Table 1 Precision, Recall, and F1-score values of the detection and identification results of different networks.
From: Detection and identification of tea leaf diseases based on AX-RetinaNet
Network | Augmentation | Precision (%) | Recall (%) | F1-score |
|---|---|---|---|---|
SSD33 | No | 89.5 | 83.75 | 0.865 |
Yes | 87 | 90 | 0.885 | |
RetinaNet | No | 89.5 | 83.75 | 0.865 |
Yes | 95.5 | 90 | 0.927 | |
Yolo V3 | No | 92 | 69 | 0.789 |
Yes | 75.25 | 91.5 | 0.825 | |
Yolo V4 | No | 97.5 | 71.75 | 0.827 |
Yes | 96.75 | 80 | 0.876 | |
Centernet34 | No | 98.75 | 57 | 0.723 |
Yes | 99.50 | 79.5 | 0.884 | |
M2det | No | 88.75 | 77.5 | 0.827 |
Yes | 93.5 | 86 | 0.896 | |
EfficientNet35 | No | 94.5 | 81.25 | 0.873 |
Yes | 98.25 | 84.25 | 0.907 | |
AX-RetinaNet | No | 91.25 | 86.75 | 0.889 |
Yes | 96.75 | 94 | 0.954 |
