Table 1 Classification metrics for different combinations of models.
Feature extractor | Classifier | Accuracy | Precision | Recall | F1-score |
---|---|---|---|---|---|
VGG16 | XGBoost | 0.87 | 0.86 | 0.86 | 0.85 |
MLP | 0.82 | 0.82 | 0.80 | 0.81 | |
RF | 0.81 | 0.81 | 0.80 | 0.80 | |
SVM | 0.74 | 0.76 | 0.73 | 0.72 | |
Inception V3 | SVM | 0.88 | 0.86 | 0.87 | 0.87 |
MLP | 0.79 | 0.79 | 0.79 | 0.78 | |
RF | 0.78 | 0.78 | 0.79 | 0.78 | |
XGBoost | 0.77 | 0.77 | 0.78 | 0.77 | |
ResNet50 | RF | 0.76 | 0.75 | 0.75 | 0.74 |
MLP | 0.75 | 0.75 | 0.74 | 0.73 | |
SVM | 0.70 | 0.70 | 0.69 | 0.68 | |
XGBoost | 0.70 | 0.69 | 0.69 | 0.68 |