Improved single image super-resolution based on edge directed interpolation
Haiyang Zhou, Ling Yan, Lei Zhang, Rong Zheng, Feihong Yu · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2016
Single image super-resolution is one of the most prevalent techniques in digital image processing with a wide range of applications. In this paper, we analyzed the well-known new edge directed interpolation (NEDI) and proposed an improved single image super-resolution method based on edge directed interpolation which could preserve the edge features and reduce common artifacts efficiently. In order to obtain a good tradeoff between quality and speed, a new scheme which moves local window along edge direction is applied. Simulation results demonstrate that the proposed algorithm improves the subjective quality of the interpolated images over the other conventional interpolations with competitive computation complexity.