对比Transformer与YOLO模型在古籍版面分析中的表现，发现旋转框对复杂手稿至关重要。
From Codicology to Code: A Comparative Study of Transformer and YOLO-based Detectors for Layout Analysis in Historical Documents
- 用旋转框（OBB）建模古籍非矩形布局，显著提升检测精度
- CNN+OBB模型在复杂古籍数据集上优于Transformer，mAP达0.568
- 适合处理视觉多样、版面复杂的古籍数字化任务
鲁棒的文档版面分析对自动化处理复杂版面的历史文献至关重要。本文在三个代表不同抄本复杂度的标注数据集上评估五种先进目标检测架构：e-NDP（1326-1504年巴黎修道院册页）、CATMuS（12-17世纪多源文献）和HORAE（13-16世纪装饰性祈祷书）。对比两种Transformer模型（Co-DETR、Grounding DINO）与三种YOLO变体（AABB、OBB、YOLO-World）。结果表明，模型性能受架构、数据集特征及边界框表示方式影响显著。e-NDP上Co-DETR表现最佳（[email protected]:.95=0.752），紧随其后的是YOLOv11X-OBB（0.721）。而在更复杂的CATMuS和HORAE上，基于CNN的YOLOv11x-OBB显著领先（0.564和0.568）。研究证实，使用旋转边界框（OBB）并非微调，而是准确建模历史手稿非笛卡尔结构的根本需求。结论表明，Transformer全局上下文感知能力适合结构化布局，而CNN+OBB模型在视觉多样且复杂的文档中更具泛化优势。
原文摘要 · Abstract (English)
Robust Document Layout Analysis (DLA) is critical for the automated processing and understanding of historical documents with complex page organizations. This paper benchmarks five state-of-the-art object detection architectures on three annotated datasets representing a spectrum of codicological complexity: The e-NDP, a corpus of Parisian medieval registers (1326-1504); CATMuS, a diverse multiclass dataset derived from various medieval and modern sources (ca.12th-17th centuries) and HORAE, a corpus of decorated books of hours (ca.13th-16th centuries). We evaluate two Transformer-based models (Co-DETR, Grounding DINO) against three YOLO variants (AABB, OBB, and YOLO-World). Our findings reveal significant performance variations dependent on model architecture, data set characteristics, and bounding box representation. In the e-NDP dataset, Co-DETR achieves state-of-the-art results (0.752 [email protected]:.95), closely followed by YOLOv11X-OBB (0.721). Conversely, on the more complex CATMuS and HORAE datasets, the CNN-based YOLOv11x-OBB significantly outperforms all other models (0.564 and 0.568, respectively). This study unequivocally demonstrates that using Oriented Bounding Boxes (OBB) is not a minor refinement but a fundamental requirement for accurately modeling the non-Cartesian nature of historical manuscripts. We conclude that a key trade-off exists between the global context awareness of Transformers, ideal for structured layouts, and the superior generalization of CNN-OBB models for visually diverse and complex documents.
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。