Improvements in Sub-character HMM Model Based Arabic Text Recognition

Irfan Ahmad; Gernot A. Fink; Sabri A. Mahmoud

doi:10.1109/ICFHR.2014.96

Improvements in Sub-character HMM Model Based Arabic Text Recognition

Irfan Ahmad, Gernot A. Fink, Sabri A. Mahmoud

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

26 Scopus citations

Abstract

Sub-character HMM models for Arabic text recognition allow sharing of common patterns between different position-dependent shape forms of an Arabic character as well as between different characters. The number of HMMs gets reduced considerably while still capturing the variations in shape patterns. This results in a compact, efficient, and robust recognizer with reduced model set. In the current paper we are presenting our recent improvements in sub-character HMM modeling for Arabic text recognition where we use special 'connector' and 'space' models. Additionally we investigated contextual sub-characters HMMs for text recognition. We also present multi-stream contextual sub-character HMMs where the features calculated from a sliding window frame form one stream and its derivative features are part of the second stream. We report state-of-the-art results on the IFN/ENIT (benchmark) database of handwritten Arabic text and the recognition rate of 85.12% on sets outperforms previously published results.

Original language	English
Title of host publication	Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	537-542
Number of pages	6
ISBN (Electronic)	9781479943340
DOIs	https://doi.org/10.1109/ICFHR.2014.96
State	Published - 9 Dec 2014

Publication series

Name	Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR
Volume	2014-December
ISSN (Print)	2167-6445
ISSN (Electronic)	2167-6453

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

Keywords

Arabic text recognition
Sub-character HMM
contextual-HMM
multi-stream HMM
space modeling

ASJC Scopus subject areas

Computer Science Applications
Computer Vision and Pattern Recognition

Access to Document

10.1109/ICFHR.2014.96

Cite this

Ahmad, I., Fink, G. A., & Mahmoud, S. A. (2014). Improvements in Sub-character HMM Model Based Arabic Text Recognition. In Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014 (pp. 537-542). Article 6981075 (Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR; Vol. 2014-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICFHR.2014.96

Ahmad, Irfan ; Fink, Gernot A. ; Mahmoud, Sabri A. / Improvements in Sub-character HMM Model Based Arabic Text Recognition. Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 537-542 (Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR).

@inproceedings{8d65755e0e3f4424875fb5ae8ef07cf0,

title = "Improvements in Sub-character HMM Model Based Arabic Text Recognition",

abstract = "Sub-character HMM models for Arabic text recognition allow sharing of common patterns between different position-dependent shape forms of an Arabic character as well as between different characters. The number of HMMs gets reduced considerably while still capturing the variations in shape patterns. This results in a compact, efficient, and robust recognizer with reduced model set. In the current paper we are presenting our recent improvements in sub-character HMM modeling for Arabic text recognition where we use special 'connector' and 'space' models. Additionally we investigated contextual sub-characters HMMs for text recognition. We also present multi-stream contextual sub-character HMMs where the features calculated from a sliding window frame form one stream and its derivative features are part of the second stream. We report state-of-the-art results on the IFN/ENIT (benchmark) database of handwritten Arabic text and the recognition rate of 85.12% on sets outperforms previously published results.",

keywords = "Arabic text recognition, Sub-character HMM, contextual-HMM, multi-stream HMM, space modeling",

author = "Irfan Ahmad and Fink, {Gernot A.} and Mahmoud, {Sabri A.}",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.",

year = "2014",

month = dec,

day = "9",

doi = "10.1109/ICFHR.2014.96",

language = "English",

series = "Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "537--542",

booktitle = "Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014",

address = "United States",

}

Ahmad, I, Fink, GA & Mahmoud, SA 2014, Improvements in Sub-character HMM Model Based Arabic Text Recognition. in Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014., 6981075, Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR, vol. 2014-December, Institute of Electrical and Electronics Engineers Inc., pp. 537-542. https://doi.org/10.1109/ICFHR.2014.96

Improvements in Sub-character HMM Model Based Arabic Text Recognition. / Ahmad, Irfan; Fink, Gernot A.; Mahmoud, Sabri A.
Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 537-542 6981075 (Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR; Vol. 2014-December).

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

TY - GEN

T1 - Improvements in Sub-character HMM Model Based Arabic Text Recognition

AU - Ahmad, Irfan

AU - Fink, Gernot A.

AU - Mahmoud, Sabri A.

PY - 2014/12/9

Y1 - 2014/12/9

N2 - Sub-character HMM models for Arabic text recognition allow sharing of common patterns between different position-dependent shape forms of an Arabic character as well as between different characters. The number of HMMs gets reduced considerably while still capturing the variations in shape patterns. This results in a compact, efficient, and robust recognizer with reduced model set. In the current paper we are presenting our recent improvements in sub-character HMM modeling for Arabic text recognition where we use special 'connector' and 'space' models. Additionally we investigated contextual sub-characters HMMs for text recognition. We also present multi-stream contextual sub-character HMMs where the features calculated from a sliding window frame form one stream and its derivative features are part of the second stream. We report state-of-the-art results on the IFN/ENIT (benchmark) database of handwritten Arabic text and the recognition rate of 85.12% on sets outperforms previously published results.

AB - Sub-character HMM models for Arabic text recognition allow sharing of common patterns between different position-dependent shape forms of an Arabic character as well as between different characters. The number of HMMs gets reduced considerably while still capturing the variations in shape patterns. This results in a compact, efficient, and robust recognizer with reduced model set. In the current paper we are presenting our recent improvements in sub-character HMM modeling for Arabic text recognition where we use special 'connector' and 'space' models. Additionally we investigated contextual sub-characters HMMs for text recognition. We also present multi-stream contextual sub-character HMMs where the features calculated from a sliding window frame form one stream and its derivative features are part of the second stream. We report state-of-the-art results on the IFN/ENIT (benchmark) database of handwritten Arabic text and the recognition rate of 85.12% on sets outperforms previously published results.

KW - Arabic text recognition

KW - Sub-character HMM

KW - contextual-HMM

KW - multi-stream HMM

KW - space modeling

UR - http://www.scopus.com/inward/record.url?scp=84942249878&partnerID=8YFLogxK

U2 - 10.1109/ICFHR.2014.96

DO - 10.1109/ICFHR.2014.96

M3 - Conference contribution

AN - SCOPUS:84942249878

T3 - Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR

SP - 537

EP - 542

BT - Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Ahmad I, Fink GA, Mahmoud SA. Improvements in Sub-character HMM Model Based Arabic Text Recognition. In Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 537-542. 6981075. (Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR). doi: 10.1109/ICFHR.2014.96

Improvements in Sub-character HMM Model Based Arabic Text Recognition

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this