Ground-Truth and Metric for the Evaluation of Arabic Handwritten Character Segmentation

Yousef Elarian; Abdelmalek Zidouri; Wasfi Al-Khatib

doi:10.1109/ICFHR.2014.134

Ground-Truth and Metric for the Evaluation of Arabic Handwritten Character Segmentation

Yousef Elarian, Abdelmalek Zidouri, Wasfi Al-Khatib

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

4 Scopus citations

Abstract

In this paper, we present a character-level ground-truth for an Arabic dataset of 8,640 character-shapes along with an evaluation metric that is adapted from image segmentation. These tools together constitute a benchmark for character-segmentation. We demonstrate the use of this benchmark on some segmentation algorithms and report their quantitative results in bits. Our approach can be extended to other scripts.

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	766-770
Number of pages	5
ISBN (Electronic)	9781479943340
DOIs	https://doi.org/10.1109/ICFHR.2014.134
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 handwriting
entropy-based metric
ground-truth
segmentation

ASJC Scopus subject areas

Computer Science Applications
Computer Vision and Pattern Recognition

Access to Document

10.1109/ICFHR.2014.134

Cite this

Elarian, Y., Zidouri, A., & Al-Khatib, W. (2014). Ground-Truth and Metric for the Evaluation of Arabic Handwritten Character Segmentation. In Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014 (pp. 766-770). Article 6981113 (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.2014.134

Elarian, Yousef ; Zidouri, Abdelmalek ; Al-Khatib, Wasfi. / Ground-Truth and Metric for the Evaluation of Arabic Handwritten Character Segmentation. Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 766-770 (Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR).

@inproceedings{42a6c0d67b734f22b2a3eddda2cfc775,

title = "Ground-Truth and Metric for the Evaluation of Arabic Handwritten Character Segmentation",

abstract = "In this paper, we present a character-level ground-truth for an Arabic dataset of 8,640 character-shapes along with an evaluation metric that is adapted from image segmentation. These tools together constitute a benchmark for character-segmentation. We demonstrate the use of this benchmark on some segmentation algorithms and report their quantitative results in bits. Our approach can be extended to other scripts.",

keywords = "Arabic handwriting, entropy-based metric, ground-truth, segmentation",

author = "Yousef Elarian and Abdelmalek Zidouri and Wasfi Al-Khatib",

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

year = "2014",

month = dec,

day = "9",

doi = "10.1109/ICFHR.2014.134",

language = "English",

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

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

pages = "766--770",

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

address = "United States",

}

Elarian, Y, Zidouri, A & Al-Khatib, W 2014, Ground-Truth and Metric for the Evaluation of Arabic Handwritten Character Segmentation. in Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014., 6981113, Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR, vol. 2014-December, Institute of Electrical and Electronics Engineers Inc., pp. 766-770. https://doi.org/10.1109/ICFHR.2014.134

Ground-Truth and Metric for the Evaluation of Arabic Handwritten Character Segmentation. / Elarian, Yousef; Zidouri, Abdelmalek; Al-Khatib, Wasfi.
Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 766-770 6981113 (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 - Ground-Truth and Metric for the Evaluation of Arabic Handwritten Character Segmentation

AU - Elarian, Yousef

AU - Zidouri, Abdelmalek

AU - Al-Khatib, Wasfi

PY - 2014/12/9

Y1 - 2014/12/9

N2 - In this paper, we present a character-level ground-truth for an Arabic dataset of 8,640 character-shapes along with an evaluation metric that is adapted from image segmentation. These tools together constitute a benchmark for character-segmentation. We demonstrate the use of this benchmark on some segmentation algorithms and report their quantitative results in bits. Our approach can be extended to other scripts.

AB - In this paper, we present a character-level ground-truth for an Arabic dataset of 8,640 character-shapes along with an evaluation metric that is adapted from image segmentation. These tools together constitute a benchmark for character-segmentation. We demonstrate the use of this benchmark on some segmentation algorithms and report their quantitative results in bits. Our approach can be extended to other scripts.

KW - Arabic handwriting

KW - entropy-based metric

KW - ground-truth

KW - segmentation

UR - http://www.scopus.com/inward/record.url?scp=84942233302&partnerID=8YFLogxK

U2 - 10.1109/ICFHR.2014.134

DO - 10.1109/ICFHR.2014.134

M3 - Conference contribution

AN - SCOPUS:84942233302

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

SP - 766

EP - 770

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

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Elarian Y, Zidouri A, Al-Khatib W. Ground-Truth and Metric for the Evaluation of Arabic Handwritten Character Segmentation. In Proceedings - 14th International Conference on Frontiers in Handwriting Recognition, ICFHR 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 766-770. 6981113. (Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR). doi: 10.1109/ICFHR.2014.134

Ground-Truth and Metric for the Evaluation of Arabic Handwritten Character Segmentation

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this