Title :
Offline grammar-based recognition of handwritten sentences
Author :
Zimmermann, Matthias ; Chappelier, Jean-Cédric ; Bunke, Horst
Author_Institution :
Int. Comput. Sci. Inst., Berkeley, CA, USA
fDate :
5/1/2006 12:00:00 AM
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;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2006.103
