Abstract
Digital image inpainting technique has been widely used in many socioeconomic areas and methods based on partial differential equations (PDE) attract intensive research in the hope of an automatic inpainting methodology. However the methods based on PDE are very time-consuming because they need to be solved by numerical integration along the temporal axis. In this paper, a fast convergent image inpainting method is proposed by combining Richardson extrapolation with an improved BSCB inpainting model, which improves the convergence rate of the numerical iterations. Experimental results show that the new model is effective and efficient.
