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

Table 1

Quantitative assessment based on recall, precision, and IoU for detecting different parts of a car.

Parts	Precision (%)	Recall (%)	IoU
Windshield	91	94	0.89
Trunk lid	88	92	0.87
Roof	87	89	0.86
Front bumper	88	90	0.83
Rear bumper	87	91	0.81
Front doors	92	92	0.90
Back doors	87	90	0.86
Quarters	87	90	0.85
Fenders	93	95	0.86
Hood	90	93	0.82