线条图形数字化：迈向全自动化的一步
Line Graphics Digitization: A Step Towards Full Automation
AI总结：
本文提出线条图形（LG）数据集，包含520幅数学图形图像的像素级标注，支持语义分割和目标检测，并评测了7种先进模型，以推动统计图形自动数字化研究。
摘要：
文档数字化能够提升可访问性与可复现性。尽管文档版面与文本内容的自动数字化长期以来一直是研究重点，但针对图形元素（如统计图表）的这一问题仍未被充分探索。本文引入了数学图形细粒度视觉理解任务，并提出了线条图形（LG）数据集，该数据集包含5个粗粒度类别和10个细粒度类别的像素级标注。我们的数据集涵盖520幅数学图形图像，收集自450篇不同学科的文档。我们提出的数据集可支持两种不同的计算机视觉任务，即语义分割和目标检测。为对LG数据集进行基准评测，我们探索了7种最先进的模型。为促进统计图形数字化的进一步研究，我们将向社区公开该数据集、代码和模型。
英文摘要：
The digitization of documents allows for wider accessibility and reproducibility. While automatic digitization of document layout and text content has been a long-standing focus of research, this problem in regard to graphical elements, such as statistical plots, has been under-explored. In this paper, we introduce the task of fine-grained visual understanding of mathematical graphics and present the Line Graphics (LG) dataset, which includes pixel-wise annotations of 5 coarse and 10 fine-grained categories. Our dataset covers 520 images of mathematical graphics collected from 450 documents from different disciplines. Our proposed dataset can support two different computer vision tasks, i.e., semantic segmentation and object detection. To benchmark our LG dataset, we explore 7 state-of-the-art models. To foster further research on the digitization of statistical graphs, we will make the dataset, code, and models publicly available to the community.
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。
