Analysis the Statistical Parameters of the Wavelet Coefficients for Image Denoising

Abstract

mage denoising is aimed at the removal of noise which may corrupt an image during its acquisition or transmission. De-noising of the corrupted image by Gaussian noise using wavelet transform is very effective way because of its ability to capture the energy of a signal in few larger values. This paper proposes a threshold selection method for image de-noising based on the statistical parameters which depended on sub-band data. The threshold value is computed based on the number of coefficients in each scale jof wavelet decomposition and the noise variance in various sub-band. Experimental results in PSNR on several test images are compared for different de-noise techniques