The iterative deconvolution of linearly blurred images using non-parametric stabilizing functions

An iterative solution to the problem of image deconvolution is presented. The previous image estimate is pre-filtered using a stabilizing function that is updated based on current error and noise estimates. Noise propagation from one iteration to the next is reduced by the use of a second, regularizing operator resulting in a hybrid iteration technique. Further, error terms are developed that shed new light on the error propagation properties of this method by quantifying the extent of noise and regularization error propagation. Optimal non-parametric stabilizing and regularization functions are then derived based on this error analysis