端到端检测文本行并排序，解决历史文献排版难题
End-to-End Text Line Detection and Ordering
- 将文本行检测与排序合为一个图像到序列任务，直接生成阅读顺序的基线
- 在196,691页多语种数据上训练，零样本下阅读顺序准确率接近完美
- 适用于多栏、注释、表格等复杂排版，微调后可适应特殊文档布局
面向历史文献的实用文本识别流程通常将版面分析分解为文本行检测和阅读顺序确定两个独立步骤，后者常依赖手工编写的几何启发式规则，难以处理边注、多栏、表格及特定来源的编辑惯例。本文提出Orli（有序线回归），一种端到端模型，将两个子任务统一为图像到序列问题：从页面图像出发，Orli 自回归地生成按阅读顺序排列的文本行基线。基线采用弦坐标参数化，同时锚定位置、方向和长度，并通过垂直偏移编码局部几何特征；迭代优化头与局部视觉修正模块生成最终曲线。在包含10种书写系统的196,691页异构语料上训练，Orli 在cBAD文本行检测任务上略超现有最先进水平，无需特定数据集训练；在多个阅读顺序基准测试中实现接近完美的覆盖率与排序准确率，且仅需少量微调即可适应更专业的域外布局。代码与模型权重已开源。
原文摘要 · Abstract (English)
Practical text-recognition pipelines for historical documents typically decompose layout analysis into line detection followed by a separate reading-order step, with the latter most often handled by a hand-coded geometric heuristic that struggles with marginalia, multiple columns, tables, and source-specific editorial conventions. This article introduces Orli (Ordered Regression of Lines), an end-to-end model that casts both sub-tasks as a single image-to-sequence problem: from a page image, Orli autoregressively generates text-line baselines directly in reading order. Baselines are represented in a chord-frame parameterization that anchors a line's position, orientation, and extent while encoding local geometry through perpendicular offsets; an iterative refinement head and a local visual refiner produce the final curve. Trained on a heterogeneous corpus of 196,691 pages spanning ten writing systems, Orli marginally exceeds the previously reported state of the art for cBAD line detection without dataset-specific training, reaches near perfect coverage and ordering on multiple reading-order benchmarks zero-shot, and adapts to more specialized out-of-domain layouts with limited fine-tuning. The method's source code and model weights are available under an open license at https://github.com/mittagessen/orli.
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。