计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (6): 185-187.DOI: 10.3778/j.issn.1002-8331.2010.06.054

• 图形、图像、模式识别 • 上一篇    下一篇

引入蛇模型的曲率驱动扩散图像修复方法

吴亚娟1,2,刘晓锋2   

  1. 1.四川大学 计算机学院,成都 610065
    2.西华师范大学 计算机学院,四川 南充 637002
  • 收稿日期:2009-10-26 修回日期:2009-12-21 出版日期:2010-02-21 发布日期:2010-02-21
  • 通讯作者: 吴亚娟

Image inpainting by curvature-driven diffusions with snake model

WU Ya-juan1,2,LIU Xiao-feng2   

  1. 1.College of Computer Science,Sichuan University,Chengdu 610065,China
    2.College of Computer Science,China West Normal University,Nanchong,Sichuan 637002,China
  • Received:2009-10-26 Revised:2009-12-21 Online:2010-02-21 Published:2010-02-21
  • Contact: WU Ya-juan

摘要: 数字图像修复方法可以自动地修复数字图像中用户定义的污损区域。T.F.Chan等人提出的非纹理的曲率驱动扩散算法是基于偏微分方程的图像修复的代表算法之一。通过在该算法中应用蛇模型的图像增强项,提出了引入蛇模型的曲率驱动扩散图像修复方法,在热扩散过程中,拉动曲线向目标边界演化,达到修复污损图像中的断裂边缘的目的,从而较好保持图像的视觉连通性。实验结果表明,在迭代次数相同的条件下,可以比原始的曲率驱动扩散图像修复算法获得更好的修复效果。

关键词: 图像修复, 曲率, 蛇模型, 图像增强项

Abstract: Digital image inpainting approaches can restore the damaged region automatically on digital images.T.F.Chan,et al.bring up an inpainting algorithm by Curvature-Driven Diffusions(CDD) which is a representative algorithm based on partial differential equation.In the inpainting algorithm,image enhancement term of snake model is incorporated into CDD algorithm.In the heat diffusion process,this term attracts the boundaries of the objects,so the broken boundaries can be repaired.Thus the image visual connectivity is holding effectively.As the experimental results show,it can repair the damaged image better than CDD algorithm with same iterative times.

Key words: image inpainting, curvature, snake model, image enhancement term

中图分类号: