[Retracted] Study on Automatic Multi-Classification of Spine Based on Deep Learning and Postoperative Infection Screening

Table 4

Accuracy and statistics of different methods.

Traditional classifier	Method	Validation set accuracy	Test set accuracy
1-NN	LBP	49.4 2.1	51.8 2.5	0.712
	LPQ	63.5 2.7	53.7 2.7	0.517
	GLCM	65.3 1.7	53.6 1.6	0.725
	ORB	66.1 3.5	63.7 3.4	0.764
	HOG	51.7 1.3	61.3 0.7	0.768
ELM	LBP	69.4 1.0	51.3 2.1	0.742
	LPQ	61.6 1.8	57.6 2.3	0.76
	GLCM	73.3 2.9	57.3 3.0	0.786
	ORB	67.2 1.9	65.4 3.8	0.73
	HOG	63.5 2.7	61.4 1.8	0.697