DocumentCode
384075
Title
DVHMM: variable length text recognition error model
Author
Takasu, Atsuhiro ; Aihara, Kenro
Author_Institution
Nat. Inst. of Informatics, Tokyo, Japan
Volume
3
fYear
2002
fDate
2002
Firstpage
110
Abstract
This paper proposes a text recognition error model called the dual variable length output hidden Markov model (DVHMM) and gives a parameter estimation algorithm based on the EM algorithm. Although existing probabilistic error models are limited to substitution (1, 1), insertion (1, 0), and deletion (0, 1) errors, the DVHMM can handle error patterns of any pair (i, j) of lengths including substitution, insertion, and deletion.
Keywords
document image processing; errors; hidden Markov models; optical character recognition; parameter estimation; probability; DVHMM; OCR; deletion; document recognition; dual variable length output hidden Markov model; insertion; parameter estimation; probabilistic error models; substitution; variable length text recognition error model; Automata; Character recognition; Error correction; Hidden Markov models; Informatics; Matrices; Optical character recognition software; Pattern recognition; Speech recognition; Text recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 2002. Proceedings. 16th International Conference on
ISSN
1051-4651
Print_ISBN
0-7695-1695-X
Type
conf
DOI
10.1109/ICPR.2002.1047807
Filename
1047807
Link To Document