High Frequency Component Compensation based Super-Resolution Algorithm for Face Video Enhancement

  • Authors:

  • Junwen Wu;Mohan Trivedi;Bhaskar Rao

  • Affiliations:

  • UC San Diego, La Jolla;UC San Diego, La Jolla;UC San Diego, La Jolla

  • Venue:
  • ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper proposes a video-based high-frequency component compensation (HFCC) super-resolution algorithm. The lost high-frequency information is estimated by local MAP criteria, using the registered frames. By compensating the high frequency component iteratively, the high-resolution images are recovered. The algorithm has lower computational cost than the alternatives. Experimental evaluation verified the usefulness of the algorithm.