Bayesian image restoration using a wavelet-based subband decomposition

In this paper the subband decomposition of a single channel image restoration problem is examined. The decomposition will be carried out in the image model (prior model) in order to take into account the frequency activity of each band of the original image. The hyperparameters associated to each band together with the original image are rigurously estimated within the Bayesian framework. Finally the proposed method is tested and compared with other methods on real and synthetic images.