An adaptive strategy for adjusting contribution of frames in super resolution imaging

In this paper we address the problem of superresolution imaging. Super-resolution (SR) technique aims to produce a high-resolution (HR) image using a set of aliased low-resolution (LR) images of the same scene. In the process of reconstructing super-resolution image, the assumed model violations for the imaging process effect in final reconstructed HR image. So, a method which promises robustness against these errors would have desirable performance. In this paper, we proposed a new adaptive strategy for each LR frames in SR image reconstruction and hence can automatically suppress the contribution of those frames that suffer from restoration problem and noise which causes violation from their assumed model. The result of experiment shows the proposed algorithm performs well in existence of noise and misregistration.