一种鲁棒的散焦模糊图像点扩散函数参数估计方法  

One Robust Parameter Estimation Method of Point Spread Function from Defocus Blurred Image

作　　者：梁敏[1] 徐彤阳[1] 张人上[1] LIANG Min(School of Information Management, Shanxi University of Finance and Economics, Taiyuan 030031, China)

机构地区：[1]山西财经大学信息管理学院,太原030031

出　　处：《长春工程学院学报（自然科学版）》2016年第1期109-113,118,共6页Journal of Changchun Institute of Technology：Natural Sciences Edition

基　　金：山西财经大学青年科研基金项目(QN-2014028);山西省哲学社会科学"十二五"规划2015年度课题(2015.10)

摘　　要：提出了一种具有较强抗噪能力的频率域鉴别散焦模糊参数的方法。该方法对模糊图像对数频谱图实施极坐标变换,然后计算距频谱中心不同半径下的多方向幅值累加和函数,进而提取第一过零圆环的半径,完成散焦模糊参数的估计。实验结果表明,该方法能够适应带噪散焦模糊图像退化模型的参数估计问题,且具有较高的鉴别精度。A robust parameter estimation method from defocus blurred image in frequency domain is proposed in this article.First,polar transformation is applied to the logarithmic power spectrum of the defocus image in the frequency domain.Then the defocus blur radius can be obtained by calculating the sum of the logarithmic spectrum along concentric circles in the polar coordinate.The experiment results show that the proposed method can adapt to parameter estimation for deteriorate model with Gaussian noise blurred images and has high identifying accuracy.

关 键 词：散焦模糊 图像复原 点扩散函数 参数估计 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]