Recognizing the Damaged Surface Parts of Cars in the Real Scene Using a Deep Learning Framework

Table 2

Quantitative comparison between the proposed model and eight other models based on recall, precision, and IoU for detecting different parts of a car.

Architecture	Precision (%)	Recall (%)	IoU
PANet [42]	86	85	0.78
Combined feature(YOLOv3) [43]	66	62	0.61
VGG models [1]	64	62	0.60
FCOMB [12]	56	58	0.55
Improved mask RCNN [44]	69	72	0.64
Mask RCNN [45]	65	70	0.69
HTC [46]	83	84	0.76
Texture descriptor [8]	87	86	0.80
Proposed method	89	92	0.85