arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.15469cs.CV
收藏

CISOL:一个面向建筑行业表格结构识别的开放且可扩展的数据集

CISOL: An Open and Extensible Dataset for Table Structure Recognition in the Construction Industry

Bauhaus-Universität Weimar(魏玛包豪斯大学)

David Tschirschwitz, Volker Rodehorst

AI总结:

本文提出了CISOL数据集,包含800多张土木工程文档图像和超12万标注实例,为表格结构识别与检测任务提供基础,YOLOv8基准测试达67.22 mAP,优于TATR模型。

摘要:

可重复性和可复制性是实证研究的关键支柱,特别是在机器学习领域,它们不仅依赖于模型的可用性,还依赖于用于训练和评估这些模型的数据集。在本文中,我们介绍了建筑行业钢材订购清单(CISOL)数据集,该数据集的开发重点关注透明度,以确保可重复性、可复制性和可扩展性。CISOL提供了一个宝贵的新研究资源,并突出了拥有多样化数据集的重要性,即使在土木工程表格提取等细分应用领域也是如此。CISOL的独特之处在于它包含来自工业界的真实土木工程文档,使其成为该领域的一项独特贡献。该数据集在超过800张文档图像中包含超过120,000个标注实例,将其定位为中型数据集,为表格结构识别(TSR)和表格检测(TD)任务提供了坚实的基础。基准测试结果表明,使用YOLOv8模型,CISOL达到了67.22 mAP@0.5:0.95:0.05,优于专门针对TSR的TATR模型。这突显了CISOL作为推进TSR的基准的有效性,尤其是在专业领域。

英文摘要:

Reproducibility and replicability are critical pillars of empirical research, particularly in machine learning, where they depend not only on the availability of models, but also on the datasets used to train and evaluate those models. In this paper, we introduce the Construction Industry Steel Ordering List (CISOL) dataset, which was developed with a focus on transparency to ensure reproducibility, replicability, and extensibility. CISOL provides a valuable new research resource and highlights the importance of having diverse datasets, even in niche application domains such as table extraction in civil engineering. CISOL is unique in that it contains real-world civil engineering documents from industry, making it a distinctive contribution to the field. The dataset contains more than 120,000 annotated instances in over 800 document images, positioning it as a medium-sized dataset that provides a robust foundation for Table Structure Recognition (TSR) and Table Detection (TD) tasks. Benchmarking results show that CISOL achieves 67.22 mAP@0.5:0.95:0.05 using the YOLOv8 model, outperforming the TSR-specific TATR model. This highlights the effectiveness of CISOL as a benchmark for advancing TSR, especially in specialized domains.

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。

↑