A Survey and Approach to Chart Classification

TL;DR

This paper surveys current techniques for chart classification, compares CNN and transformer methods on a large dataset, and introduces a vision transformer that achieves state-of-the-art accuracy.

Contribution

It provides a comprehensive survey of chart classification methods and introduces a new vision transformer model with superior performance.

Findings

Transformer-based approach outperforms CNNs on the dataset

Extensive comparison of traditional ML, CNN, and transformer methods

The proposed transformer model achieves state-of-the-art results

Abstract

Charts represent an essential source of visual information in documents and facilitate a deep understanding and interpretation of information typically conveyed numerically. In the scientific literature, there are many charts, each with its stylistic differences. Recently the document understanding community has begun to address the problem of automatic chart understanding, which begins with chart classification. In this paper, we present a survey of the current state-of-the-art techniques for chart classification and discuss the available datasets and their supported chart types. We broadly classify these contributions as traditional approaches based on ML, CNN, and Transformers. Furthermore, we carry out an extensive comparative performance analysis of CNN-based and transformer-based approaches on the recently published CHARTINFO UB-UNITECH PMC dataset for the CHART-Infographics competition at ICPR 2022. The data set includes 15 different chart categories, including 22,923 training images and 13,260 test images. We have implemented a vision-based transformer model that produces state-of-the-art results in chart classification.