Image amplification based on pixel-splitting

In this paper, we propose a pixel-splitting based image amplification method, which involves two main operations: edge-keeping and mean-keeping. Our main idea is to splitting each parent-pixel into multiple sub-pixels. Based on the edge detection and image gradient, we separate edge into vertical and horizontal short rods. The main orientation of each rod is estimated. Then the intensities of sub-pixels around the rod are calculated according to the intensities and edge orientation of parent-pixels. The rest sub-pixels are estimated based on the principle of mean-keeping. The experimental results demonstrate that our method is effective in zigzagging artifacts reduction, de-blurring, and contrast enhancement.