基于Bayesian估计和Wiener滤波的阈值去噪方法  

Adaptive Wavelet Thresholding Denoising Method Based on Bayesian

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：《光子学报》2003年第7期889-891,共3页Acta Photonica Sinica

基　　金：陕西省自然科学基金 (2 0 0 0SL0 2 )资助项目

摘　　要：基于阈值的小波域去噪方法的核心是阈值选取 ,通过最小化一个Bayesian风险函数得到一种自适应阈值 ,结合线性滤波中具有代表性的Wiener方法 ,提出了一种新的去噪方法 .实验结果表明 ,该方法能有效地去除图像中的白噪声 ,同时还能较好地保留图像的边缘信息 。Selecting threshold is the most important in threshold-based nonlinear filtering by wavelet transform.A novel adaptive threshold by minimizing a Bayesian risk is presented. A new denoising method is proposed by combining this thresholding method with Wiener filtering. Experimental results show that the proposed method indeed removes noise significantly and retains most image edges. The results compare favorably with the reported results in the recent denoising literature.

关 键 词：图像处理 阈值去噪 小波变换 Bayesian估计 WIENER滤波 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]