Edge-Membership Based Blurred Image Reconstruction Algorithm

Enhancing the sharpness of edges and avoiding the ringing effect are two important issues in blurred image reconstruction. However, there is a tradeoff between the two goals. A reconstruction filter with long impulse response can reduce the ringing artifact, however, the sharpness of the edge is decreased. By contrast, a short impulse response reconstruction filter can perfectly retrieve the edge but is not robust to noise. In this paper, an edge-membership based blurred image reconstruction algorithm is proposed. In order to achieve the two goals simultaneously, we design two filters. One focuses on edge restoration and the other one focuses on noise removing. After performing linear combination of the outputs of the two reconstruction filters, the edges are preserved and the ringing artifacts are removed at the same time. Simulation results show that our approach can reconstruct the blurred image with sharp edge and less ringing effect.