Abstract: Traditional methods for image restoration usually focus on eliminating noises to accomplish restoring image，but for images polluted by strong noises，it is hard to achieve it in this way.Stochastic resonance can use noise to enhance signals，and due to this feature，a method for image restoration is proposed，which the bistable system adaptively adjusts its parameters by comparing mutual entropy to generate stochastic resonance.Results show that images restored based on the method introduced by this paper，have higher SNR，better robustness，and are more superior to traditional methods.