一种基于小波变换的图像去噪算法与实现

在众多的小波去噪方法中,运用最多的是Donoho小波阈值萎缩法。这一阈值是最佳阈值的上限但不是最佳阈值,并且它只与噪声大小有关而与图像自身特性无关。新阈值函数克服了软阈值函数中小波系数估计和原系数之间的具有固定偏差的缺点。同时,该函数克服了硬阈值函数不连续的缺点。通过调节A(任意正常数)取值可以改变新阈值函数的趋向,这也体现了新阈值函数的灵活性。仿真结果表明,改进后的方法应用于图像去噪,无论是视觉效果还是峰值信噪比都有了改善。

One Image Denoising Algorithm and its Implementaion Based on Wavelet Transform

In many kinds of wavelet denoising methods,Donoho's wavelet shrinkage is widely used forim agede noising.which is not optima threshold but the maximum of the optimal shrinkage threshold.And it is irrelevant with the image itself.This new thresholding function overcomes the shortcoming that there is an invariable dispersion between the estimated wavelet coefficients and the decomposed wavelet coefficients of the soft2-thresh olding method.At the same time,this new function overcomes the shortcoming of the hard-thresholding method with discontinuous function.By changing A(const.),we can change the trend of this new function,which can illuminate the elasticity of the new function.Simulation results indicate that the de-noising approach with the new threshold function outperforms the traditional soft-threshold function in both visional effects and peak signal to noise ratio.