面向精准印刷体数学表达式识别的双分支网络
Dual Branch Network Towards Accurate Printed Mathematical Expression Recognition
AI总结：
针对卷积神经网络上下文信息不足导致的印刷体数学表达式识别误差问题，提出基于Transformer的双分支网络，结合上下文耦合模块与动态软目标策略，实现了当前最优的识别性能。
摘要：
近年来，印刷体数学表达式识别（Printed Mathematical Expression Recognition, PMER）发展迅速。然而，由于卷积神经网络捕获的上下文信息不足，部分数学符号可能被错误识别或遗漏。为解决该问题，本文提出一种基于Transformer的双分支网络（Dual Branch Network, DBN），通过学习局部与全局上下文信息实现精准PMER。在DBN中，局部与全局特征被同时提取，且本文设计了上下文耦合模块（Context Coupling Module, CCM）以实现全局与局部上下文间的特征互补。CCM采用交互模式，使耦合后的上下文线索与每个表达式符号高度相关。此外，本文设计了动态软目标（Dynamic Soft Target, DST）策略，利用符号类别间的相似性生成合理标签。实验结果表明，DBN能够精准识别数学表达式，达到了当前最优性能。
英文摘要：
Over the past years, Printed Mathematical Expression Recognition (PMER) has progressed rapidly. However, due to the insufficient context information captured by Convolutional Neural Networks, some mathematical symbols might be incorrectly recognized or missed. To tackle this problem, in this paper, a Dual Branch transformer-based Network (DBN) is proposed to learn both local and global context information for accurate PMER. In our DBN, local and global features are extracted simultaneously, and a Context Coupling Module (CCM) is developed to complement the features between the global and local contexts. CCM adopts an interactive manner so that the coupled context clues are highly correlated to each expression symbol. Additionally, we design a Dynamic Soft Target (DST) strategy to utilize the similarities among symbol categories for reasonable label generation. Our experimental results have demonstrated that DBN can accurately recognize mathematical expressions and has achieved state-of-the-art performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
