Detecting dense foreground stripes in Arabic handwriting for accurate baseline positioning

Felix Stahlberg, Stephan Vogel

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Since Arabic script has a strong baseline, many state-of-the-art recognition systems for handwritten Arabic make use of baseline-dependent features. For printed Arabic, the baseline can be detected reliably by finding the maximum in the horizontal projection profile or the Hough transformed image. However, the performance of these methods drops significantly on handwritten Arabic. In this work, we present a novel approach to baseline detection in handwritten Arabic which is based on the detection of stripes in the image with dense foreground. Such a stripe usually corresponds to the area between lower and upper baseline. Our method outperforms a previous method by 22.4% relative for the task of finding acceptable baselines in Tunisian town names in the IFN/ENIT database.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Document Analysis and Recognition, ICDAR
PublisherIEEE Computer Society
Pages361-365
Number of pages5
Volume2015-November
ISBN (Print)9781479918058
DOIs
Publication statusPublished - 20 Nov 2015
Event13th International Conference on Document Analysis and Recognition, ICDAR 2015 - Nancy, France
Duration: 23 Aug 201526 Aug 2015

Other

Other13th International Conference on Document Analysis and Recognition, ICDAR 2015
CountryFrance
CityNancy
Period23/8/1526/8/15

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Stahlberg, F., & Vogel, S. (2015). Detecting dense foreground stripes in Arabic handwriting for accurate baseline positioning. In Proceedings of the International Conference on Document Analysis and Recognition, ICDAR (Vol. 2015-November, pp. 361-365). [7333784] IEEE Computer Society. https://doi.org/10.1109/ICDAR.2015.7333784

Detecting dense foreground stripes in Arabic handwriting for accurate baseline positioning. / Stahlberg, Felix; Vogel, Stephan.

Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. Vol. 2015-November IEEE Computer Society, 2015. p. 361-365 7333784.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Stahlberg, F & Vogel, S 2015, Detecting dense foreground stripes in Arabic handwriting for accurate baseline positioning. in Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. vol. 2015-November, 7333784, IEEE Computer Society, pp. 361-365, 13th International Conference on Document Analysis and Recognition, ICDAR 2015, Nancy, France, 23/8/15. https://doi.org/10.1109/ICDAR.2015.7333784
Stahlberg F, Vogel S. Detecting dense foreground stripes in Arabic handwriting for accurate baseline positioning. In Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. Vol. 2015-November. IEEE Computer Society. 2015. p. 361-365. 7333784 https://doi.org/10.1109/ICDAR.2015.7333784
Stahlberg, Felix ; Vogel, Stephan. / Detecting dense foreground stripes in Arabic handwriting for accurate baseline positioning. Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. Vol. 2015-November IEEE Computer Society, 2015. pp. 361-365
@inproceedings{f845bacd38584f1aa9956d83981fa6e7,
title = "Detecting dense foreground stripes in Arabic handwriting for accurate baseline positioning",
abstract = "Since Arabic script has a strong baseline, many state-of-the-art recognition systems for handwritten Arabic make use of baseline-dependent features. For printed Arabic, the baseline can be detected reliably by finding the maximum in the horizontal projection profile or the Hough transformed image. However, the performance of these methods drops significantly on handwritten Arabic. In this work, we present a novel approach to baseline detection in handwritten Arabic which is based on the detection of stripes in the image with dense foreground. Such a stripe usually corresponds to the area between lower and upper baseline. Our method outperforms a previous method by 22.4{\%} relative for the task of finding acceptable baselines in Tunisian town names in the IFN/ENIT database.",
author = "Felix Stahlberg and Stephan Vogel",
year = "2015",
month = "11",
day = "20",
doi = "10.1109/ICDAR.2015.7333784",
language = "English",
isbn = "9781479918058",
volume = "2015-November",
pages = "361--365",
booktitle = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Detecting dense foreground stripes in Arabic handwriting for accurate baseline positioning

AU - Stahlberg, Felix

AU - Vogel, Stephan

PY - 2015/11/20

Y1 - 2015/11/20

N2 - Since Arabic script has a strong baseline, many state-of-the-art recognition systems for handwritten Arabic make use of baseline-dependent features. For printed Arabic, the baseline can be detected reliably by finding the maximum in the horizontal projection profile or the Hough transformed image. However, the performance of these methods drops significantly on handwritten Arabic. In this work, we present a novel approach to baseline detection in handwritten Arabic which is based on the detection of stripes in the image with dense foreground. Such a stripe usually corresponds to the area between lower and upper baseline. Our method outperforms a previous method by 22.4% relative for the task of finding acceptable baselines in Tunisian town names in the IFN/ENIT database.

AB - Since Arabic script has a strong baseline, many state-of-the-art recognition systems for handwritten Arabic make use of baseline-dependent features. For printed Arabic, the baseline can be detected reliably by finding the maximum in the horizontal projection profile or the Hough transformed image. However, the performance of these methods drops significantly on handwritten Arabic. In this work, we present a novel approach to baseline detection in handwritten Arabic which is based on the detection of stripes in the image with dense foreground. Such a stripe usually corresponds to the area between lower and upper baseline. Our method outperforms a previous method by 22.4% relative for the task of finding acceptable baselines in Tunisian town names in the IFN/ENIT database.

UR - http://www.scopus.com/inward/record.url?scp=84962609736&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962609736&partnerID=8YFLogxK

U2 - 10.1109/ICDAR.2015.7333784

DO - 10.1109/ICDAR.2015.7333784

M3 - Conference contribution

SN - 9781479918058

VL - 2015-November

SP - 361

EP - 365

BT - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

PB - IEEE Computer Society

ER -