Image Resolution Enhancement using Wavelet Domain Hidden Markov Tree and Coefficient Sign Estimation

Image resolution enhancement using wavelets is a relatively new subject and many new algorithms have been proposed recently. These algorithms assume that the low resolution image is the approximation subband of a higher resolution image and attempts to estimate the unknown detail coefficients to reconstruct a high resolution image. A subset of these recent approaches utilized probabilistic models to estimate these unknown coefficients. Particularly, hidden Markov tree (HMT) based methods using Gaussian mixture models have been shown to produce promising results. However, one drawback of these methods is that, as the Gaussian is symmetrical around zero, signs of the coefficients generated using this distribution function are inherently random, adversely affecting the resulting image quality. In this paper, we demonstrate that, sign information is an important element affecting the results and propose a method to estimate signs of these coefficients more accurately.