A two-stage deep neural network for multi-norm license plate detection and recognition

作者：

Highlights：

• A two-stage multi-norm LP detection and recognition system is proposed.

• A semi-automatic annotation procedure of LP images is proposed.

• A new public multi-norm LP images dataset is provided freely for research purpose.

• The proposed system is robust and efficient in real-time applications.

摘要

•A two-stage multi-norm LP detection and recognition system is proposed.•A semi-automatic annotation procedure of LP images is proposed.•A new public multi-norm LP images dataset is provided freely for research purpose.•The proposed system is robust and efficient in real-time applications.

论文关键词：License plate detection and recognition,Semi-automatic annotation,Convolutional neural networks,Recurrent neural networks,YOLO,Deep learning

论文评审过程：Received 2 March 2019, Revised 26 May 2019, Accepted 16 June 2019, Available online 18 June 2019, Version of Record 24 June 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.06.036