Exemplar-based Image Inpainting using Structure Tesnor

DOI

10.2991/icacsei.2013.148How to use a DOI?

Keywords

Image inpainting, texture synthesis, exemplar, structure tensor, structural similarity (SSIM)

Abstract

Exemplar-based image inpainting techniques face two main problems. One is the decision of filling-in order which has a strong impact on image inpainting effect. Another problem is greedy search process while searching for the best exemplar patch. This paper presents a robust method for exemplar-based image inpainting based on structure tensor. The novel priority function is redefined. Experimentation results show that our image inpainting method improves the quality of image inpainting compared with the conventional exemplar-based image completion algorithms.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Kui Liu
AU  - Jie qing Tan
AU  - Ben yue Su
PY  - 2013/08
DA  - 2013/08
TI  - Exemplar-based Image Inpainting using Structure Tesnor
BT  - Proceedings of the 2013 International Conference on Advanced Computer Science and Electronics Information (ICACSEI 2013)
PB  - Atlantis Press
SP  - 619
EP  - 623
SN  - 1951-6851
UR  - https://doi.org/10.2991/icacsei.2013.148
DO  - 10.2991/icacsei.2013.148
ID  - Liu2013/08
ER  -