Watermark recognition is a key problem for archivists and historians. We are developing a Computer Vision approach to recognise tens of thousands of variants from a single photograph. Learn more on our project website!
This project is in collaboration with the Filigranes pour tous project, with whom we are developing a web app for easy large scale watermark identification. It lead to further collaboration with the Newton Watermarks project in Cambridge.
Publications:
Large-Scale Historical Watermark Recognition: dataset and a new consistency-based approach, Xi Shen, Ilaria Pastrolin, Oumayma Bounou, Spyros Gidaris, Marc Smith, Olivier Poncet and Mathieu Aubry,
ICPR 2020,
PDF, Project page.
A Web Application for Watermark Recognition
Oumayma Bounou, Tom Monnier, Ilaria Pastrolin, Xi Shen, Christine Benevent, Marie-Françoise Limon-Bonnet, François Bougard, Mathieu Aubry, Marc Smith, Olivier Poncet, Pierre-Guillaume Raverdy
Journal of Data Mining and Digital Humanities 2020
PDF