Image denoising based on a mixture of bivariate gaussian distributions with local parameters in complex wavelet domain

The performance of estimators, such as maximum a posteriori (MAP), is strongly dependent on the accuracy of the employed distribution for the noise-free data and the accuracy of the involving parameters. In this paper, we select a proper model for the distribution of wavelet coefficients and present a new image denoising algorithm. We model the wavelet coefficients in each subband with a mixture of bivariate Gaussian probability density functions (pdfs) using local parameters for the mixture model. This model allows to capture the heavy-tailed nature of the coefficients and to exploit the interscale dependencies of the wavelet coefficients. The empirically observed correlation between the coefficient amplitudes are locally calculated and used in order to characterize the model. We propose a MAP estimator for image denoising using this mixture model and the estimated local parameters. Our simulation results reveal that the proposed method outperforms several existing methods both visually and in terms of peak-signal-to-noise-ratio (PSNR).