Optimal choice of local regularization weights in iterative image restoration

In the study of space-variant regularization for image restoration, little effort has been devoted to the search of optimal local regularization weights. In this paper, we address how to derive the optimal local regularization weights in the context of iterative image restoration. The optimal relationship between the two weight matrices for local regularization is derived, and, based on that relationship, a proper choice of the weight matrices is then presented. The results we derived provide a mathematical backup of the viability of some heuristic solutions suggested in the literature