计算机工程 ›› 2008, Vol. 34 ›› Issue (14): 191-193.doi: 10.3969/j.issn.1000-3428.2008.14.068

• 人工智能及识别技术 • 上一篇    下一篇

一种基于颜色区域分割的图像修复算法

朱 霞1,李 宏1,张 卫2   

  1. (1. 中南大学信息科学与工程学院,长沙 410083;2. 湖南大学建筑学院,长沙 410082)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-07-20 发布日期:2008-07-20

Image Inpainting Algorithm Based on Color Region Segmentation

ZHU Xia1, LI Hong1, ZHANG Wei2   

  1. (1. School of Information Science and Engineering, Central South University, Changsha 410083; 2. College of Architecture, Hunan University, Changsha 410082 )
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-07-20 Published:2008-07-20

摘要: 现有的基于样本块纹理合成的数字图像修复技术在全局式搜索样本匹配块时可能选择错误的匹配块,导致繁衍错误信息而使修复结果不理想。该文提出一种基于颜色区域分割的图像修复方法,其目标匹配块的搜索限定在源样本块所覆盖的颜色区域中。实验结果表明这是一种更健壮、视觉效果更理想的修复算法,可以有效修复各种破损情况,尤其是具有复杂背景的较大区域填充。

关键词: 图像修复, 样本匹配, 颜色区域分割

Abstract: Using exemplar-based inpainting method to search the source patch globally may lead to error match, and such error accumulates and propagates to other areas quickly, even makes the results completely unacceptable. This paper introduces an algorithm for digital inpainting based on color region segmentation. Patch matching is restricted within the relevant regions where the current patch overlaps. Experimental results show that the method can efficiently handle different cases especially large regions in complex background by producing visually more plausible effect.

Key words: image inpainting, exemplars match, color region segmentation

中图分类号: