On-line handwritten English word recognition based on cascade connection of character HMMS

Wei Zhao; Jia Feng Liu; Xiang Long Tang

On-line handwritten English word recognition based on cascade connection of character HMMS

Wei Zhao^*
, Jia Feng Liu
, Xiang Long Tang

^*Corresponding author for this work

School of Computer Science and Technology, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Scopus citations

Abstract

In this paper, a Cascade Connection Hidden Markov Model (CCHMM) method for on-line English word recognition is proposed. This model, which allows state transition, skip and duration, extends the way of HMM pattern description of handwriting English words. According to the statistic probabilities, the behavior of handwriting curve may be depicted more precisely. The Viterbi algorithm for the cascade connection model may be applied after the whole sample series of a word is input Compared with the method of creating models for each word in lexicon, this method gives a faster recognition speed. Experiments show that CCHMM approach could obtain 89.26% recognition rate for the first candidate, while the combination of character and ligature HMM method's first candidate is 82.34%.

Original language	English
Title of host publication	Proceedings of 2002 International Conference on Machine Learning and Cybernetics
Pages	1758-1761
Number of pages	4
State	Published - 2002
Externally published	Yes
Event	Proceedings of 2002 International Conference on Machine Learning and Cybernetics - Beijing, China Duration: 4 Nov 2002 → 5 Nov 2002

Publication series

Name	Proceedings of 2002 International Conference on Machine Learning and Cybernetics
Volume	4

Conference

Conference	Proceedings of 2002 International Conference on Machine Learning and Cybernetics
Country/Territory	China
City	Beijing
Period	4/11/02 → 5/11/02

Keywords

Cascade connection Hidden Markov model
Handwritten word recognition
Inter-model state transition probability

Cite this

@inproceedings{735dc84a700d47ad9a64dd4cfe36fe13,

title = "On-line handwritten English word recognition based on cascade connection of character HMMS",

abstract = "In this paper, a Cascade Connection Hidden Markov Model (CCHMM) method for on-line English word recognition is proposed. This model, which allows state transition, skip and duration, extends the way of HMM pattern description of handwriting English words. According to the statistic probabilities, the behavior of handwriting curve may be depicted more precisely. The Viterbi algorithm for the cascade connection model may be applied after the whole sample series of a word is input Compared with the method of creating models for each word in lexicon, this method gives a faster recognition speed. Experiments show that CCHMM approach could obtain 89.26\% recognition rate for the first candidate, while the combination of character and ligature HMM method's first candidate is 82.34\%.",

keywords = "Cascade connection Hidden Markov model, Handwritten word recognition, Inter-model state transition probability",

author = "Wei Zhao and Liu, \{Jia Feng\} and Tang, \{Xiang Long\}",

year = "2002",

language = "英语",

isbn = "0780375084",

series = "Proceedings of 2002 International Conference on Machine Learning and Cybernetics",

pages = "1758--1761",

booktitle = "Proceedings of 2002 International Conference on Machine Learning and Cybernetics",

note = "Proceedings of 2002 International Conference on Machine Learning and Cybernetics ; Conference date: 04-11-2002 Through 05-11-2002",

}

Zhao, W, Liu, JF & Tang, XL 2002, On-line handwritten English word recognition based on cascade connection of character HMMS. in Proceedings of 2002 International Conference on Machine Learning and Cybernetics. Proceedings of 2002 International Conference on Machine Learning and Cybernetics, vol. 4, pp. 1758-1761, Proceedings of 2002 International Conference on Machine Learning and Cybernetics, Beijing, China, 4/11/02.

On-line handwritten English word recognition based on cascade connection of character HMMS. / Zhao, Wei; Liu, Jia Feng; Tang, Xiang Long.
Proceedings of 2002 International Conference on Machine Learning and Cybernetics. 2002. p. 1758-1761 (Proceedings of 2002 International Conference on Machine Learning and Cybernetics; Vol. 4).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - On-line handwritten English word recognition based on cascade connection of character HMMS

AU - Zhao, Wei

AU - Liu, Jia Feng

AU - Tang, Xiang Long

PY - 2002

Y1 - 2002

N2 - In this paper, a Cascade Connection Hidden Markov Model (CCHMM) method for on-line English word recognition is proposed. This model, which allows state transition, skip and duration, extends the way of HMM pattern description of handwriting English words. According to the statistic probabilities, the behavior of handwriting curve may be depicted more precisely. The Viterbi algorithm for the cascade connection model may be applied after the whole sample series of a word is input Compared with the method of creating models for each word in lexicon, this method gives a faster recognition speed. Experiments show that CCHMM approach could obtain 89.26% recognition rate for the first candidate, while the combination of character and ligature HMM method's first candidate is 82.34%.

AB - In this paper, a Cascade Connection Hidden Markov Model (CCHMM) method for on-line English word recognition is proposed. This model, which allows state transition, skip and duration, extends the way of HMM pattern description of handwriting English words. According to the statistic probabilities, the behavior of handwriting curve may be depicted more precisely. The Viterbi algorithm for the cascade connection model may be applied after the whole sample series of a word is input Compared with the method of creating models for each word in lexicon, this method gives a faster recognition speed. Experiments show that CCHMM approach could obtain 89.26% recognition rate for the first candidate, while the combination of character and ligature HMM method's first candidate is 82.34%.

KW - Cascade connection Hidden Markov model

KW - Handwritten word recognition

KW - Inter-model state transition probability

UR - https://www.scopus.com/pages/publications/0036926748

M3 - 会议稿件

AN - SCOPUS:0036926748

SN - 0780375084

T3 - Proceedings of 2002 International Conference on Machine Learning and Cybernetics

SP - 1758

EP - 1761

BT - Proceedings of 2002 International Conference on Machine Learning and Cybernetics

T2 - Proceedings of 2002 International Conference on Machine Learning and Cybernetics

Y2 - 4 November 2002 through 5 November 2002

ER -

On-line handwritten English word recognition based on cascade connection of character HMMS

Abstract

Publication series

Conference

Keywords

Other files and links

Fingerprint

Cite this