Research Article
High Order Volumetric Directional Pattern for Video-Based Face Recognition
Table 5
Recognition rates using all video frames as changing the threshold
and the proposed approach order on Honda/UCSD database.
| Descriptor | Recognition Accuracy (%) Using libsvm Classifier | Order | | | | | |
| Order (VDP) | 94.75 % | 95.09 % | 95.96 % | 95.82 % | 94.05 % |
| Order | 96.26 | 96.55 | 97.23 | 96.57 % | 95.74 % |
| Order | 95.08 % | 94.42 % | 96.23 % | 96.55 % | 95.32 % |
| Order | 95.57 % | 95.11 % | 96.72 % | 97.13 | 95.84 |
| Descriptor | Recognition Accuracy (%) Using knn Classifier | Order | | | | | |
| Order (VDP) | 96.13 % | 95.58 % | 96.87 % | 95.97 % | 95.44 % |
| Order | 96.52 | 96.87 | 97.08 | 96.61 | 96.23 |
| Order | 95.41 % | 95.95 % | 96.74 % | 96.44 % | 95.65 % |
| Order | 95.42 % | ā | 96.63 % | 96.51 % | 95.86 % |
|
|