Table 5.
Performance comparison of models based on accuracy, precision, recall, and F1-score.
| Model | Accuracy | Precision | Recall | F1-score |
|---|---|---|---|---|
| VGG16 | 94.94% | 0.9428 | 0.9256 | 0.9331 |
| Resnet-50 | 99.45% | 0.9931 | 0.9919 | 0.9924 |
| Efficient Net-B0 | 99.69% | 0.9952 | 0.9950 | 0.9951 |
| DenseNet-121 | 99.76% | 0.9960 | 0.9969 | 0.9965 |
| MobileNet-V2 | 99.62% | 0.9946 | 0.9948 | 0.9947 |
| Inception-V3 | 99.73% | 0.9960 | 0.9959 | 0.9962 |
| Incpetion-ResnetV2 | 99.74% | 0.9959 | 0.9959 | 0.9960 |
| Xception | 99.70% | 0.9949 | 0.9957 | 0.9953 |
| Proposed CNN-SEEIB | 99.79% | 0.9970 | 0.9972 | 0.9971 |