Recent Developments in OCR for Digital Libraries
This one day workshop will disseminate the latest progress achieved in the field of Optical Character Recognition systems (OCR) within the framework of various digitization projects for Digital Libraries.
Preliminary program
9h30-10h Welcome
10h-11h User specification
- Main objectives of the IMPACT project, Hildelies Balk, Den Haag Koenigs Bibliotek
- The BVH project: latest developments : Marie-Luce Demonet, CESR CNRS Tours
11h-12h30 Recent developments in OCR
- Recent developments within IMPACT, Mickael Fuchs, Abby EU
- OCR adaptation for old documents, K. Ait Mohand, LITIS - LI Tours, France
- Managing OCR for digital libraries, Jean-Pierre Raysz, Jouve, France
- Apostolos Antonacopoulos, PRIMA, Univ. Salford, UK
Lunch break
14h-14h40 OCR and Typography
- JY Ramel, LI Tours, France
- Lead typography and the OCR on ancient documents : handling irregularities, Rémi Jimenes, CESR Tours, France
14h40-15h40 OCR Evaluation & Verification
- User assessment methodology within IMPACT, Geneviève Cron, Bibliothèque nationale de France
- Evaluation & Verification of OCR at BnF, A. Ben Salah, BnF & LITIS
- Visualisation & Collaborative annotation of Newspaper Archives, T Palfray, LITIS
- Digitalkoot - digitizing Finnish cultural heritage through crowdsourcing, Ville Miettinen, Microtask Ltd, Finland
15h40-16h20 Linguistic Resources for OCR
- Les ressources lexicales de l'ATILF pour le traitement de documents anciens, Gilles Souvay, ATILF Nancy
- Ocring and processing Early Modern French texts with adapted tools, Marie-Luce Demonet, CESR Tours


