运动模糊图像的去卷积方法研究  

Study for deconvolution method of motion blurred images

作　　者：陈以超[1] 洪汉玉[1] 张艳[1] 

机构地区：[1]武汉工程大学机械工程学院,湖北武汉430074

出　　处：《武汉工程大学学报》2007年第1期68-70,共3页Journal of Wuhan Institute of Technology

基　　金：国家自然科学基金项目(60572040);湖北省教育厅科学技术研究项目(D200615001)

摘　　要：针对成像过程中观测图像存在像素灰度信息丢失的情况,在分析此类图像的退化原理及建立其数学模型和离散化表达式的基础上,将最优化方法中的共轭梯度法引入图像复原过程中,提出基于共轭梯度优化迭代的非零背景运动模糊图像去卷积方法.实验表明,该算法复原效果良好,是一种有效的图像复原方法.On the condition of the missing pixel information of the observed image during the process of imaging, based on the analysis of the degradation principle and establishment of the math model as well as discrete expression, this paper incorporates optimization method into the process of blur image restoration and proposes the deconvolution methods of non - zero background motion blurred image based on conjugate gradient optimization iteration. The experiment indicates that the result restores well with the proposed algorithm and it is a kind of effective method to restore motion blurred images.

关 键 词：运动模糊 模糊函数 去卷积 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]