| Super-resolution inpainting |
| |
| 作者姓名： | SHIHTimothyK. CHANGRong-chi |
| |
| 作者单位： | Department of |
| |
| 摘 要： | INTRODUCTION Video sequences can be interfered with by noise.When the noise ratio of a video is high,even though itis not possible to restore the original,to repair videoframes or damaged artifacts with visually good resultis a hopefully achievable goal(see example in Fig.3),especially for archival resources in digital museumprojects.One of the simplest but efficient mecha-nisms is presented in(Oliveira et al.,2001).The dif-fusion kernel can repair damages of small area with abarrier to …
|
| 关 键 词： | 图象通信 图象处理 视频序列 噪音处理 数字技术 |
| 收稿时间： | 20 April 2005 |
| 修稿时间： | 30 April 2005 |
Super-resolution inpainting |
| |
| SHIHTimothyK. CHANGRong-chi.Super-resolution inpainting[J].Journal of Zhejiang University Science,2005,6(6):487-491. |
| |
| Authors: | Shih Timothy K Chang Rong-chi |
| |
| Institution: | (1) Department of Computer Science and Information Engineering, Tamkang University, 25137 Taipei, Taiwan, China |
| |
| Abstract: | Image or video resources are often received in poor condition, mostly with noise or defects making the resources hard to read. We propose an effective algorithm based on digital image inpainting. The mechanism can be used in restoring images or video frames with very high noise or defect ratio (e.g., 90%). The algorithm is based on the concept of image subdivision and estimation of color variations. Noises inside blocks of different sizes are inpainted with different levels of surrounding information.The results showed that an almost unrecognizable image can be recovered with visually good result. The algorithm can be further extended for processing motion picture with high percentage of noise. |
| |
| Keywords: | Image inpainting Super resolution Image processing |
| 本文献已被 CNKI 维普 万方数据 SpringerLink 等数据库收录！ |
