改进的整体变分法在图像修复中的应用  

Improved total variation method for image inpainting

作　　者：周密[1] 彭进业[1] 赵健[1] 田艳艳[1] 史晶[1] 

机构地区：[1]西北大学信息科学与技术学院,西安710127

出　　处：《计算机工程与应用》2007年第27期88-90,共3页Computer Engineering and Applications

基　　金：国家部委基础研究项目;陕西省自然科学基金(the Natural Science Foundation of Shaanxi Province of China under Grant No.2006F42)

摘　　要：提出了一种改进的整体变分法并且将其应用于图像修复中。在修复的过程中考虑图像破损区域外部参考像素和待修补点的相关度,再利用图像破损区外部参考像素信息从破损区域的边缘逐步地向破损区域内部进行扩散,从而达到图像修复的目的。仿真试验表明,改进后的算法与原方法相比图像边缘过渡更加自然,修复效果得到改善。An improved image inpainting method based on the total variation algorithm is presented in this paper.The relativity coefficient is introduced according to the surrounding information of the damaged area.With the help of the relativity coefficient, we gradually diffuse the surrounding information to the damaged area and restore the damaged area.A range of experiments show that the new method is effective for the image inpainting,and the edge of the damaged area becomes more natural.

关 键 词：图像处理 图像修复 整体变分 相关度系数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]