TY  -  
T1  - OCR and post-correction of historical Finnish texts 
SN  -  /  
UR  - http://hdl.handle.net/10138/229864 
T3  - Linköping Electronic Conference Proceedings 
A1  - Drobac, Senka; Kauppinen, Pekka Sakari; Linden, Bo Krister Johan 
A2  - Tiedemann, Jörg 
PB  - Linköping University Electronic Press 
Y1  - 2017 
LA  - eng 
AB  - This paper presents experiments on Optical character recognition (OCR) as a combination of Ocropy software and data-driven spelling correction that uses Weighted Finite-State Methods. Both model training and testing were done on Finnish corpora of historical newspaper text and the best combination of OCR and post-processing models give 95.21% character recognition accuracy.... 
VO  -  
IS  -  
SP  -  
OP  -  
KW  - 6121 Languages 
N1  -   
PP  -  
ER  -