Abstract: In the research on spatially adaptive regularized image restoration algorithm，it is observed that the effect of the algorithm is not satisfactory in the case that there is salt and pepper noise in the image.In order to solve this problem，a new visibility function is presented，in which fuzzy entropy is substitute to mean square error to evaluate the spatial activity of the image，so the algorithm can accommodate the disturb of more kinds of noise，with the quality improvement of restorations.Computer simulation shows that the performance of the new algorithm is much better than the traditional one in the presence of salt and pepper noise and the restored result of blurred-noisy image is given in the experiment.