中山大学学报自然科学版 ›› 2012, Vol. 51 ›› Issue (1): 9-13.

• 研究论文 • 上一篇    下一篇

基于Navier-Stokes方程的图像修复算法

李率杰, 李 鹏,冯兆永,姚正安   

  1. (中山大学数学与计算科学学院,广东 广州 510275)
  • 收稿日期:2011-07-20 修回日期:1900-01-01 出版日期:2012-01-25 发布日期:2012-01-25
  • 通讯作者: 冯兆永

A New Algorithm for Image Inpainting Based on the NavierStokes Equation

LI Shuaijie, LI Peng,FENG Zhaoyong,YAO Zhengan   

  1. (School of Mathematics and Computational Science, Sun Yatsen University, Guangzhou 510275)
  • Received:2011-07-20 Revised:1900-01-01 Online:2012-01-25 Published:2012-01-25

摘要: 图像修复是一个基于周围未被损坏信息对图像中丢失或损坏信息进行修补的过程。提出了一个基于NavierStokes方程的新的图像修复算法。该算法能够同时在修复区域内部进行信息的填充,而在修复区域外部去除噪声(如果存在)。实验结果表明模型对于图像中划痕,信息丢失,甚至移除整个景物都是有效的。

关键词: 图像修复, 图像去噪, NavierStokes方程, 等照度线方向

Abstract: Image inpainting is the process of filling in missing parts of damaged images based on information gleaned from surrounding areas. A new algorithm for inpainting based on the NavierStokes equation, which allows for inpainting inside of the inpainting region and denoising outside of the inpainting region, is outlined. The experimental results show the effective performance of the proposed model in restoring scratched photos, missing parts and even removal of entire objects from images.

Key words: inpainting, denoising, NavierStokes equation, isophote direction

中图分类号: