DocumentCode
3056921
Title
Performance evaluation of an HMM based OCR system
Author
Anigbogu, J.C. ; Belai, A.
Author_Institution
CRIN-CNRS/Inria Lorraine, Vandoeuvre-les-Nancy, France
fYear
1992
fDate
30 Aug-3 Sep 1992
Firstpage
565
Lastpage
568
Abstract
Presents a performance analysis of a first order hidden Markov model based OCR system. Trade-offs between accuracy in terms of recognition rates and complexity in terms of the number of states in the model are discussed. For most fonts, optimal performance is achieved with 6-state models. With adequate heuristics and reliable post-processors, 5-state and even 4-state models give reasonable performances (up to 99.60% at 4-states)
Keywords
hidden Markov models; optical character recognition; 4-state models; 5-state models; 6-state models; accuracy; complexity; first order hidden Markov model based OCR system; fonts; performance analysis; performance evaluation; recognition rates; Algorithm design and analysis; Character recognition; Hidden Markov models; Merging; Optical character recognition software; Performance analysis; Shape; Testing; Text recognition; Viterbi algorithm;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on
Conference_Location
The Hague
Print_ISBN
0-8186-2915-0
Type
conf
DOI
10.1109/ICPR.1992.201697
Filename
201697
Link To Document