A Novel Method for the Determination of the Wavelet Denoising Threshold

Wavelet threshold shrinking algorithm can effectively remove image noises. In the algorithm the establishment of denoising threshold directly affects denoising results. The noise standard variance is an important factor in ascertainment of thresholds in wavelet denoising. In order to find more suitable algorithms to estimate denosing threshold, a novel algorithm using fuzzy mean error instead of standard variance is proposed based on characteristics of medical images. The experiment results show that the proposed algorithm can efficiently wipe off the noises while keep the image details.