Detection of Apple Lesions in Orchards Based on Deep Learning Methods of CycleGAN and YOLOV3-Dense

Table 5

Detection results of three detection models on test set images.

Model	Manual annotation	Faster R-CNN with VGG16 NET	YOLO-V3	YOLOV3-dense
Number of detected lesions	219	168	185	194
Number of missed lesions	0	51	34	25
Number of wrong lesions	0	17	12	9