Computer Vision and Historical Scientific Illustrations - Institut des sciences du calcul et des données Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Computer Vision and Historical Scientific Illustrations

Résumé

The VHS project (computer Vision and Historical analysis of Scientific illustration circulation) proposes a new approach to the historical study of the circulation of scientific knowledge based on new methods of illustration analysis. Our contributions in this paper are twofold. First, we present a semi-automatic interactive pipeline for scientific illustration extraction that allows and incorporates expert feedback from historians. Second, we introduce a new dataset of scientific illustrations from the Middle Ages to the modern era consisting of 8k illustrations validated by historians and a total number of 235k illustrations obtained from 405k corpora pages. We further discuss our current research for identifying a series of related illustrations from this data.
Fichier principal
Vignette du fichier
VHS_IAMAHA_Conference-1.pdf (233.16 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
licence : CC BY - Paternité

Dates et versions

hal-04316644 , version 1 (30-11-2023)

Identifiants

  • HAL Id : hal-04316644 , version 1

Citer

Fouad Aouinti, Zeynep Sonat Baltaci, Mathieu Aubry, Aleksandre Guilbaud, Stavros Lazaris. Computer Vision and Historical Scientific Illustrations. 1st Symposium in Artificial Intelligence & Applied Mathematics for History & Archaeology « IAMAHA » -, Nov 2023, Nice, France. ⟨hal-04316644⟩
72 Consultations
73 Téléchargements

Partager

Gmail Facebook X LinkedIn More