A Survey on Figure Classification Techniques in Scientific Documents

TL;DR

This survey reviews AI and ML techniques for classifying figures in scientific documents, categorizing figures into five types and analyzing existing methods, datasets, and future research directions.

Contribution

It systematically categorizes figure types and critically reviews current methodologies and datasets for figure classification in scientific papers.

Findings

Figures are categorized into five classes: tables, photos, diagrams, maps, and plots.

Existing methodologies and datasets are critically analyzed.

Research gaps and future directions are identified.

Abstract

Figures visually represent an essential piece of information and provide an effective means to communicate scientific facts. Recently there have been many efforts toward extracting data directly from figures, specifically from tables, diagrams, and plots, using different Artificial Intelligence and Machine Learning techniques. This is because removing information from figures could lead to deeper insights into the concepts highlighted in the scientific documents. In this survey paper, we systematically categorize figures into five classes - tables, photos, diagrams, maps, and plots, and subsequently present a critical review of the existing methodologies and data sets that address the problem of figure classification. Finally, we identify the current research gaps and provide possible directions for further research on figure classification.