arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.04147cs.CVcs.AIcs.LG
收藏

图表分类的综述与方法

A Survey and Approach to Chart Classification

Indian Institute of Information Technology, Allahabad(阿拉哈巴德印度信息技术学院);University at Buffalo(布法罗大学)

Anurag Dhote, Mohammed Javed, David S Doermann

AI总结:

本文综述了图表分类的现有技术,并在CHARTINFO UB-UNITECH PMC数据集上比较了CNN与Transformer方法,提出一种视觉Transformer模型,在15类图表分类中取得最优结果。

摘要:

图表是文档中视觉信息的重要来源,有助于深入理解和解释通常以数值形式传达的信息。在科学文献中,存在大量图表,且各自具有风格差异。近年来,文档理解领域开始关注自动图表理解问题,而该问题的第一步是图表分类。本文对当前最先进的图表分类技术进行了综述,并讨论了可用数据集及其支持的图表类型。我们将这些贡献大致分为基于机器学习(ML)、卷积神经网络(CNN)和Transformer的传统方法。此外,我们在最近发布的CHARTINFO UB-UNITECH PMC数据集上,对基于CNN和基于Transformer的方法进行了广泛的比较性能分析,该数据集用于ICPR 2022的CHART-Infographics竞赛。该数据集包含15种不同的图表类别,包括22,923张训练图像和13,260张测试图像。我们实现了一种基于视觉的Transformer模型,在图表分类中取得了最先进的结果。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑