Single frame superresolution

Abstract

Super-resolving an image from single frame observation image. In many cases more than one low resolution observations may not be available, need high spatial resolution images e.g. medical imaging, remote sensing etc.. We obtain the estimate of the high frequency (edges) contents by learning the wavelet coefficients from a database of similar or arbitrary high resolution images. We then employ a suitable regularization approach for edge preservation as well as for ensuring spatial continuity among pixels. The learnt wavelet coefficients are used as edge prior. An Markov Random Field (MRF) model is used for spatial dependence. The final cost function consists of data fitting term and two regularization terms, which is minimized by global optimizing (Gradient Decent) method. The experiments conducted on real images show considerable improvement both perceptually and quantitatively when compared to conventional interpolation (Bicubic Interpolation images) methods. The advantage of the proposed technique is that unlike many other super-resolution techniques, a number of low resolution observations are not required. Finally instead of MRF we used Inhomogeneous markov random field(IGMRF) for maintain the spatial dependency effectively in super-resolved image, the results show that its better than MRF prior.