Deblurring Poissonian Images via Multi-constraint Optimization

摘要

This paper deals with the restoration of images corrupted by a non-invertible or ill-conditioned linear transform and Poisson noise. The paper is experimental and can be seen as a continuation of "as reported by Harizanov et al. (Epigraphical Projection for Solving Least Squares Anscombe Transformed Constrained Optimization Problems 2013)". The constraint set in the minimization problem, considered there, was too large and the results tend to oversmooth the initial image. Here, we consider various techniques for restricting this set in order to improve the image quality of the result, and numerically investigate them. They are based on image domain decomposition and give rise to multi-constraint optimization problems.