Abstract | ||
---|---|---|
Old age, repeat play and improper preservation always deteriorate the film, and dust and mechanical operations produce artifacts like scratches and blotches. Many researches carried out to repair the damaged digital videos and video inpainting gradually becomes an important topic in digital image process ing. Challenges in scratched video inpainting are automatic detection of scratches and restoration of damaged part. This paper presents an automatic scratch detec tion method as well as a novel scratch removal approach. Stationary wavelet transform (SWT) which shows excellent performance in keeping translation-invariant is introduced to automatically detect the scratches, this strategy makes the scratches' detection more accurate. At the heart of our method is a new nonlinear interpolation method based on continued fraction in which Thiele-type continued fraction is used to interpolate surrounding known pixels for repairing the damaged part. Algorithm presented in this paper also utilizes both spatial and temporal information of the scratched video during the restoration stage. Experimental results show that our scheme not only obtains more accurate detection of scratches, but also gives better video quality. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1007/s11042-013-1523-8 | Multimedia Tools and Applications |
Keywords | Field | DocType |
Video inpainting,Scratch detection,Continued fraction,Non-linear interpolation | Computer vision,Scratch,Nonlinear interpolation,Pattern recognition,Computer science,Interpolation,Digital image,Inpainting,Artificial intelligence,Pixel,Stationary wavelet transform,Video quality | Journal |
Volume | Issue | ISSN |
71 | 2 | 1380-7501 |
Citations | PageRank | References |
1 | 0.35 | 18 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xing Huo | 1 | 1 | 0.69 |
Jieqing Tan | 2 | 130 | 28.88 |
Lei He | 3 | 21 | 4.75 |
Min Hu | 4 | 31 | 12.64 |