基于多小波变换及多层阈值的图像降噪研究

An Approach to Image Noise Reduction Based on Multiwavelet Trans form and Multilevel Threshold

提出了一种基于多小波变换分层阈值的图像降噪的方法。此方法首先对一幅噪声图像进行多小波分解;接着根据多小波分解后的能量分布特性,在不同尺度的高频子带内,对小波系数进行不同阀值处理;最后经多小波反变换,得到重构图像。实验结果表明:此方法既可以有效地降低噪声,又可以较好地保持图像细节。

A Method of image denoising based on multiwavelet transform and multilevel threshold is proposed.Firstly,noised image are decomposed by multiwavelet transform,Secondly,in high frequency area with different scale,the coefficients are dealed with different threshold according to coefficients energy distribution.Finally,reconstructed image can be obtained by using the inverse multiwavelet transform for all important coefficients and approximation coefficients.Experimental results prove that by using this method,image noise can be reduced effectively and image details can be preserved a lot.