A new super-resolution algorithm by interpolation in homogeneous areas
Chunjiang Duanmu, Di Zhao · 2016
Single image super-resolution technique has been used in wide applications to enlarge the resolution of a image. In this paper, a new single image super-resolution algorithm is proposed. In the proposed algorithm, the edge pixels are firstly detected by using the Sobel operator. Then, the set of the pixels which participate in the filtering and estimation of each high-resolution pixel is determined. Finally, the filtering in homogeneous areas is carried out to determine the high-resolution image edge pixel value and non-edge pixel value. Since the filtering is conducted in homogeneous areas, the image edge blurs can be avoided and better results can be obtained. Simulation results verify the superiority of the proposed algorithm.