用图神经网络识别手写公式结构，提升准确率。
Link prediction Graph Neural Networks for structure recognition of Handwritten Mathematical Expressions
- 将符号和空间关系建模为图，用GNN预测连接关系。
- 在HME-RS数据集上达到91.2%的结构识别准确率。
- 适合手写公式识别、数学内容理解等场景。
我们提出一种基于图神经网络（GNN）的手写数学表达式（HME）识别方法，将HME表示为图结构，节点代表符号，边捕捉空间依赖关系。通过深度双向LSTM网络实现符号分割、识别及空间关系分类，构建初始原始图。随后使用二维上下文无关文法（2D-CFG）解析器生成所有可能的空间关系，GNN-based链接预测模型则通过去除冗余连接来优化结构，最终形成符号标签图。实验表明，该方法在HME结构识别任务中表现优异，于HME-RS数据集上取得91.2%的准确率。
原文摘要 · Abstract (English)
We propose a Graph Neural Network (GNN)-based approach for Handwritten Mathematical Expression (HME) recognition by modeling HMEs as graphs, where nodes represent symbols and edges capture spatial dependencies. A deep BLSTM network is used for symbol segmentation, recognition, and spatial relation classification, forming an initial primitive graph. A 2D-CFG parser then generates all possible spatial relations, while the GNN-based link prediction model refines the structure by removing unnecessary connections, ultimately forming the Symbol Label Graph. Experimental results demonstrate the effectiveness of our approach, showing promising performance in HME structure recognition.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。