Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
KIŠŠ, M. BENEŠ, K. HRADIŠ, M.
Originální název
AT-ST: Self-Training Adaptation Strategy for OCR in Domains with Limited Transcriptions
Typ
článek ve sborníku ve WoS nebo Scopus
Jazyk
angličtina
Originální abstrakt
This paper addresses text recognition for domains with limited manual annotations by a simple self-training strategy. Our approach should reduce human annotation effort when target domain data is plentiful, such as when transcribing a collection of single person's correspondence or a large manuscript. We propose to train a seed system on large scale data from related domains mixed with available annotated data from the target domain. The seed system transcribes the unannotated data from the target domain which is then used to train a better system. We study several confidence measures and eventually decide to use the posterior probability of a transcription for data selection. Additionally, we propose to augment the data using an aggressive masking scheme. By self-training, we achieve up to 55 % reduction in character error rate for handwritten data and up to 38 % on printed data. The masking augmentation itself reduces the error rate by about 10 % and its effect is better pronounced in case of difficult handwritten data.
Klíčová slova
self-training, text recognition, language model, unlabelled data, confidence measures, data augmentation.
Autoři
KIŠŠ, M.; BENEŠ, K.; HRADIŠ, M.
Vydáno
8. 9. 2021
Nakladatel
Springer Nature Switzerland AG
Místo
Lausanne
ISBN
978-3-030-86336-4
Kniha
Lladós J., Lopresti D., Uchida S. (eds) Document Analysis and Recognition - ICDAR 2021
Edice
Lecture Notes in Computer Science
Strany od
463
Strany do
477
Strany počet
14
URL
https://pero.fit.vutbr.cz/publications
BibTex
@inproceedings{BUT175776, author="Martin {Kišš} and Karel {Beneš} and Michal {Hradiš}", title="AT-ST: Self-Training Adaptation Strategy for OCR in Domains with Limited Transcriptions", booktitle="Lladós J., Lopresti D., Uchida S. (eds) Document Analysis and Recognition - ICDAR 2021", year="2021", series="Lecture Notes in Computer Science", volume="12824", pages="463--477", publisher="Springer Nature Switzerland AG", address="Lausanne", doi="10.1007/978-3-030-86337-1\{_}31", isbn="978-3-030-86336-4", url="https://pero.fit.vutbr.cz/publications" }