RTHDet：图像中旋转表格区域与表头表尾检测
RTHDet: Rotate Table Area and Head Detection in images
AI总结：
本文提出RTHDet方法，通过旋转矩形角度表示和角度损失分支，结合迁移学习与自适应边界旋转增强，在旋转表格检测任务中将AP50从23.7%提升至88.7%，并集成到MMRotate工具包。
摘要：
传统模型专注于水平表格检测，但在旋转场景中表现不佳，限制了表格识别的发展。本文提出了一项新任务：在旋转场景中检测表格区域并定位表头与表尾部分。我们提出了相应的数据集、评估指标和方法。我们的新方法“自适应边界旋转”解决了旋转表格及其表头表尾检测中数据集稀缺的问题。我们基于“ICDAR2019MTD”制作了“TRR360D”数据集，该数据集包含表格表头和表尾的语义信息。新指标“R360 AP”用于衡量旋转区域检测及表头表尾定位的精度。经过广泛审查和测试，我们选择了高速且准确的“RTMDet-S”作为基线模型。我们引入了“RTHDet”，通过“r360”旋转矩形角度表示和“Angle Loss”分支增强基线，改善了表头表尾定位。通过应用迁移学习和自适应边界旋转增强，RTHDet的AP50（T<90）从基线的23.7%提升至88.7%。这证明了RTHDet在检测旋转表格区域和准确定位表头表尾方面的有效性。RTHDet已集成到广泛使用的开源MMRotate工具包中：https://github.com/open-mmlab/mmrotate/tree/dev-1.x/projects/RR360。
英文摘要：
Traditional models focus on horizontal table detection but struggle in rotating contexts, limiting progress in table recognition. This paper introduces a new task: detecting table regions and localizing head-tail parts in rotation scenarios. We propose corresponding datasets, evaluation metrics, and methods. Our novel method, 'Adaptively Bounded Rotation,' addresses dataset scarcity in detecting rotated tables and their head-tail parts. We produced 'TRR360D,' a dataset incorporating semantic information of table head and tail, based on 'ICDAR2019MTD.' A new metric, 'R360 AP,' measures precision in detecting rotated regions and localizing head-tail parts. Our baseline, the high-speed and accurate 'RTMDet-S,' is chosen after extensive review and testing. We introduce 'RTHDet,' enhancing the baseline with a 'r360' rotated rectangle angle representation and an 'Angle Loss' branch, improving head-tail localization. By applying transfer learning and adaptive boundary rotation augmentation, RTHDet's AP50 (T<90) improved from 23.7% to 88.7% compared to the baseline. This demonstrates RTHDet's effectiveness in detecting rotating table regions and accurately localizing head and tail parts.RTHDet is integrated into the widely-used open-source MMRotate toolkit: https://github.com/open-mmlab/mmrotate/tree/dev-1.x/projects/RR360.
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。
