Table Structure Recognition and Form Parsing by End-to-End Object Detection and Relation Parsing

作者：

Highlights：

• A graph neural network (GNN) based unified framework named TSRNet is proposed to jointly detect and recognize the structures of various tables and forms.

• GNN is used to classify and group primitive regions into page objects and classify the relationships.

• The parameters of all the modules in the system is trained end-to-end to optimize the overall performance

• Superior performance has been achieved on table detection, table structure recognition and template-free form parsing.

摘要

•A graph neural network (GNN) based unified framework named TSRNet is proposed to jointly detect and recognize the structures of various tables and forms.•GNN is used to classify and group primitive regions into page objects and classify the relationships.•The parameters of all the modules in the system is trained end-to-end to optimize the overall performance•Superior performance has been achieved on table detection, table structure recognition and template-free form parsing.

论文关键词：Table detection,Table structure recognition,Template-free form parsing,Graph neural network,End-to-end training

论文评审过程：Received 13 August 2021, Revised 25 June 2022, Accepted 25 July 2022, Available online 26 July 2022, Version of Record 4 August 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108946