Table 4.

Recognition results after applying candidate optimization algorithm.

	ResNet-50			ResNet-101
	Original	ωc = 0.8 ωp = 0.2	ωc = 0.5 ωp = 0.5	Original	ωc = 0.8 ωp = 0.2	ωc = 0.5 ωp = 0.5
Precision	0.942	0.975	0.971	0.964	0.988	0.977
Recall	0.990	0.978	0.980	0.993	0.978	0.989
F1 Score	0.965	0.976	0.975	0.978	0.983	0.983

Bold values indicate the best results in that particular row (particular section).