Wavelet-domain image denoising algorithm using series expansion of coefficient P.D.F. in terms of Hermite polynomials

Abstract

A new wavelet-domain image denoising algorithm is proposed that uses series expansion of continuous probability density function (pdf) for estimating wavelet coefficient variance field. The expanded pdf is derived using standard normal as weighting function that results the Hermite polynomials in the series. Variance field estimated using the proposed algorithm is used in a minimum mean square error (MMSE) estimator to restore the noisy image wavelet coefficients. Simulation results on standard images show improved performance both in visual quality and in terms of peak signal to noise ratio (PSNR) as compared to other recent image denoising methods.