运动模糊图像的去卷积方法研究

Study for deconvolution method of motion blurred images

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.