Table 6.
Recognition accuracy (EER) of a recognition system that uses only visible-light or thermal images for the recognition problem using SVM and CNN features without PCA (unit: %).
| SVM Kernel | Accuracies of Recognition Systems Using Single Image Types | |||||
|---|---|---|---|---|---|---|
| Using only Visible-Light Images | Using only Thermal Images | |||||
| EER | FAR | GAR | EER | FAR | GAR | |
| Linear | 17.379 | 10.000 | 72.541 | 16.560 | 10.000 | 73.228 |
| 15.000 | 80.085 | 15.000 | 81.392 | |||
| 17.380 | 82.622 | 16.580 | 83.460 | |||
| 20.00 | 85.239 | 20.00 | 87.361 | |||
| 25.00 | 88.618 | 25.00 | 91.471 | |||
| RBF | 17.379 | 10.000 | 72.565 | 16.510 | 10.000 | 73.082 |
| 15.000 | 80.058 | 15.000 | 81.471 | |||
| 17.400 | 82.642 | 16.520 | 83.500 | |||
| 20.00 | 85.055 | 20.00 | 87.475 | |||
| 25.00 | 88.604 | 25.00 | 91.577 | |||