针对变形表格单元格定位难题，提出新模型与数据集，提升分割精度。
OG-HFYOLO :Orientation gradient guidance and heterogeneous feature fusion for deformation table cell instance segmentation
- 通过梯度方向感知提取增强边缘响应，融合异构核特征适应多尺度目标
- 在主流模型上实现更优分割精度，关键指标显著超越基线方法
- 适合文档分析、表格识别领域研究者，尤其关注细粒度空间定位任务
表格结构识别是文档分析的关键任务。然而，变形表格中的几何失真导致内容信息与结构关联弱化，使下游任务难以获取准确内容。为获得单元格的精细空间坐标，本文提出OG-HFYOLO模型：通过梯度方向感知提取器增强边缘响应，引入异构核交叉融合模块与尺度感知损失函数以适应多尺度目标特征，并在后处理中采用掩码驱动的非极大值抑制，替代传统边界框抑制机制。此外，还设计了一种数据生成器，填补细粒度变形表格单元格空间定位数据集空白，构建了大规模数据集Deformation Wired Table (DWTAL)。实验表明，所提模型在所有主流实例分割模型上均展现出优异分割精度。代码与数据集已开源：https://github.com/justliulong/OGHFYOLO。
原文摘要 · Abstract (English)
Table structure recognition is a key task in document analysis. However, the geometric deformation in deformed tables causes a weak correlation between content information and structure, resulting in downstream tasks not being able to obtain accurate content information. To obtain fine-grained spatial coordinates of cells, we propose the OG-HFYOLO model, which enhances the edge response by Gradient Orientation-aware Extractor, combines a Heterogeneous Kernel Cross Fusion module and a scale-aware loss function to adapt to multi-scale objective features, and introduces mask-driven non-maximal suppression in the post-processing, which replaces the traditional bounding box suppression mechanism. Furthermore, we also propose a data generator, filling the gap in the dataset for fine-grained deformation table cell spatial coordinate localization, and derive a large-scale dataset named Deformation Wired Table (DWTAL). Experiments show that our proposed model demonstrates excellent segmentation accuracy on all mainstream instance segmentation models. The dataset and the source code are open source: https://github.com/justliulong/OGHFYOLO.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。