Research Article
[Retracted] Fast Recognition Method for Multiple Apple Targets in Complex Occlusion Environment Based on Improved YOLOv5
Table 2
Evaluation results of 5 algorithms under different lighting angles.
| Method | Precision/% | Recall/% | /% | Average image recognition time/s |
| Hog + SVM | 82.23 | 79.85 | 81.5 | 0.296 | Faster RCNN | 91.76 | 86.34 | 88.96 | 0.255 | YOLOv6 | 94.81 | 92.65 | 93.71 | 0.024 | Baseline YOLOv5 | 90.54 | 92.16 | 91.34 | 0.032 | Improved YOLOv5 | 96.35 | 94.6 | 94.21 | 0.026 |
|
|