Image super resolution reconstruction algorithm based on sparse representation and the UV chroma processing

The paper proposes an image super resolution reconstruction algorithm based on sparse representation and the UV chroma processing. For each patch of the low resolution input images, a sparse representation is sought to generate the high-resolution output. The sparse representation of a low resolution image patch can be applied to generate a high resolution image patch through dictionary learning. To further improve the effects of super resolution images, the UV chroma processing based on super resolution luminance information with bilateral filtering is put forward as well. The experimental results show the method in this paper obtains better outcomes no matter in visual effects or in the quality measures of RMSE and SSEVI.