It is well known that image restoration is an essential preprocessing step for many image analysis applications. Image restoration has been widely investigated in the field of image processing. So far, the majority of works have been devoted to the image denoising. For this issue, the most common problem is that some interesting structures in the image will be removed from the concerned image during noise suppression. Such interesting structures in an image often correspond to the discontinuities of the image. In this paper, we propose a novel pixon-based multiresolution method for image denoising. The key idea to our approach is that a pixon map is embedded into the MRF models under a Bayesian framework. The remarkable advantage of our approach is that restoring corrupted images and preserving the shape transitions in the restored results have been orchestrated very well. i simulated annealing algorithm is implemented to find the MAP solution. Experiments illustrate that our method is much more effective and powerful than the Wiener and median filtering techniques, two most typical and widely used techniques. At the end of this paper, we thoroughly discussed the issues on how to select effective parameters of our algorithm. Although the work is based on experiments, our results do give some wise advice on this issue.
修改评论