Image inpainting based on energy minimization

Image inpainting is an important work in the field of image processing. The basic idea of inpainting algorithm is to fill-in regions with available information from their surroundings. In this paper, we propose two image inpainting models based on variational method. The paper shows that the diffusion performance of the proposed models for image inpainting are superior to total variational (TV) model according to the physical characteristics in local coordinates. The experimental results show the effective performance of the proposed models in restoring text removal, scratched photos, and even removal of entire objects from images.