Abstract | ||
---|---|---|
In this paper we present a super-resolution scheme specifica lly designed for faces. First, a face detector is used to find faces in a video fr ame, after which an optical flow algorithm is applied to track feature points o n the faces. Given the set of flow vectors corresponding to a single face, we prop ose to use the epipolar geometry for rejecting outlying flow vectors. This will improve the registration of the face over multiple frames, and thus lead to an improved super-resolution image. An iterative backprojection method is used for ac- quiring the super-resolution images. |
Year | Venue | Keywords |
---|---|---|
2007 | BMVC | electronics,optical flow,epipolar geometry,super resolution |
Field | DocType | Citations |
Computer vision,Epipolar geometry,Computer graphics (images),Computer science,Electronics,Artificial intelligence,Detector,Optical flow,Superresolution | Conference | 2 |
PageRank | References | Authors |
0.41 | 7 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Richard J. M. den Hollander | 1 | 26 | 4.21 |
Dirk-Jan J. de Lange | 2 | 12 | 1.08 |
Klamer Schutte | 3 | 173 | 18.26 |