Table 3.

Comparative result of precision, recall, and accuracy using proposed MAR-ERNN and Existing DL-based feature detector [1], Partitioned Deep CNN [2], DeTrAs [3], and Faster-RCNN [4]

Methods	Parameters
	Precision	Recall	Accuracy
MAR-ERNN	97.85	95.55	98.35
DL- based feature detector [1]	97.00	90.15	98.00
Partitioned Deep CNN [2]	97.50	93.5	96.30
DeTrAs [3]	95.15	88.25	88.63
Faster-RCNN [4]	93.00	85.00	98.00