High-Order Total Bounded Variation Approach for Gaussian Noise and Blur Removal

Abstract

In this paper, we proposed a high-order total bounded variation method for image restoration under Gaussian noise and blur. The proposed method can avoid the staircase effect, while preserving the textures, edges and fine details in the restored image. Further, we proposed strongly convex model to get the global optimal solution. For this model, we employ a Split Bregman algorithm to solve numerically. Finally, our results are provided to demonstrate both in terms of quantitative and qualitative measure. We can say that our proposed method is better than the normal total bounded variation (TBV) based method.