Adaptive regularized image restoration using the theory of convex projections

An adaptive solution to the regularized image restoration problem is formulated in the context of projections onto convex sets (POCS). In this paper, we introduce two new closed convex sets, an extended Wiener set and a bounded local image variance set. The extended Wiener set is defined based on the Wiener solution in the frequency domain. The adaptivity of the new algorithm is provided by the bounded local image variance set. The bound on the local image variance is determined as a function of the local activity of the degraded image. Experimental results are provided to demonstrate the superior performance of the new technique.