Papers
arxiv:2506.20326

From Codicology to Code: A Comparative Study of Transformer and YOLO-based Detectors for Layout Analysis in Historical Documents

Published on Jun 25
Authors:

Abstract

Evaluation of Transformer and CNN-based object detection architectures on historical documents shows significant performance differences, emphasizing the importance of Oriented Bounding Boxes for complex layouts.

AI-generated summary

Robust Document Layout Analysis (DLA) is critical for the automated processing and understanding of historical documents with complex page organizations.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.

Community

Sign up or log in to comment

Models citing this paper 1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2506.20326 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2506.20326 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.