Support driven wavelet frame-based image deblurring

Wavelet frames have been widely applied in the field of image processing, due to their good capability for sparsely representing the piece-wise smooth functions which are suitable for describing natural images. In this paper, we propose a novel and efficient wavelet frame based sparse recovery model denoted as Support Driven Sparse Regularization (SDSR) for image deblurring. The partial support information of the wavelet frame coefficients is first attained via a self-learning strategy applied on a reference image, and this support prior is then exploited via a proposed truncated to regularization term. Moreover, existing off-the-shelf deblurring methods can be easily incorporated into the open interface of our flexible algorithmic framework, by providing the initial reference image for support detection. In the experiments, we compare our method with several state-of-the-art deblurring approaches. The results demonstrate the effectiveness of the proposed method in terms of PSNR and SSIM values. (C) 2018 Elsevier Inc. All rights reserved.