An Efficient License Plate Detection Approach Using Lightweight Deep Convolutional Neural Networks

Table 4

Detection results on the RP subset of AOLP dataset.

Model	Feature extraction network	Input resolution	Detection ratio (%)	MFLOPs
Tiny-YOLO [2]	Tiny darknet	416 × 416	65.5	3490
YOLOv2 [2]	Darknet-19	416 × 416	81.8	17400
SSD-300 [3]	VGG-16	300 × 300	83.5	31750
R-FCN [4]	ResNet-50	600 × 1000	84.3	58900
Proposed method	ESPNetv2	320 × 320	99.35	5210