Post Processing for Wavelet Domain HMT Image Resolution Enhancement

Wavelet domain image resolution enhancement algorithms assume that the available image is the low-frequency subband of a higher resolution image and high-frequency subbands are not available. Then, these high-frequency coefficients are estimated and the higher resolution image is generated by application of inverse wavelet transform. Some of these techniques have used probabilistic methods and utilisation of HMT (hidden Markov tree) was shown to produce promising results. HMT based methods model the wavelet coefficients as Gaussian distributions. However, as Gaussian distributions are symetrical around zero, coefficient signs are generated randomly and have an equal change of being positive or negative. In this paper, significance of having correst coefficient sign information is demonstrated and a postprocessing method is proposed to increase the accuracy of the estimated signs.