal, skew-normal (Azzalini, 1985), skew generalized normal (Arellano-Valle et al., 2004) and skew flexible-normal (Gomez et al., 2011) distributions as special cases. Some important properties of this distribution are establi...

In this contribution, we address the issue of Blind Source Separation (BSS) in non-Gaussian noise. We propose a twostep approach by combining the fractional lower order statistics (FLOS) for the mixing matrix estimation and minimum entropy criterion for noise-free source components estimation with the gradient-based BSS algorithms in an elegant way. First, we extend the existing gradient algori...