The Application Of Wavelet-Domain HMT Models

As a new framework for statistical signal processing,wavelet-domain hidden Markov tree models(HMT) is suitable for a wide range of applications,including image denoising,image segmentation and texture analysis and so on.It can concisely model the statistical dependencies and non-Gaussian statistics encountered in real-world signals.For the high noise and low contrast degree of infrared image,this paper proposes a new denoising method using significant coefficient rule based on HMT.In the proposed method,wavelet coefficients of logarithmic image are firstly modeled as mixture density of two Gaussian distributions with zero mean.In order to incorporate the spatial dependencies into the denoising procedure,HMT is explored and Expectation Maximization algorithm is used to estimate model parameters.The wavelet coefficients are updated according to a rule whether the coefficient is a significant one.The experimental results show that the proposed method could keep images edges from damaging and increase PSNR.