Saved in:
Bibliographic Details
Main Authors: Clérice, Thibault, Janes, Juliette, Scheithauer, Hugo, Bénière, Sarah, Cafiero, Florian, Romary, Laurent, Gabay, Simon, Sagot, Benoît
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