LPRNet: License Plate Recognition via Deep Neural Networks

TL;DR

LPRNet is a real-time, end-to-end deep neural network system for license plate recognition that achieves high accuracy without character segmentation or RNNs, suitable for embedded applications.

Contribution

It introduces LPRNet, the first real-time license plate recognition system without RNNs, capable of high accuracy on Chinese plates in embedded environments.

Findings

Achieves up to 95% accuracy on Chinese license plates

Operates in real-time at 3 ms/plate on GPU and 1.3 ms/plate on CPU

Does not require character segmentation or RNNs

Abstract

This paper proposes LPRNet - end-to-end method for Automatic License Plate Recognition without preliminary character segmentation. Our approach is inspired by recent breakthroughs in Deep Neural Networks, and works in real-time with recognition accuracy up to 95% for Chinese license plates: 3 ms/plate on nVIDIA GeForce GTX 1080 and 1.3 ms/plate on Intel Core i7-6700K CPU. LPRNet consists of the lightweight Convolutional Neural Network, so it can be trained in end-to-end way. To the best of our knowledge, LPRNet is the first real-time License Plate Recognition system that does not use RNNs. As a result, the LPRNet algorithm may be used to create embedded solutions for LPR that feature high level accuracy even on challenging Chinese license plates.