| Title | Highly efficient local non-texture Image inpainting based on partial differential equation |
| Authors | Zhu, Chuang Jia, Huizhu Li, Meng Huang, Xiaofeng Xie, Xiaodong |
| Affiliation | School of Electronics Engineering and Computer Science, Peking University, Beijing, China |
| Issue Date | 2015 |
| Citation | 17th IEEE International Conference on Computational Science and Engineering, CSE 2014 - Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms,.C |
| Abstract | Image inpainting has been a popular study point in recent years and a number of strategies have been developed. Partial differential equation (PDE) image inpainting approach often acts as a fundamental building block in this area. However, the high computing load limits the application of PDE-based image inpainting, especially in mobile terminal. In this paper, first an enhanced Curvature-Driven Diffusions (ECDD) model is proposed to improve the repairing performance. Then a fast local non-texture inpainting scheme is performed based on ECDD and total variation (TV) to make the computing of the PDE-based image inpainting more efficient. The experimental results show that the proposed strategy not only can repair the long disconnected objects more accurately, but also can greatly shorten the iteration time of image inpainting. ? 2014 IEEE. |
| URI | http://hdl.handle.net/20.500.11897/294722 |
| ISSN | 9781479979813 |
| DOI | 10.1109/CSE.2014.164 |
| Indexed | EI |
| Appears in Collections: | 信息科学技术学院 |
