Improving Optical Character Recognition of Finnish Historical Newspapers with a Combination of Fraktur & Antiqua Models and Image Preprocessing

Mika Koistinen, Kimmo Kettunen, Tuula Pääkkönen


Anthology ID:
W17-0238
Volume:
Proceedings of the 21st Nordic Conference on Computational Linguistics
Month:
May
Year:
2017
Address:
Gothenburg, Sweden
Editors:
Jörg Tiedemann, Nina Tahmasebi
Venue:
NoDaLiDa
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
277–283
Language:
URL:
https://aclanthology.org/W17-0238
DOI:
Bibkey:
Cite (ACL):
Mika Koistinen, Kimmo Kettunen, and Tuula Pääkkönen. 2017. Improving Optical Character Recognition of Finnish Historical Newspapers with a Combination of Fraktur & Antiqua Models and Image Preprocessing. In Proceedings of the 21st Nordic Conference on Computational Linguistics, pages 277–283, Gothenburg, Sweden. Association for Computational Linguistics.
Cite (Informal):
Improving Optical Character Recognition of Finnish Historical Newspapers with a Combination of Fraktur & Antiqua Models and Image Preprocessing (Koistinen et al., NoDaLiDa 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-0238.pdf