Radical analysis network for learning hierarchies of Chinese characters

作者：

Highlights：

• A novel radical-based Chinese character/text recognition method is proposed.

• The proposed method has the capability of few-/zero-shot learning.

• The hierarchical radical structure of 27,533 Chinese characters is released.

• Achieved the first place on ICPR MTWI 2018 challenge.

摘要

•A novel radical-based Chinese character/text recognition method is proposed.•The proposed method has the capability of few-/zero-shot learning.•The hierarchical radical structure of 27,533 Chinese characters is released.•Achieved the first place on ICPR MTWI 2018 challenge.

论文关键词：Radical,Attention,Chinese character,Few-/zero-shot learning

论文评审过程：Received 12 July 2019, Revised 12 February 2020, Accepted 23 February 2020, Available online 28 February 2020, Version of Record 5 March 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107305