Table 2. The tabular presentation of ML-CNN and VGGML-CNN performance evaluation Using accuracy and aggregate loss on BU-3DFE and CK+ datasets, and their comparison with some existing methods.
In the table, metric with ↑ indicates that the higher the metric value the better the model performance, and metric with ↓ indicates that the lower or smaller the value of the metric the better the model performance.
| ML-Models | Database | Accuracy ↑ | Aggregate loss ↓ |
|---|---|---|---|
| ML-CNN | BU-3DFE | 88.56 | 0.3534 |
| AUG_BU-3DFE | 92.84 | 0.1841 | |
| CK+ | 93.24 | 0.2513 | |
| VGGML-CNN | Bu-3DFE | 94.18 | 0.1723 |
| AUG_BU-3DFE | 98.01 | 0.1411 | |
| CK+ | 97.16 | 0.1842 | |
| Kamarol et al. (2017) | CK+ | 82.4 | NA |
| Walecki et al. (2015) | CK+ | 94.5 | NA |
| Quan, Qian & Ren (2014) | CK+ | 88.3 | NA |