ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX

TL;DR

This paper reports on the ICDAR 2021 competition focused on converting scientific table images into LaTeX code, highlighting dataset creation, evaluation metrics, and participant methods to advance automated table recognition.

Contribution

It introduces a new benchmark for scientific table image recognition to LaTeX, providing datasets, evaluation protocols, and a competitive platform to foster progress in this challenging task.

Findings

VCGroup achieved 74% accuracy in Subtask 1

55% accuracy in Subtask 2, surpassing baselines

The competition advances automated table recognition technology

Abstract

Tables present important information concisely in many scientific documents. Visual features like mathematical symbols, equations, and spanning cells make structure and content extraction from tables embedded in research documents difficult. This paper discusses the dataset, tasks, participants' methods, and results of the ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX. Specifically, the task of the competition is to convert a tabular image to its corresponding LaTeX source code. We proposed two subtasks. In Subtask 1, we ask the participants to reconstruct the LaTeX structure code from an image. In Subtask 2, we ask the participants to reconstruct the LaTeX content code from an image. This report describes the datasets and ground truth specification, details the performance evaluation metrics used, presents the final results, and summarizes the participating methods. Submission by team VCGroup got the highest Exact Match accuracy score of 74% for Subtask 1 and 55% for Subtask 2, beating previous baselines by 5% and 12%, respectively. Although improvements can still be made to the recognition capabilities of models, this competition contributes to the development of fully automated table recognition systems by challenging practitioners to solve problems under specific constraints and sharing their approaches; the platform will remain available for post-challenge submissions at https://competitions.codalab.org/competitions/26979 .