MRF model and edge-preserving image restoration with neural network

In the Bayesian approach, using MRF models, prior knowledge is incorporated into the problem via a parametric Gibbs prior and the solution is obtained by minimizing the resulting posterior energy function. There are two major difficult with this approach: the non-convexity of the function to be optimized and the choice of the MRF model parameters that best fit the available prior knowledge. Since these parameters considerably affect the quality of the reconstruction, selecting them is very critical task. This paper deals with the restoration of piecewise smooth images. The trained Generalized Boltzmann Machine can then be used in connection with a Hopfield analogue circuit to implement a mixed-annealing scheme for the minimization of the non-convex posterior energy.