Matching based ground-truth annotation for online handwritten mathematical expressions

作者：

Highlights：

• A method for annotating ground-truth data to handwritten mathematical expressions.

• Expression matching formulated as a single assignment problem.

• Evaluation of the influence of local (symbol) and global (structural) features on matching performance.

• Overall mean symbol assignment rate above 99%.

摘要

Highlights•A method for annotating ground-truth data to handwritten mathematical expressions.•Expression matching formulated as a single assignment problem.•Evaluation of the influence of local (symbol) and global (structural) features on matching performance.•Overall mean symbol assignment rate above 99%.

论文关键词：Structural pattern analysis,Shape information,Handwriting recognition,Linear assignment problem,Ground-truth annotation,Mathematical expression dataset

论文评审过程：Received 25 September 2013, Revised 8 September 2014, Accepted 18 September 2014, Available online 28 September 2014.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.09.015