This paper presents our solution for the ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX. This competition has two sub-tasks: Table Structure Reconstruction (TSR) and Table Content Reconstruction (TCR). We treat both sub-tasks as two individual image-to-sequence recognition problems. We leverage our previously proposed algorithm MASTER \cite{lu2019master}, which is originally proposed for scene text recognition. We optimize the MASTER model from several perspectives: network structure, optimizer, normalization method, pre-trained model, resolution of input image, data augmentation, and model ensemble. Our method achieves 0.7444 Exact Match and 0.8765 Exact Match @95\% on the TSR task, and obtains 0.5586 Exact Match and 0.7386 Exact Match 95\% on the TCR task.

中文翻译：

---

平安VC集团为ICDAR 2021竞赛提供的乳胶科学表格图像识别解决方案

本文介绍了针对LaTeX的ICDAR 2021科学表格图像识别竞赛的解决方案。这项比赛有两个子任务：表结构重建（TSR）和表内容重建（TCR）。我们将这两个子任务视为两个单独的图像到序列识别问题。我们利用先前提出的算法MASTER \ cite {lu2019master}，该算法最初是为场景文本识别而提出的。我们从多个角度优化MASTER模型：网络结构，优化器，归一化方法，预训练模型，输入图像的分辨率，数据扩充和模型集成。我们的方法在TSR任务上达到0.7444精确匹配和0.8765精确匹配@ 95 \％，在TCR任务上获得0.5586精确匹配和0.7386精确匹配95 \％。