A Web Application for Watermark RecognitionArticleAuteurs : Oumayma Bounou
1,2,3,4,5; Tom Monnier
6,3,4; Ilaria Pastrolin
7; Xi SHEN ; Christine Benevent
8,2; Marie-Françoise Limon-Bonnet
9,7; François Bougard
10; Mathieu Aubry
3; Marc H. Smith
6,7; Olivier Poncet
11,7; Pierre-Guillaume Raverdy
12,5
NULL##NULL##NULL##NULL##NULL##NULL##0000-0001-8540-8141##NULL##NULL##NULL##NULL
Oumayma Bounou;Tom Monnier;Ilaria Pastrolin;Xi SHEN;Christine Benevent;Marie-Françoise Limon-Bonnet;François Bougard;Mathieu Aubry;Marc H. Smith;Olivier Poncet;Pierre-Guillaume Raverdy
The study of watermarks is a key step for archivists and historians as it enables them to reveal the origin of paper. Although highly practical, automatic watermark recognition comes with many difficultiesand is still considered an unsolved challenge. Nonetheless, Shen et al. [2019] recently introduced a newapproach for this specific task which showed promising results. Building upon this approach, this workproposes a new public web application dedicated to automatic watermark recognition entitled Filigranespour tous. The application not only hosts a detailed catalog of more than 17k watermarks manually collected from the French National Archives (Minutier central) or extracted from existing online resources(Briquet database), but it also enables non-specialists to identify a watermark from a simple photographin a few seconds. Moreover, additional watermarks can easily be added by the users making the enrichment of the existing catalog possible through crowdsourcing. Our Web application is available athttp://filigranes.inria.fr/.
Volume : Atelier Digit\_Hum
Rubrique : Déluge de données : quelles compétences pour quelles données ?
Publié le : 17 juillet 2020
Accepté le : 15 juillet 2020
Soumis le : 26 mars 2020
Mots-clés : [SHS.MUSEO]Humanities and Social Sciences/Cultural heritage and museology, [en] cross-domain recognition, deep learning, watermark recognition, web application, paper analysis
Financement :
Source : OpenAIRE Graph- Exploitation des bases d'images patrimoniales; Financeur: French National Research Agency (ANR); Code: ANR-17-CE23-0008