Journal of Computations & Modelling

Hybrid regularization for wavelet frame and total variation with application to Poisson noise removal

• [ Download ]
• Times downloaded: 9795

• Abstract

   

  Blurred images corrupted by Poisson noise frequently appear in various applications such as medical and astronomical imaging. Due to the strong edge preserving ability, the Total variation (TV) regularization has been developed as an important regularization method to solve the Poisson denoising problem. However, TV introduces staircase effects. In this paper, we propose a hybrid variational model which takes advantages of the wavelet tight frame and TV. An efficient iterative algorithm based on the augmented Lagrangian technique is proposed. Under some conditions, the convergence property of the proposed algorithm is also investigated. Numerical experiments illustrate the effectiveness of the proposed method.