SVD域的图像高斯噪声强度估计  

Gaussian noise level estimation in SVD domain for images

作　　者：柳薇[1] 

机构地区：[1]华南师范大学计算机学院,广州510631

出　　处：《中国图象图形学报》2012年第8期923-933,共11页Journal of Image and Graphics

基　　金：广东省科技攻关基金项目(2009B010900027)

摘　　要：精确估计图像或视频中的噪声强度对于后续的信号处理是至关重要的先决条件。通过对含噪图像的奇异值特性的研究,提出一种精确的SVD域的图像噪声强度估计算法。该算法对噪声强度估计提出了创新的解决方法:1)利用奇异值的尾部数据进行噪声强度估计,这样达到尽可能地降低图像信息对噪声估计的干扰;2)对含噪图像加入已知强度的高斯白噪声,以计算噪声估计时需要设置的与图像内容相关的参数,因此该算法可以自适应图像的结构,能够广泛地适应各种类型的图片。实验结果表明SVD域噪声强度估计算法适用于各种图片类型,而且在极大的噪声强度范围内都能够稳定精确地估计噪声强度。Accurate estimation of Gaussian noise level is of fundamental interest in a wide variety of vision and image pro-cessing applications as it is critical to the processing techniques that follow. In this paper, a new, effective noise level esti-mation method is proposed based on the study of singular values of noise-corrupted images. There are two major novel as-pects of this work to address the major challenges in noise estimation： 1 ） the use of the tail of singular values for noise esti-mation to alleviate the influence of the signal on the data basis for the noise estimation process; 2） the addition of known noise to estimate the content-dependent parameter, so that the proposed scheme is adaptive to visual signal and therefore it enables wider application scope of the proposed scheme. The experiments results demonstrate that the proposed algorithm can reliably infer noise levels and shows robust behavior over a wide range of visual content and noise conditions, in com-parison with the relevant existing methods.

关 键 词：噪声估计 高斯白噪声 奇异值分解 图像处理 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]