基于空间自适应和正则化技术的盲目图像复原

在原非负支撑域递归逆滤波（NAS-RIF）算法基础上，本文提出一种基于空间自适应和正则化技术的改进算法。在代价函数中，引入两项空间自适应的加权项，分别用来确保图像复原的逼真和平滑，自适应加权项需根据观察图像的局部特性和噪声方差求得。并加入正则化项，以达到抑制噪声的目的。本文提出了根据观察图像来估计噪声方差的方法，因而不需要知道噪声方差的先验条件。在求解中，采用共轭梯度算法来进行求解。对不同背景和不同信噪比的图像进行了仿真实验。结果表明：改进后的算法比原来的算法复原效果更好。

Blind Image Restoration Algorithm Based on Space-adaptive and Regularization

Based on original nonnegativity and support constrains recursive inverse filtering (NAS-RIF) algorithm, an improved algorithm is proposed in this paper. In order to control the trade-off between fidelity to the observed image and smoothness of the restored image and to prevent noise amplification, a newly cost function of the NAS-RIF algorithm can be obtained by adding space-adaptive terms and a regularization term. The space-adaptive terms can be calculated through the local properties of the observed image and the noise variance. An estimating method of noise variance is also proposed in this paper. This improved algorithm uses conjugate-gradient routine to calculate the optimal result. The experimental results show that the improved NAS-RIF algorithm provides a better restoration result.