International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 91 - Number 2 |
Year of Publication: 2014 |
Authors: Ankita Bagul, Asha Bhalerao, Vaishali Dhage |
10.5120/15851-4749 |
Ankita Bagul, Asha Bhalerao, Vaishali Dhage . Video Inpainting. International Journal of Computer Applications. 91, 2 ( April 2014), 5-10. DOI=10.5120/15851-4749
Video inpainting or completion is a vital video improvement technique used to repair or editing of digital videos. In this paper, we are describing masking and nearest neighbor algorithm for repairing damaged frames in video films, focusing on maintaining good spatiotemporal continuity. Masking algorithm is used for detection of scratches or damaged portions in video frames. Nearest neighbor algorithm used for quickly finding approximate nearest neighbor matches between image patches. The given algorithm offers performance improvement, because of that anyone can use it in interactive editing tools. Video completion has been used all over the world to convert cultural artifacts such as vintage videos and films into digital form. However, such types of videos are usually very poor in quality and most of the time it contain unstable luminance and damaged content. Experiment on many frames of videos show the benefits of proposed approach which lead to natural looking videos with less annoying artifacts.