一种基于自适应阈值的图像去噪新方法  

Adaptive Wavelet Thresholding for Image Denoising

作　　者：尚晓清[1] 王军锋[1] 宋国乡[1] 

机构地区：[1]西安电子科技大学理学院数学系,西安710071

出　　处：《计算机科学》2003年第9期70-71,共2页Computer Science

基　　金：陕西省自然科学基金(2000SL02)

摘　　要：1引言 利用小波去除信号或图像中噪声的方法在过去十年间得到了广泛的关注.大体上可以分为三个阶段:最初是将含噪信号作正交小波变换.然后对其系数取阈值得到去噪后的信号[1].Selecting threshold is the most important in threshold.based nonlinear filtering by wavelet transform. In this paper, a novel adaptive threshold is proposed by minimizing a Bayesian risk (It is adaptive to subband because it depends on data-driven estimates of the parameters). Combining this thresholding method with Wiener filting can result a new denoising method. Expermental results show that the proposed method indeed remove noise significantly and retaining most image edges. The results compare favorably with the reported results in the recent denoising literature.

关 键 词：自适应阈值 图像去噪方法 马尔科夫模型 小波系数 图像处理 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TN911.73[自动化与计算机技术—计算机科学与技术]