Image Denoising Based on a Mixture of Laplace Distributions in Complex Wavelet Domain

Recently, discrete complex wavelet transform has been proposed as a novel analysis tool featuring near shift-invariance and improved directional selectivity compared to the standard wavelet transform. Within this framework, we describe a novel technique for removing noise from digital images. We design a maximum a posteriori (MAP) estimator based on the modeling of wavelet coefficients in each subband with a mixture of Laplace random variables (rvs). Using this relatively new statistical model we are able to better capture the heavy-tailed nature of wavelet coefficients. The simulation results show that our proposed method yields better performance than several published methods visually and quantitatively.

Keywords:

MAP estimator , mixture model , complex wavelet transform