Research Article
Directional Correlation Filter Bank for Robust Head Pose Estimation and Face Recognition
Table 5
The recognition accuracy obtained by different methods for face recognition based on the three feature representations.
| Method | Features | Face Database | PIE | HPI | UMIST |
| CFA | Gray | 13.52% | 24.17% | 41.54% | HOG | 50.44% | 25.78% | 66.61% | Gabor | 31.99% | 28.10% | 34.68% |
| OTF+CFA | Gray | 55.75% | 50.00% | 61.05% | HOG | 60.23% | 53.73% | 84.23% | Gabor | 67.62% | 51.16% | 41.07% |
| DCFB+CFA | Gray | 27.80% | 61.14% | 61.83% | HOG | 60.72% | 57.86% | 92.73% | Gabor | 86.08 | 80.73 | 97.54 |
|
|