Cécile Robin
Research Subjects
Cécile Robin has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Annie Vinter
Université Bourgogne Europe, CNRS, LEAD UMR5022, 21000 Dijon, France
1 shared publication - Edouard Bouyé
Archives Départementales de Côte d’Or, 21000 Dijon, France
1 shared publication - Florian Côme Fizaine
LEAD-CNRS, Université de Bourgogne, 21000 Dijon, France
1 shared publication - Michel Paindavoine
LEAD UMR CNRS 5022, Université Bourgogne Europe, 21000 Dijon, France
1 shared publication - Patrick Bard
Université Bourgogne Europe, CNRS, LEAD UMR5022, 21000 Dijon, France
1 shared publication - Raphaël Lefèvre
Société Nationale des Chemins de fer Français, 93200 Saint Denis, France
1 shared publication
Latest Publications
- Open Access
- 5 March 2024
- Published by MDPI AG in Journal of Imaging
- Vol. 10 (3) , 65
Historical Text Line Segmentation Using Deep Learning Algorithms: Mask-RCNN against U-Net Networks
Text line segmentation is a necessary preliminary step before most text transcription algorithms are applied. The leading deep learning networks used in this context (ARU-Net, dhSegment, and Doc-UFCN) are based on the U-Net architecture. They are efficient, but fall under the same concept, requiring a post-processing step to perform instance (e.g., text line) segmentation. In the present work, we test the advantages of Mask-RCNN, which is designed to perform instance segmentation directly. This work is the first to directly compare Mask-RCNN- and U-Net-based networks on text segmentation of historical documents, showing the superiority of the former over the latter. Three studies were conducted, one comparing these networks on different historical databases, another comparing Mask-RCNN with Doc-UFCN on a private historical database, and a third comparing the handwritten text recognition (HTR) performance of the tested networks. The results showed that Mask-RCNN outperformed ARU-Net, dhSegment, and Doc-UFCN using relevant line segmentation metrics, that performance evaluation should not focus on the raw masks generated by the networks, that a light mask processing is an efficient and simple solution to improve evaluation, and that Mask-RCNN leads to better HTR performance.
- 5 March 2024
- Published by MDPI AG in Journal of Imaging
- Vol. 10 (3) , 65
Open AccessHistorical Text Line Segmentation Using Deep Learning Algorithms: Mask-RCNN against U-Net Networks
Text line segmentation is a necessary preliminary step before most text transcription algorithms are applied. The leading deep learning networks used in this context (ARU-Net, dhSegment, and Doc-UFCN) are based on the U-Net architecture. They are efficient, but fall under the same concept, requiring a post-processing step to perform instance (e.g., text line) segmentation. In the present work, we test the advantages of Mask-RCNN, which is designed to perform instance segmentation directly. This work is the first to directly compare Mask-RCNN- and U-Net-based networks on text segmentation of historical documents, showing the superiority of the former over the latter. Three studies were conducted, one comparing these networks on different historical databases, another comparing Mask-RCNN with Doc-UFCN on a private historical database, and a third comparing the handwritten text recognition (HTR) performance of the tested networks. The results showed that Mask-RCNN outperformed ARU-Net, dhSegment, and Doc-UFCN using relevant line segmentation metrics, that performance evaluation should not focus on the raw masks generated by the networks, that a light mask processing is an efficient and simple solution to improve evaluation, and that Mask-RCNN leads to better HTR performance.