The aim of image restoration is to obtain a best possible estimate of an original image from a recorded version of the image. The effectiveness of restoration procedure requires the extent and the accuracy of the knowledge concerning the degradation process. If the degradation is unknown, it has to be estimated from the degraded image itself. In this paper, a new two-phase blind restoration algorithm is proposed. In the first phase of the algorithm, estimated power spectra of subimages of the original image is determined from the degraded image. In the second phase, a blind restoration algorithm is employed to obtain a restored image using estimated power spectra obtained in phase 1. Experimental results are presented to illustrate the proposed algorithm.
展开▼
