Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.10068 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929592520933376 |
|---|---|
| author | Clérice, Thibault Janes, Juliette Scheithauer, Hugo Bénière, Sarah Cafiero, Florian Romary, Laurent Gabay, Simon Sagot, Benoît |
| author_facet | Clérice, Thibault Janes, Juliette Scheithauer, Hugo Bénière, Sarah Cafiero, Florian Romary, Laurent Gabay, Simon Sagot, Benoît |
| contents | We present a novel, open-access dataset designed for semantic layout analysis, built to support document recreation workflows through mapping with the Text Encoding Initiative (TEI) standard. This dataset includes 7,254 annotated pages spanning a large temporal range (1600-2024) of digitised and born-digital materials across diverse document types (magazines, papers from sciences and humanities, PhD theses, monographs, plays, administrative reports, etc.) sorted into modular subsets. By incorporating content from different periods and genres, it addresses varying layout complexities and historical changes in document structure. The modular design allows domain-specific configurations. We evaluate object detection models on this dataset, examining the impact of input size and subset-based training. Results show that a 1280-pixel input size for YOLO is optimal and that training on subsets generally benefits from incorporating them into a generic model rather than fine-tuning pre-trained weights. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_10068 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Diachronic Document Dataset for Semantic Layout Analysis Clérice, Thibault Janes, Juliette Scheithauer, Hugo Bénière, Sarah Cafiero, Florian Romary, Laurent Gabay, Simon Sagot, Benoît Computer Vision and Pattern Recognition We present a novel, open-access dataset designed for semantic layout analysis, built to support document recreation workflows through mapping with the Text Encoding Initiative (TEI) standard. This dataset includes 7,254 annotated pages spanning a large temporal range (1600-2024) of digitised and born-digital materials across diverse document types (magazines, papers from sciences and humanities, PhD theses, monographs, plays, administrative reports, etc.) sorted into modular subsets. By incorporating content from different periods and genres, it addresses varying layout complexities and historical changes in document structure. The modular design allows domain-specific configurations. We evaluate object detection models on this dataset, examining the impact of input size and subset-based training. Results show that a 1280-pixel input size for YOLO is optimal and that training on subsets generally benefits from incorporating them into a generic model rather than fine-tuning pre-trained weights. |
| title | Diachronic Document Dataset for Semantic Layout Analysis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.10068 |