The motivation of this paper is to introduce a novel framework for therestoration of images corrupted by mixed Gaussian-impulse noise. To this aim,first, an adaptive curvelet thresholding criterion is proposed which tries toadaptively remove the perturbations appeared during denoising process. Then, anew statistical regularization term, called joint adaptive statistical prior(JASP), is established which enforces both the local and nonlocal statisticalconsistencies, simultaneously, in a unified manner. Furthermore, a noveltechnique for mixed Gaussian plus impulse noise removal using JASP in avariational scheme is developed--we refer to it as De-JASP. To efficientlysolve the above variational scheme, an efficient alternating minimizationalgorithm based on split Bregman iterative framework is developed. Extensiveexperimental results manifest the effectiveness of the proposed methodcomparing with the current state-of-the-art methods in mixed Gaussian-impulsenoise removal.
展开▼
