Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context

by   Xinyi Zheng, et al.

Documents are often the format of choice for knowledge sharing and preservation in business and science. Much of the critical data are captured in tables. Unfortunately, most documents are stored and distributed in PDF or scanned images, which fail to preserve table formatting. Recent vision-based deep learning approaches have been proposed to address this gap, but most still cannot achieve state-of-the-art results. We present Global Table Extractor (GTE), a vision-guided systematic framework for joint table detection and cell structured recognition, which could be built on top of any object detection model. With GTE-Table, we invent a new penalty based on the natural cell containment constraint of tables to train our table network aided by cell location predictions. GTE-Cell is a new hierarchical cell detection network that leverages table styles. Further, we design a method to automatically label table and cell structure in existing documents to cheaply create a large corpus of training and test data. We use this to create SD-tables and SEC-tables, real world and complex scientific and financial datasets with detailed table structure annotations to help train and test structure recognition. Our deep learning framework surpasses previous state-of-the-art results on the ICDAR 2013 table competition test dataset in both table detection and cell structure recognition, with a significant 6.8 system. We also show more than 30 F1-score when compared to a vanilla RetinaNet object detection model in our out-of-domain financial dataset (SEC-Tables).


page 1

page 2

page 3

page 4


TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition

A table arranging data in rows and columns is a very effective data stru...

Tablext: A Combined Neural Network And Heuristic Based Table Extractor

A significant portion of the data available today is found within tables...

Detecting Table Region in PDF Documents Using Distant Supervision

Superior to state-of-the-art approaches which compete in table recogniti...

Efficient Information Sharing in ICT Supply Chain Social Network via Table Structure Recognition

The global Information and Communications Technology (ICT) supply chain ...

Guided Table Structure Recognition through Anchor Optimization

This paper presents the novel approach towards table structure recogniti...

DocParser: Hierarchical Structure Parsing of Document Renderings

Translating document renderings (e.g. PDFs, scans) into hierarchical str...

Table Structure Recognition with Conditional Attention

Tabular data in digital documents is widely used to express compact and ...

Please sign up or login with your details

Forgot password? Click here to reset