Recognizing online handwritten Chinese characters using RNNs with new computing architectures

作者：

Highlights：

• We propose a new RNN based recognizer for online handwritten character.

• In the RNN system, two new computing architectures are proposed.

• One is variance constraint, and the other is attention weight vector.

• The system performance is improved by using the two innovations.

摘要

•We propose a new RNN based recognizer for online handwritten character.•In the RNN system, two new computing architectures are proposed.•One is variance constraint, and the other is attention weight vector.•The system performance is improved by using the two innovations.

论文关键词：Online handwritten Chinese character recognition,Recurrent neural network,New computing architectures

论文评审过程：Received 21 August 2018, Revised 30 March 2019, Accepted 13 April 2019, Available online 13 April 2019, Version of Record 30 April 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.04.015