A relaxation evolutionary image restoration method

Evolution strategies (ESs) are global optimization models in the light of natural evolution. Using relaxation evolution strategy, a novel method for restoration of gray level images blurred by a known shift-invariant point spread function and corrupted by added Gaussian white noise is presented in this paper. With relaxation mutation and other improvements of traditional ESs, a practical evolution image restoration method is proposed. Computer simulation examples illustrate the usefulness of our method. Comparisons to other image restoration methods, such as inverse filter and neural restoration method, are also provided