Online Arabic handwriting recognition using continuous Gaussian mixture HMMS

Ghaleb Al-Habian; Khaled Assaleh

doi:10.1109/ICIAS.2007.4658571

Online Arabic handwriting recognition using continuous Gaussian mixture HMMS

Ghaleb Al-Habian
, Khaled Assaleh

American University of Sharjah

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

15 Scopus citations

Abstract

In this paper, we present a recognizer structure aimed at recognizing online Arabic handwriting written in continuous form. The basic units of recognition used are strokes, which are sub-letter parts. To recognize strokes we used Hidden Markov Models (HMMs) to model each stroke. Decision logic was then used to interpret the output of stroke HMMs, converting their output into recognizedwords. Data collected from six writers was used to validate the functionality of the system. Experimental simulation of the proposed system resulted in promising recognition rates (>75%), which is significantly better than currently available solutions.

Original language	English
Title of host publication	2007 International Conference on Intelligent and Advanced Systems, ICIAS 2007
Pages	1183-1186
Number of pages	4
DOIs	https://doi.org/10.1109/ICIAS.2007.4658571
State	Published - 2007
Externally published	Yes
Event	2007 International Conference on Intelligent and Advanced Systems, ICIAS 2007 - Kuala Lumpur, Malaysia Duration: 25 Nov 2007 → 28 Nov 2007

Publication series

Name	2007 International Conference on Intelligent and Advanced Systems, ICIAS 2007

Conference

Conference	2007 International Conference on Intelligent and Advanced Systems, ICIAS 2007
Country/Territory	Malaysia
City	Kuala Lumpur
Period	25/11/07 → 28/11/07

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Access to Document

10.1109/ICIAS.2007.4658571

Cite this

@inproceedings{3f47a1ae74db49c88f02916a8903f16d,

title = "Online Arabic handwriting recognition using continuous Gaussian mixture HMMS",

abstract = "In this paper, we present a recognizer structure aimed at recognizing online Arabic handwriting written in continuous form. The basic units of recognition used are strokes, which are sub-letter parts. To recognize strokes we used Hidden Markov Models (HMMs) to model each stroke. Decision logic was then used to interpret the output of stroke HMMs, converting their output into recognizedwords. Data collected from six writers was used to validate the functionality of the system. Experimental simulation of the proposed system resulted in promising recognition rates (>75\%), which is significantly better than currently available solutions.",

author = "Ghaleb Al-Habian and Khaled Assaleh",

year = "2007",

doi = "10.1109/ICIAS.2007.4658571",

language = "English",

isbn = "1424413559",

series = "2007 International Conference on Intelligent and Advanced Systems, ICIAS 2007",

pages = "1183--1186",

booktitle = "2007 International Conference on Intelligent and Advanced Systems, ICIAS 2007",

note = "2007 International Conference on Intelligent and Advanced Systems, ICIAS 2007 ; Conference date: 25-11-2007 Through 28-11-2007",

}

Al-Habian, G & Assaleh, K 2007, Online Arabic handwriting recognition using continuous Gaussian mixture HMMS. in 2007 International Conference on Intelligent and Advanced Systems, ICIAS 2007., 4658571, 2007 International Conference on Intelligent and Advanced Systems, ICIAS 2007, pp. 1183-1186, 2007 International Conference on Intelligent and Advanced Systems, ICIAS 2007, Kuala Lumpur, Malaysia, 25/11/07. https://doi.org/10.1109/ICIAS.2007.4658571

Online Arabic handwriting recognition using continuous Gaussian mixture HMMS. / Al-Habian, Ghaleb; Assaleh, Khaled.
2007 International Conference on Intelligent and Advanced Systems, ICIAS 2007. 2007. p. 1183-1186 4658571 (2007 International Conference on Intelligent and Advanced Systems, ICIAS 2007).

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

TY - GEN

T1 - Online Arabic handwriting recognition using continuous Gaussian mixture HMMS

AU - Al-Habian, Ghaleb

AU - Assaleh, Khaled

PY - 2007

Y1 - 2007

N2 - In this paper, we present a recognizer structure aimed at recognizing online Arabic handwriting written in continuous form. The basic units of recognition used are strokes, which are sub-letter parts. To recognize strokes we used Hidden Markov Models (HMMs) to model each stroke. Decision logic was then used to interpret the output of stroke HMMs, converting their output into recognizedwords. Data collected from six writers was used to validate the functionality of the system. Experimental simulation of the proposed system resulted in promising recognition rates (>75%), which is significantly better than currently available solutions.

AB - In this paper, we present a recognizer structure aimed at recognizing online Arabic handwriting written in continuous form. The basic units of recognition used are strokes, which are sub-letter parts. To recognize strokes we used Hidden Markov Models (HMMs) to model each stroke. Decision logic was then used to interpret the output of stroke HMMs, converting their output into recognizedwords. Data collected from six writers was used to validate the functionality of the system. Experimental simulation of the proposed system resulted in promising recognition rates (>75%), which is significantly better than currently available solutions.

UR - https://www.scopus.com/pages/publications/57949100835

U2 - 10.1109/ICIAS.2007.4658571

DO - 10.1109/ICIAS.2007.4658571

M3 - Conference contribution

AN - SCOPUS:57949100835

SN - 1424413559

SN - 9781424413553

T3 - 2007 International Conference on Intelligent and Advanced Systems, ICIAS 2007

SP - 1183

EP - 1186

BT - 2007 International Conference on Intelligent and Advanced Systems, ICIAS 2007

T2 - 2007 International Conference on Intelligent and Advanced Systems, ICIAS 2007

Y2 - 25 November 2007 through 28 November 2007

ER -

Online Arabic handwriting recognition using continuous Gaussian mixture HMMS

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this