基于求解泊松方程和梯度的图像修复的研究  

Research on Image Completion by Solving Poisson Equation and Gradient

作　　者：杨勇[1] 汪继文[1] 

机构地区：[1]安徽大学计算机学院,安徽合肥230039

出　　处：《计算机技术与发展》2008年第2期98-100,103,共4页Computer Technology and Development

基　　金：安徽省自然科学研究项目(2006KJ028B)

摘　　要：提出了一种基于梯度的新的图像修复算法从图片或照片上面去除有影响的物体。文中的方法是分两个阶段来重建移除的区域:移除区域的梯度通过填充算法来填充;通过解泊松方程在梯度映射下来重构图像。在填充梯度的方法中提出了一个新的补丁匹配标准。在这个标准中,同时用到梯度和颜色信息,所以,有一个好的图像修复结果。文中用一些修复例子和结果进行比较,来演示本方法的优越性。Presents a novel gradient - based image completion algorithm for removing significant objects from natural images or photographs. The method reconstructs the region of removal in two phases. Firstly, the gradient maps in the removed area are completed through a patch based on filling algorithm. After that, the image is reconstructed from the gradient maps by solving a Poisson equation. A new patch - matching criterion is developed in approach to govern the completion of gradient maps. Both the gradient and the color informarion are incorporated in this new criterion, so a better image completion result is obtained. Several examples and comparisons are given at the end of the paper to demonstrate the performance of gradient- based image completion approach.

关 键 词：图像修复 梯度 填充顺序 泊松方程 补丁传播 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]