Table 4 Performance comparison of ensemble combinations (Top-2, Top-3, Top-4 Models).
From: Deep learning-based automatic diagnosis of rice leaf diseases using ensemble CNN models
Ensemble Configuration | Accuracy (%) | Precision (%) | Recall (%) | F1-Score (%) | MCC |
|---|---|---|---|---|---|
GoogLeNet + DenseNet-121 | 95.61 | 95.20 | 94.80 | 94.95 | 0.932 |
GoogLeNet + DenseNet-121 + VGG16 | 96.78 | 96.45 | 96.10 | 96.27 | 0.948 |
GoogLeNet + DenseNet-121 + VGG16 + ResNet-34 | 97.21 | 96.80 | 96.75 | 96.77 | 0.956 |
