Robust Table Detection and Structure Recognition from Heterogeneous Document Images

作者：

Highlights：

• We propose a new table detection and structure recognition approach named RobusTabNet to extract tables from heterogeneous document images.

• For table detection, we use CornerNet as a new region proposal network for Faster R-CNN to improve localization accuracy.

• For table structure recognition, we propose a new split-and-merge based approach, which contains a spatial CNN based separation line prediction module and a Grid CNN based cell merging module.

• Our approach is robust to tables with complex structures, large blank spaces, as well as distorted or even curved shapes.

• Our approach achieves state-of-the-art performance on both table detection and structure recognition public benchmarks.

摘要

•We propose a new table detection and structure recognition approach named RobusTabNet to extract tables from heterogeneous document images.•For table detection, we use CornerNet as a new region proposal network for Faster R-CNN to improve localization accuracy.•For table structure recognition, we propose a new split-and-merge based approach, which contains a spatial CNN based separation line prediction module and a Grid CNN based cell merging module.•Our approach is robust to tables with complex structures, large blank spaces, as well as distorted or even curved shapes.•Our approach achieves state-of-the-art performance on both table detection and structure recognition public benchmarks.

论文关键词：Table detection,Table structure recognition,Corner detection,Spatial CNN,Grid CNN,Split-and-merge

论文评审过程：Received 16 March 2022, Revised 10 August 2022, Accepted 27 August 2022, Available online 29 August 2022, Version of Record 12 September 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.109006