单小波去噪方法在多小波去噪中的应用研究

单小波去噪方法中Visualshrink去噪法是渐进最优的。但将'Visualshrink单小波去噪方法用于多小波去噪,其优越性丧失,图象中存在严重的Gibbs效应,且去噪效果降低,对此,我们改进了单小波Visualshrink去噪方法的门限选取,提出了改进的Visualshrink多小波去噪方法(VMD)。同时,还给出了离散多小波变换的具体实现方法。实验结果证明,改进的多小波去噪方法与直接将Visualshrink方法用于多小波去噪相比,前者效果明显好于后者。

A Study on Multiwavelet Image Denoising Based on Methods of Singlewavelet Image Denoising

Visulshrink is regressively optimal among algorithms of singlewavelet denoising. But the advantage is forfeit if Visulshrink is used in multiwavelet denoising. On this condition, there is serious Gibbs effect in images and not good effect in image denoising. In order to solve this problem, we improved the algorithm of threshold selection of Visualshrink and proposed an improved Visualshrink multiwavelet denoising (VMD).During this procedure, we also provide a concrete method to realize multiwavelet transform. The experimental results show that VMD is superior to multiwavelet denoising with Visualshrink.