Undecimated Wavelet Based New Threshold Method for Speckle Noise Removal in Ultrasound Images

This paper includes different approaches for adaptive wavelet. threshold (Bayes Shrink and Normal Shrink) and a robust wavelet domain method for noise filtering in ultrasound images. The search for efficient image denoising methods is still a valid challenge at the crossing of functional analysis and statistics. The proposed work in this paper extends the existing technique by improving the threshold function and produces results which are based on different noise levels. The standard signal to noise ratio (SNR) is not adequate to evaluate the noise removal in speckled images therefore to calculate multiplicative noise suppression a signal-to-mse (S/MSE) ratio is used as a measure of the quality of denoising.