Automatic Die Studies for Ancient Numismatics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cornet, Clément, Aumaître, Héloïse, Besançon, Romaric, Olivier, Julien, Faucher, Thomas, Borgne, Hervé Le
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909274356056064
author Cornet, Clément
Aumaître, Héloïse
Besançon, Romaric
Olivier, Julien
Faucher, Thomas
Borgne, Hervé Le
author_facet Cornet, Clément
Aumaître, Héloïse
Besançon, Romaric
Olivier, Julien
Faucher, Thomas
Borgne, Hervé Le
contents Die studies are fundamental to quantifying ancient monetary production, providing insights into the relationship between coinage, politics, and history. The process requires tedious manual work, which limits the size of the corpora that can be studied. Few works have attempted to automate this task, and none have been properly released and evaluated from a computer vision perspective. We propose a fully automatic approach that introduces several innovations compared to previous methods. We rely on fast and robust local descriptors matching that is set automatically. Second, the core of our proposal is a clustering-based approach that uses an intrinsic metric (that does not need the ground truth labels) to determine its critical hyper-parameters. We validate the approach on two corpora of Greek coins, propose an automatic implementation and evaluation of previous baselines, and show that our approach significantly outperforms them.
format Preprint
id arxiv_https___arxiv_org_abs_2407_20876
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Automatic Die Studies for Ancient Numismatics
Cornet, Clément
Aumaître, Héloïse
Besançon, Romaric
Olivier, Julien
Faucher, Thomas
Borgne, Hervé Le
Computer Vision and Pattern Recognition
Die studies are fundamental to quantifying ancient monetary production, providing insights into the relationship between coinage, politics, and history. The process requires tedious manual work, which limits the size of the corpora that can be studied. Few works have attempted to automate this task, and none have been properly released and evaluated from a computer vision perspective. We propose a fully automatic approach that introduces several innovations compared to previous methods. We rely on fast and robust local descriptors matching that is set automatically. Second, the core of our proposal is a clustering-based approach that uses an intrinsic metric (that does not need the ground truth labels) to determine its critical hyper-parameters. We validate the approach on two corpora of Greek coins, propose an automatic implementation and evaluation of previous baselines, and show that our approach significantly outperforms them.
title Automatic Die Studies for Ancient Numismatics
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.20876