Super-resolution Based Image Inpainting

-This paper introduces a new examplar-based inpainting framework. A coarse version of the input image is first inpainted by a non-parametric patch sampling. Compared to existing approaches, some improvements have been done (e.g. filling order computation, combination of K nearest neighbours). The inpainted of a coarse version of the input image allows to reduce the computational complexity, to be less sensitive to noise and to work with the dominant orientations of image structures. From the low-resolution inpainted image, a single-image super-resolution is applied to recover the details of missing areas. By sample of a nonparametric patch makes blur image which was given as input initially is goes in painted. When compared to previous approaches, some features have been improved. The in painted of a blur version of the input image permits to decrease the computational complexity, to be low sensitive to sound and to operate with the image structures dominant orientations. In painted image moulds from the lowresolution to a single-image which is super-resolution one and that is used to backup the data of areas which are missing. The outputs of researches on natural texture synthesis and images explain the effectiveness of the proposed system