计算机工程与应用 ›› 2022, Vol. 58 ›› Issue (22): 1-11.DOI: 10.3778/j.issn.1002-8331.2206-0337

• 热点与综述 • 上一篇    下一篇

表格检测与结构识别综述

张宇童,李启元,刘树衎   

  1. 1.中国人民解放军海军工程大学 电子工程学院,武汉 430033
    2.东南大学 计算机科学与工程学院,南京 211102
  • 出版日期:2022-11-15 发布日期:2022-11-15

Overview of Table Detection and Structure Recognition

ZHANG Yutong, LI Qiyuan, LIU Shukan   

  1. 1.School of Electronic Engineering, Naval University of Engineering, PLA, Wuhan 430033, China
    2.School of Computer Science and Engineering, Southeast University, Nanjing 211102, China
  • Online:2022-11-15 Published:2022-11-15

摘要: 针对当前文档分析领域中表格分析的发展现状,整理了近年来领域内的相关文献,分别对表格检测和表格结构识别两个关键任务进行研究。针对表格检测任务,将其划分为基于目标检测、图神经网络、生成对抗网络、可变卷积网络的方法;针对表格结构识别任务,将其划分为基于目标检测、图神经网络、循环神经网络、可变卷积与扩张卷积网络的方法。总结了各类模型的方法路径和局限性,梳理了相关任务及其对应的数据集。更广泛地总结了表格分析领域常用的公开数据集,并对各数据集的来源、规模、适用范围及文件类型进行详细介绍。列举了表格分析领域常用的评价指标,并按照实验数据集的不同对现有模型的实验结果进行对比。总结了当前表格分析领域的发展状况,并对未来发展方向进行了展望。

关键词: 表格检测, 结构识别, 深度学习, 数据集, 评价指标

Abstract: In view of the current development of table analysis in document analysis, the recent literature relevant to this field is sorted out, and the two key tasks, table detection and table structure recognition, are studied. For table detection, methods are divided into those based on object detection, graph neural network, generative adversarial network and deformable convolutional network. For table structure recognition, methods include those based on object detection, graph neural network, recurrent neural network, deformable convolutional and dilated convolutional network. The methods and limitations of various models are summarized, and the related tasks and their corresponding datasets are sorted out. The common open-source datasets in table analysis are summarized more widely, and the source, scale, scope of application and file type of each dataset are introduced in detail. The commonly used evaluation metrics in table analysis are listed, and the experimental results of existing models are compared in respect of different experimental datasets. The current development of table analysis is summarized, and the future tendency is discussed.

Key words: table detection, structure recognition, deep learning, dataset, evaluation metrics