arrow
Volume 4, Issue 6
Two-Phase Image Inpainting: Combine Edge-Fitting with PDE Inpainting

Meiqing Wang, Chensi Huang, Chao Zeng & Choi-Hong Lai

Adv. Appl. Math. Mech., 4 (2012), pp. 769-779.

Published online: 2012-12

Export citation
  • Abstract

The digital image inpainting technology based on partial differential equations (PDEs) has become an intensive research topic over the last few years due to the mature theory and prolific numerical algorithms of PDEs. However, PDE based models are not effective when used to inpaint large missing areas of images, such as that produced by object removal. To overcome this problem, in this paper, a two-phase image inpainting method is proposed. First, some edges which cross the damaged regions are located and the missing parts of these edges are fitted by using the cubic spline interpolation. These fitted edges partition the damaged regions into some smaller damaged regions. Then these smaller regions may be inpainted by using classical PDE models. Experiment results show that the inpainting results by using the proposed method are better than those of BSCB model and TV model.

  • AMS Subject Headings

65M10, 78A48

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{AAMM-4-769, author = {Wang , MeiqingHuang , ChensiZeng , Chao and Lai , Choi-Hong}, title = {Two-Phase Image Inpainting: Combine Edge-Fitting with PDE Inpainting}, journal = {Advances in Applied Mathematics and Mechanics}, year = {2012}, volume = {4}, number = {6}, pages = {769--779}, abstract = {

The digital image inpainting technology based on partial differential equations (PDEs) has become an intensive research topic over the last few years due to the mature theory and prolific numerical algorithms of PDEs. However, PDE based models are not effective when used to inpaint large missing areas of images, such as that produced by object removal. To overcome this problem, in this paper, a two-phase image inpainting method is proposed. First, some edges which cross the damaged regions are located and the missing parts of these edges are fitted by using the cubic spline interpolation. These fitted edges partition the damaged regions into some smaller damaged regions. Then these smaller regions may be inpainted by using classical PDE models. Experiment results show that the inpainting results by using the proposed method are better than those of BSCB model and TV model.

}, issn = {2075-1354}, doi = {https://doi.org/10.4208/aamm.12-12S08}, url = {http://global-sci.org/intro/article_detail/aamm/148.html} }
TY - JOUR T1 - Two-Phase Image Inpainting: Combine Edge-Fitting with PDE Inpainting AU - Wang , Meiqing AU - Huang , Chensi AU - Zeng , Chao AU - Lai , Choi-Hong JO - Advances in Applied Mathematics and Mechanics VL - 6 SP - 769 EP - 779 PY - 2012 DA - 2012/12 SN - 4 DO - http://doi.org/10.4208/aamm.12-12S08 UR - https://global-sci.org/intro/article_detail/aamm/148.html KW - Image inpainting, partial differential equations, edge fitting. AB -

The digital image inpainting technology based on partial differential equations (PDEs) has become an intensive research topic over the last few years due to the mature theory and prolific numerical algorithms of PDEs. However, PDE based models are not effective when used to inpaint large missing areas of images, such as that produced by object removal. To overcome this problem, in this paper, a two-phase image inpainting method is proposed. First, some edges which cross the damaged regions are located and the missing parts of these edges are fitted by using the cubic spline interpolation. These fitted edges partition the damaged regions into some smaller damaged regions. Then these smaller regions may be inpainted by using classical PDE models. Experiment results show that the inpainting results by using the proposed method are better than those of BSCB model and TV model.

Wang , MeiqingHuang , ChensiZeng , Chao and Lai , Choi-Hong. (2012). Two-Phase Image Inpainting: Combine Edge-Fitting with PDE Inpainting. Advances in Applied Mathematics and Mechanics. 4 (6). 769-779. doi:10.4208/aamm.12-12S08
Copy to clipboard
The citation has been copied to your clipboard