Reading car license plates using deep neural networks

作者：

Highlights：

• We propose a cascade using multiple CNN classifiers for detection and recognition.

• Our method reads text without character segmentation, based on recurrent networks.

• Our method achieves impressive performance on public car license datasets.

摘要

•We propose a cascade using multiple CNN classifiers for detection and recognition.•Our method reads text without character segmentation, based on recurrent networks.•Our method achieves impressive performance on public car license datasets.

论文关键词：Car plate detection and recognition,Convolutional neural networks,Recurrent neural networks,LSTM

论文评审过程：Received 20 December 2016, Revised 21 February 2018, Accepted 27 February 2018, Available online 6 March 2018, Version of Record 21 March 2018.

论文官网地址：https://doi.org/10.1016/j.imavis.2018.02.002