Estimation of optimal parameters of the multiplicative algorithm of wavelet filtering of images

Abstract

In most widely used wavelet filtering algorithms, the decomposition coefficients are processed with the use of threshold functions, which makes it possible to account for the “energy” feature of each decomposition coefficient. To some extent, this disadvantage is removed in a class of multiplicative algorithms, which account for the energy of decomposition coefficients located in a given proximity from a processed decomposition coefficient. However, the effective error minimization in wavelet filtering of images requires that a parameter, the choice of the optimal value of which remains to be an unsolved problem, is introduced into these processing algorithms. Therefore, the problem solved in this paper is the estimation of the optimal value of this parameter, which minimizes the root-mean-square error of the filtering. The performed studies showed the effectiveness of the proposed estimation algorithm and the possibility of its use in practice.