摘要
获取图像的过程中光学系统的像差、大气扰动、运动、散焦和系统噪音等因素会导致图像质量的下降即降质,会造成图像的模糊和变形。该文对图像复原所用的逆滤波、维纳滤波、约束最小平方复原原理进行了论述。维纳滤波复原图像需估计未退化图像和噪声功率谱,在实际中图像和噪声功率谱的比值很难估计,而信号和噪声的方差和期望容易获得,文章论述了在知道信号和噪声的方差和期望情况下实现对退化图像复原的有约束最小平方复原方法的基本原理。并通过实验仿真证明约束最小平方复原在参数选择适当的情况下复原效果优于维纳滤波。
There are a lot of factors such as the phase difference of the optical system,the atmosphere turbulence,moving,diffusion of the focus and the system noise that degrade the digital images during their obtaining.In this paper,image restoration by using the inverse filter,Wiener filter,constrained least squares restoration theory is discussed.The Wiener filter to restore the image depends on the power spectrums of the image and noise,but actually the power spectrum of image and noise is difficult to estimate,so one discusses the constrained least squares restoration which can achieve restoration of degraded images with only the noise variance and mean.The simulation results show constrained least squares restoration is superior to Wiener filtering when the parameter select appropriately.
出处
《实验科学与技术》
2010年第5期21-23,69,共4页
Experiment Science and Technology
关键词
图像复原
维纳滤波
逆滤波
有约束最小平方复原
image restoration
wiener filter
inverse filtering
constrained least squares restoration