Noise Suppression of Magnetic Resonance Image using Genetic Algorithm
I Golda Selia, Latha Parthiban, Wavelet Multiscale · 2013
Edge-Preserving denoising is an important task in medical image processing. In this paper a waveletbased multiscale products thresholding scheme for noise suppression of magnetic resonance images optimized by genetic algorithm has been proposed. A dyadic wavelet transform is employed to decay the noise rapidly. Here the adjacent wavelet subbands are multiplied to enhance edge structures. An adaptive threshold is calculated and imposed on the products to identify important features. This scheme suppresses noise better and preserves edges than other waveletthresholding methods and finally it was optimized by GA.