Handwritten word recognition using segmentation-free hidden Markov modeling and segmentation-based dynamic programming techniques

Author

Mohamed, Magdi ; Gader, Paul

Author_Institution

Dept. of Electr. & Comput. Eng., Missouri Univ., Columbia, MO, USA

Volume

18

Issue

5

fYear

1996

fDate

5/1/1996 12:00:00 AM

Firstpage

548

Lastpage

554

Abstract

A lexicon-based, handwritten word recognition system combining segmentation-free and segmentation-based techniques is described. The segmentation-free technique constructs a continuous density hidden Markov model for each lexicon string. The segmentation-based technique uses dynamic programming to match word images and strings. The combination module uses differences in classifier capabilities to achieve significantly better performance

Keywords

character recognition; computer vision; dynamic programming; hidden Markov models; image matching; image segmentation; learning systems; neural nets; dynamic programming; handwritten word recognition; hidden Markov modeling; image classifier; image matching; lexicon string; neural networks; segmentation; Algorithm design and analysis; Character recognition; Design engineering; Fuzzy logic; Handwriting recognition; Hidden Markov models; Image segmentation; Neural networks; Shape; System testing;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/34.494644

Filename

494644