A New Image Denosing Method via Variable Splitting Gradient Projection for Constrained Total Variation with Sparsity
Fan Liao, Jia Song Wu, Junlin Ouyang, Jean-Louis Coatrieux, Hua Zhong Shu · Applied Mechanics and Materials · 2014
The total variation (TV) models have been successfully used for image denoising problem, but most of them usually smooth out the details while removing the noise. In this paper, we propose a new image denoising method that incorporates the sparsity priori information into the traditional TV models. We then solve the optimization problem by combining the variable splitting and dual approaches. Our method can be applied to both isotropic and anisotropic TV models. Experimental results show that the proposed method outperforms the existing methods.