A new approach in super resolution based on an adaptive regularization parameter

Super-resolution image reconstruction has been one of the most important research areas in recent years which goals to obtain a high resolution (HR) image from several low resolution (LR) blurred, noisy, under sampled and displaced images. Relation of the HR image and LR images can be modeled by a linear system using a transformation matrix and additive noise. However, a unique solution may not be available because of the singularity of transformation matrix. To overcome this ill- posed problem, stochastic methods such as ML and MAP have been introduced. However, their performance is not good because the effect of noise energy has been ignored. In this paper, we propose an adaptive regularization approach based on the fact that the regularization parameter should be a linear function of noise variance. The performance of the proposed approach has been tested on several images and the obtained results demonstrate the superiority of our approach compared with existing methods.