Script identification in natural scene image and video frames using an attention based Convolutional-LSTM network

作者：

Highlights：

• A new attention based CNN-LSTM network is proposed for script identification.

• It is based on local and global feature extraction and dynamically weighting them.

• Attention used twice to give priority to significant features and to focus on more relevant patches.

• The method has been tested on SIW-13, CVSI-2015, ICDAR-17 and MLe2e datasets.

摘要

•A new attention based CNN-LSTM network is proposed for script identification.•It is based on local and global feature extraction and dynamically weighting them.•Attention used twice to give priority to significant features and to focus on more relevant patches.•The method has been tested on SIW-13, CVSI-2015, ICDAR-17 and MLe2e datasets.

论文关键词：Script identification,Convolutional neural network,Long short-term memory,Local feature,Global feature,Attention network,Dynamic weighting

论文评审过程：Received 28 January 2018, Revised 23 May 2018, Accepted 22 July 2018, Available online 2 August 2018, Version of Record 23 August 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.07.034