空域中基于正则化技术的有效图像复原算法  

An Effective Image Restoration Algorithm Based on Regularization in Spatial Domain

作　　者：苗晴[1] 唐斌兵[1] 周海银[1] 

机构地区：[1]国防科技大学数学与系统科学系,湖南长沙410073

出　　处：《系统工程》2005年第11期91-94,共4页Systems Engineering

基　　金：国家自然科学基金资助项目(60272013);全国优秀博士论文专项基金资助项目(200140);国防预研基金资助项目(51421030901KG01)

摘　　要：针对模糊图像的复原问题,在正则化技术解决病态性基础上提出了一种有效的空间域图像复原算法。该方法对正则项进行空间自适应加权从而局部地控制图像的平滑性,并用共轭梯度运算来改善算法的收敛性。计算机仿真结果表明,该方法很好地再现了原图像的重要信息,复原图像在峰值信噪比和主观视觉效果方面都有显著的提高。Aiming at the restoration of blurred image, an effective approach to image restoration in spatial domain is proposed based on regularization technique for dealing with ill-posed problems. In this paper, the smoothness of image is locally controlled by an adaptive weight matrix included in the regularization item, and the convergence is improved by conjugate gradient method. Computer simulations show that this proposed approach can properly retrieve the main information of original image, and the PSNR （peak signal to noise ratio） and subjective effect of the restored image are improved significandy.

关 键 词：图像复原 正则化 自适应加权 共轭梯度 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]