Table 5.

Performance comparisons of our proposed and the second-best baseline method [10] using both retrieval methods.

Method	With class prediction					Without class prediction
	Accuracy, %	F1, %	mAPa, %	mARb, %	Accuracy, %		F1, %	mAP, %	mAR, %
Owais et al [10]	92.57	93.41	94.58	92.28	93.18		94.02	94.68	93.38
Proposed	96.19	96.99	98.18	95.86	96.13		96.94	98.04	95.89

^amAP: mean average precision.

^bmAR: mean average recall.