Global Context for improving recognition of Online Handwritten Mathematical Expressions
Global Context for improving recognition of Online Handwritten Mathematical Expressions
复制标题
DOI：
10.1007/978-3-030-86331-9_40
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
C. Nguyen;Thanh-Nghia Truong;Hung Tuan Nguyen;M. Nakagawa
中科院分区：
文献类型：
--
作者：
C. Nguyen;Thanh-Nghia Truong;Hung Tuan Nguyen;M. Nakagawa
本文提出了一种用于在线手写数学表达式（HME）中符号分割、符号识别和关系分类这三个子任务的时间分类方法。分类模型通过从 HME 的符号关系树 (SRT) 表示导出的符号和空间关系的多个路径进行训练。该方法受益于深度双向长短期记忆网络的全局上下文，该网络通过连接主义时间分类损失直接从在线手写学习时间分类。为了识别在线 HME，构建了具有上下文无关语法的符号级解析树，其中从时间分类结果中获得符号和空间关系。我们在两个最新的 CROHME 数据集上展示了所提出方法的有效性。
This paper presents a temporal classification method for all three subtasks of symbol segmentation, symbol recognition and relation classification in online handwritten mathematical expressions (HMEs). The classification model is trained by multiple paths of symbols and spatial relations derived from the Symbol Relation Tree (SRT) representation of HMEs. The method benefits from global context of a deep bidirectional Long Short-term Memory network, which learns the temporal classification directly from online handwriting by the Connectionist Temporal Classification loss. To recognize an online HME, a symbol-level parse tree with Context-Free Grammar is constructed, where symbols and spatial relations are obtained from the temporal classification results. We show the effectiveness of the proposed method on the two latest CROHME datasets.