一种基于小波域系数收缩的图像降噪改进算法  

An improved image denoising method based on wavelet domain coefficients shrinkage

作　　者：赵一凡[1] 李久贤[1] 吴游[1] 夏良正[1] 

机构地区：[1]东南大学自动化学院,江苏南京210096

出　　处：《电路与系统学报》2008年第5期26-29,33,共5页Journal of Circuits and Systems

基　　金：长三角联合攻关项目(2005E60007)

摘　　要：本文根据小波变换中分解级数与噪声在小波域中的特性,利用具有平移不变性的稳态小波分解方法,将Donoho的小波系数收缩算法用于局部小波系数的处理,并提出了一种具有自适应特性的阈值设定方法。这种方法由于考虑到了局部小波系数的变化特点和图像中信息分布的不均匀性,对加性高斯白噪声的去除具有很好的效果。According to the relationship between inter/intra wavelet coefficients in different decomposition level, a new denoising method is proposed, which is based on an adaptive threshold and stationary wavelet transform. Because local wavelet coefficients characteristic and information distribution in images are considered, the proposed method has better denoising result than other methods especially for Addictive Gaussian White Noise（AWGN）.

关 键 词：小波 图像降噪 收缩算法 

分 类 号：TN911.73[电子电信—通信与信息系统]