Image Inpainting Under Local Coordinate System

  • Bo Li
  • Xiuping Liu
  • Dianxuan Gong
  • Qifeng Zhang
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 113)


This chapter focus on the regular texture inpainting problem under local coordinate system. General variational image inpainting models perform well for cartoon images, but poor for textures. In this paper, a novel local inpainting model is proposed by combining the total variation and OABE algorithm. Firstly, the local direction of texture is obtained according to the neighborhood of damaged region, the local coordinate is set up via the local texture direction and its normal direction; then the local variational inpainting model is proposed in this coordinate. We give the discrete Gauss–Seidel algorithm for this model and numerical experiments. The results show that our algorithm perform well for the regular texture images, even for textures like “Y”.


Inpainting Nonlocal total variation (NLTV) Discrete cosine transform 



This work is supported by the Project Sponsored by the Scientific Research Foundation (Nanchang Hangkong University), National Natural Science Foundation of China (No. 60873181).


  1. 1.
    Bertalmio M, Sapiro G, Caselles V, Ballester C (2000) Imageinpainting. Computer Graphics (SIGGRAPH July 2000)Google Scholar
  2. 2.
    Chan TF, Shen J (2001) Mathematical models forlocal non¡texture inpaintings. SIAM J Appl Math 62(3):1019–1043MathSciNetGoogle Scholar
  3. 3.
    Chan TF, Shen J (2002) Euler’s elastica and curvature based in paint. SIAM J Appl Math 63(2):564–592MATHMathSciNetGoogle Scholar
  4. 4.
    Criminisi A, Perez P, Toyama K (2003) Object removal by exemplar-based inpainting. IEEE Proc CVPR 2:721–728Google Scholar
  5. 5.
    Esedoglu S, Shen J (2002) Digital inpainting based on the Mumford-Shah-Euler image model. Eur J Appl Math 13:353–370Google Scholar
  6. 6.
    Bertalmio M, Vese L, Sapiro G, Osher S (2003) Simultaneous structure and texture image inpainting. IEEE Trans Image Process 12(8):882–889Google Scholar
  7. 7.
    Niu Y, Poston T (2005) Using an oriented PDE to repair image textures. VLSM, LNCS 3752, pp 61–72Google Scholar
  8. 8.
    Shao X, Liu Z, Song B (2004) An adaptive image inpainting approach based on TV model. J Circuits Syst 9:113–117Google Scholar
  9. 9.
    Yasuda M, Ohkubo J, Tanaka K (2005) Digital image inprinting based on Markov random field. IEEE CIMCA-IAWTIC, pp 245–249Google Scholar

Copyright information

© Springer Science+Business Media B.V. 2012

Authors and Affiliations

  • Bo Li
    • 1
  • Xiuping Liu
    • 2
  • Dianxuan Gong
    • 3
  • Qifeng Zhang
    • 1
  1. 1.College of Mathematics and Information ScienceNanchang Hangkong UniversityNanchangChina
  2. 2.School of Mathematical ScienceDalian University of TechnologyDalianChina
  3. 3.College of SciencesHebei United UniverstiyTangshanChina

Personalised recommendations