Stroke constrained attention network for online handwritten mathematical expression recognition

作者：

Highlights：

• A novel stroke constrained attention network for online HMER and online HCCR is proposed.

• The proposed method can be adopted in both single-modal and multi-modal cases.

• To the best of our knowledge, it achieves the state-of-the-art performance on CROHME 2014/2016/2019 testing sets.

• The proposed stroke-level representation greatly improves the recognition efficiency.

摘要

•A novel stroke constrained attention network for online HMER and online HCCR is proposed.•The proposed method can be adopted in both single-modal and multi-modal cases.•To the best of our knowledge, it achieves the state-of-the-art performance on CROHME 2014/2016/2019 testing sets.•The proposed stroke-level representation greatly improves the recognition efficiency.

论文关键词：Stroke-level information,Multi-modal fusion,Encoder-decoder,Attention mechanism,Handwritten mathematical expression recognition

论文评审过程：Received 19 February 2020, Revised 22 March 2021, Accepted 10 May 2021, Available online 25 May 2021, Version of Record 15 June 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108047