Offline grammar-based recognition of handwritten sentences

Author

Zimmermann, Matthias ; Chappelier, Jean-Cédric ; Bunke, Horst

Author_Institution

Int. Comput. Sci. Inst., Berkeley, CA, USA

Volume

28

Issue

5

fYear

2006

fDate

5/1/2006 12:00:00 AM

Firstpage

818

Lastpage

821

Abstract

This paper proposes a sequential coupling of a hidden Markov model (HMM) recognizer for offline handwritten English sentences with a probabilistic bottom-up chart parser using stochastic context-free grammars (SCFG) extracted from a text corpus. Based on extensive experiments, we conclude that syntax analysis helps to improve recognition rates significantly.

Keywords

context-free grammars; handwritten character recognition; hidden Markov models; text analysis; handwritten English sentences; hidden Markov model; offline grammar-based recognition; probabilistic bottom-up chart parser; stochastic context-free grammars; syntax analysis; text corpus; Character recognition; Error analysis; Handwriting recognition; Hidden Markov models; Natural languages; Optical character recognition software; Speech analysis; Speech recognition; Stochastic processes; Text recognition; Optical character recognition; handwriting analysis; natural language parsing and understanding.; Algorithms; Artificial Intelligence; Automatic Data Processing; Handwriting; Image Enhancement; Image Interpretation, Computer-Assisted; Information Storage and Retrieval; Online Systems; Pattern Recognition, Automated; Semantics;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/TPAMI.2006.103

Filename

1608043