Image Restoration Based on Wiener Filter and Constrained Least Square Filter

In the process of image acquisition, the final acquired image is always accompanied by dynamic blurring and noise. This article describes the image degradation process as a degradation system. The original image function is first convolved with Point Spread Function (PSF) to simulate the motion blur process, and then Gaussian white noise is added to obtain the final degraded image. For degraded images, this article discusses how to use the Wiener filter and constrained least square filter to restore the image. The Wiener filter uses the minimum mean square error as a criterion for recovery while the least square filter uses the least square criterion for recovery. On the premise of accurately grasping the degradation function and the statistical information of the original picture and noise, the Wiener filter can have a better restoration effect. When only the information about the mean value and variance of the noise is grasped, the constrained least square filtering method can be used to obtain a better restoration effect.