Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Mélodie Boillet"'
Publikováno v:
Pattern Recognition Letters. 166:31-37
Deep neural networks are becoming increasingly powerful and large and always require more labelled data to be trained. However, since annotating data is time-consuming, it is now necessary to develop systems that show good performance while learning
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8101e93f898be24ffdcfa4eb7c694ff8
https://doi.org/10.1016/j.patrec.2022.12.024
https://doi.org/10.1016/j.patrec.2022.12.024
Publikováno v:
International Journal on Document Analysis and Recognition (IJDAR). 25:95-114
Text line segmentation is one of the key steps in historical document understanding. It is challenging due to the variety of fonts, contents, writing styles and the quality of documents that have degraded through the years. In this paper, we address
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be131be28d7d57299acc505d2128b2b5
https://doi.org/10.1007/s10032-022-00395-7
https://doi.org/10.1007/s10032-022-00395-7
Autor:
Solène Tarride, Martin Maarand, Mélodie Boillet, James McGrath, Eugénie Capel, Hélène Vézina, Christopher Kermorvant
This paper presents a complete workflow designed for extracting information from Quebec handwritten parish registers. The acts in these documents contain individual and family information highly valuable for genetic, demographic and social studies of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6cbeeabbd6846ddfd837ebd4cb649e89
Publikováno v:
ICPR
In this paper, we introduce a fully convolutional network for the document layout analysis task. While state-of-the-art methods are using models pre-trained on natural scene images, our method Doc-UFCN relies on a U-shaped model trained from scratch
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2961e9a3936cf1784b9b964480af04fb
https://doi.org/10.1109/icpr48806.2021.9412447
https://doi.org/10.1109/icpr48806.2021.9412447
Publikováno v:
Communications in Computer and Information Science ISBN: 9783030937324
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::be531b82df665e7dd0bd7e63b2135441
https://doi.org/10.1007/978-3-030-93733-1_39
https://doi.org/10.1007/978-3-030-93733-1_39
Autor:
Amir Hazem, Béatrice Daille, Marie-Laurence Bonhomme, Martin Maarand, Mélodie Boillet, Christopher Kermorvant, Dominique Stutzmann
Publikováno v:
Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)
12th Language Resources and Evaluation Conference
12th Language Resources and Evaluation Conference, May 2020, Marseille (Virtual), France. pp.776-784
HAL
12th Language Resources and Evaluation Conference
12th Language Resources and Evaluation Conference, May 2020, Marseille (Virtual), France. pp.776-784
HAL
International audience; The Book of Hours was the bestseller of the late Middle Ages and Renaissance. It is a historical invaluable treasure, documentingthe devotional practices of Christians in the late Middle Ages. Up to now, its textual content ha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::f62b67cda31782002aed2c882b8c592f
https://hal.archives-ouvertes.fr/hal-02931294/document
https://hal.archives-ouvertes.fr/hal-02931294/document