摘要
在D.L.Donoho提出的小波阈值去噪的基础上,提出了一种新的阈值函数,其功能与硬阈值函数相当,但是它具有二阶连续可导性.相对于软阈值函数,此函数“硬”特性可以很好保留图像边缘等局部特征;而其可导性为实现图像的自适应去噪提供了可能.本文应用此阈值函数,基于SURE无偏估计,给出了一种小波自适应阈值去噪方法,并用Lenna和Barbara图做了仿真实验,实验结果显示此方法在最小均方误差(LMSE)意义上的优越性.
Based on the wavelet threshold denoising theory proposed by D. L. Donoho, a new threshold function is presented in this paper. It is rather similar to the hard threshold one, but it has two order continuous derivatives. Compared to soft threshold function, it can reserve image details much better due to its "hard" characteristic. Moreover, us two order deirvative makes it possible to construct an adaptive algorithm for image denoising. By using the new threshold function, a new adaptive shrinkage method is presented based on Stein's unbiased risk estimate(SURE). Two examples of Lenna and Barbara are given. The results indicate that the proposed method is very effective for image denoising application, in adaptively finding the optimal solution with least mean square error(LMSE) sense.
出处
《北京交通大学学报》
EI
CAS
CSCD
北大核心
2007年第2期15-18,共4页
JOURNAL OF BEIJING JIAOTONG UNIVERSITY
基金
北京交通大学校科技基金(2005SM011)