[Retracted] Fast Recognition Method for Multiple Apple Targets in Complex Occlusion Environment Based on Improved YOLOv5

Table 3

Evaluation results of 5 algorithms under different occlusions.

Method	Precision/%	Recall/%	/%	Average image recognition time/s
Hog + SVM	73.50	75.34	74.4	0.296
Faster RCNN	81.06	80.32	80.69	0.255
YOLOv6	93.76	90.6	92.15	0.024
Baseline YOLOv5	90.23	88.76	89.49	0.036
Improved YOLOv5	94.64	92.89	93.76	0.026