Directional decomposition based total variation image restoration
Daniel Rodrigues Pipa, Stanley H. Chan, Truong Q. Nguyen · 2012
This paper proposes an extension of total variation (TV) im-age deconvolution technique that enhances image quality over classical TV while preserving algorithm speed. Enhancement is achieved by altering the regularization term to include di-rectional decompositions before the gradient operator. Such decompositions select areas of the image with characteristics that are more suitable for a certain type of gradient than an-other. Speed is guaranteed by the use of the augmented La-grangian approach as basis for the algorithm. Experimental evidence that the proposed approach improves TV deconvolu-tion is provided, as well as an outline for a future work aiming to support and substantiate the proposed method. Index Terms — Total variation, augmented Lagrangian, image deconvolution, image restoration, directional decom-positions. 1.