Low-complexity image denoising based on Bayesian estimation of statistical parameter

The distortion of images by additive white Gaussian noise (AWGN) is common during its acquisition, processing, compression, storage, transmission, and reproduction. This paper is concerned with dual-tree complex wavelet-based image denoising using Bayesian techniques. Indeed, one of the cruxes of the Bayesian image denoising algorithms is to estimate the local variance of the image. Here, we employ maximum a posterior (MAP) estimation to calculate local observed variance with Pareto density prior for local observed variance and Laplacian or Gaussian distribution for noisy wavelet coefficients. Evidently, our selection of prior distribution is motivated by analytical and computational tractability. The experimental results show that the proposed method yields good denoising results.