Paper Info
Title
Minimum classification error training for online handwriting recognition.
Abstract
This paper describes an application of the Minimum Classification Error (MCE) criterion to the problem of recognizing online unconstrained-style characters and words. We describe an HMM-based, character and word-level MCE training aimed at minimizing the character or word error rate while enabling flexibility in writing style through the use of multiple allographs per character. Experiments on a writer-independent character recognition task covering alpha-numerical characters and keyboard symbols show that the MCE criterion achieves more than 30 percent character error rate reduction compared to the baseline Maximum Likelihood-based system. Word recognition results, on vocabularies of 5k to 10k, show that MCE training achieves around 17 percent word error rate reduction when compared to the baseline Maximum Likelihood system.
Year
DOI
Venue
2006
10.1109/TPAMI.2006.146
IEEE Trans. Pattern Anal. Mach. Intell.
Keywords
Field
DocType
word recognition result,writer-independent character recognition task,minimum classification error training,percent word error rate,word error rate,online unconstrained-style character,percent character error rate,alpha-numerical character,mce training,mce criterion,word-level mce training,online handwriting recognition,finite state machine,hidden markov model,hidden markov models,hmm,documentation,image classification,word recognition,writing style,artificial intelligence,dynamic programming,writing,maximum likelihood,algorithms,handwriting recognition
Computer science,Handwriting recognition,Artificial intelligence,Contextual image classification,Word processing,Computer vision,Pattern recognition,Markov model,Word error rate,Word recognition,Speech recognition,Hidden Markov model,Vocabulary
Journal
Volume
Issue
ISSN
28
7
0162-8828
Citations 
PageRank 
References 
20
0.86
23
Authors
1
Name
Order
Citations
PageRank
Alain Biem128818.64