基于第二代bandelets的图像去噪  

Second Generation Bandelets Based Image Denoising

作　　者：杨晓慧[1] 焦李成[1] 李伟[1] 

机构地区：[1]西安电子科技大学智能信息处理研究所,陕西西安710071

出　　处：《电子学报》2006年第11期2063-2067,共5页Acta Electronica Sinica

基　　金：国家自然科学基金(No.60133010;No.60472084);国家973计划(No.2001CB309403)

摘　　要：本文提出一种基于第二代bandelets,并结合多层阈值和自适应Wiener滤波的图像去噪方法.第二代bandelets能充分利用图像内在的几何正则性,自适应获得图像的最优表示;多层阈值符合小波多尺度域的系数统计特性;维纳滤波可以有效去除阈值去噪带来的纹理效应.实验结果表明:该去噪方法与基于小波变换的方法相比,作用于含有加性高斯白噪声的光学图像时,避免了小波变换带来的边界的振铃效应,并在峰值信噪比上有一定的改善;作用于合成孔径雷达图像中的相干斑抑制时,不论从视觉效果还是等效视数和比值图等衡量指标上都取得了较好的效果.Based on second generation bandelets and combined with multi-level thresholding and Wiener filter, this paper proposes a novel denoising method. As a new multiresolufion geometric analysis tool, second generation bandelets can make full use of intrinsic geometric regularity and provide optimal representation adaptively. Multilevel threshoidings sat/sly the statistic characteristics of coefficients. Wiener filter can get rid of the texture effects introduced by thresholding denoising. Numerical tests applied on optical images show that the image denoising method avoids visible tinging effects and provides improvements in Peak-to-Signal Ratio, More significance, this technique is used for restraining speckle noise in synthetic aperture radar images successfully in equivalent number of looks and ratio images.

关 键 词：多尺度几何分析 第二代bandelets 几何正则性 多层阈值 合成孔径雷达 

分 类 号：TN911[电子电信—通信与信息系统]