Clustering coins according to their die is a problem that has many applications in numismatics. This clustering is crucial for understanding the economic history of tribes (especially for tribes for whom few written records exist, such as the Celts). It is a difficult task, requiring a lot of time and expertise. However, there is very little work that has been done on coin die identification. This presentation will present an automatic tool to know if two patterns have been impressed with the same tool, especially to know if two coins have been struck with the same die. Based on deep learning-based registration algorithms, the proposed method has allowed us to classify a hoard of a thousand Riedone coins dating from the 2nd century BC. This treasure allowed us to build an annotated dataset of 3D acquisitions called Riedones3D. Riedones3D is useful for Celtic coin specialists, but also for the computer vision community to develop new coin die recognition algorithms. Rigorous evaluations on Riedones3D and on other Celtic works show the interest of the proposed method.
Exposé de Katherine Gruel (CNRS, AOROC ENS-PSL) et Sofiane Horache (Mines ParisTech) dans le cadre du Séminaire Digital Humanities / Artificial Intelligence (DHAI).
Voir aussi
Institutions : Ecole normale supérieure-PSL
Cursus :
Katherine Gruel est Directrice de recherche au CNRS, directrice-adjointe de l'AOROC (UMR 8546), spécialiste de protohistoire en Gaule septentrionale.
Cliquer ICI pour fermer
Cursus :
Sofiane Horache est doctorant à Mines Paristech. Sa thèse porte sur la reconnaissance de formes sur un nuage de points 3D et ses applications dans les arts celtiques.
Sofiane Horache met l’intelligence artificielle au service de l’archéologie, de l’histoire et du patrimoine. Il travaille sur le projet CELTES 3D, fruit d’une collaboration entre le laboratoire AOROC du département d'archéologie de l'ENS Ulm et le Centre de Robotique du département Mathématiques et Systèmes de Mines Paristech.
Dernière mise à jour : 03/02/2023