Direct unsupervised text line extraction from colored historical manuscript images using DCT

Asim Baig; Somaya Al-Maadeed; Ahmed Bouridane; Mohamed Cheriet

doi:10.1007/978-3-319-41501-7_84

Direct unsupervised text line extraction from colored historical manuscript images using DCT

Asim Baig, Somaya Al-Maadeed, Ahmed Bouridane, Mohamed Cheriet

Computer and Information Sciences Department

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

Abstract

Extracting lines of text from a manuscript is an important preprocessing step in many digital paleography applications. These extracted lines play a fundamental part in the identification of the author and/or age of the manuscript. In this paper we present an unsupervised approach to text line extraction in historical manuscripts that can be applied directly to a color manuscript image. Each of the red, green and blue channels are processed separately by applying DCT on them individually. One of the key advantages of this approach is that it can be applied directly to the manuscript image without any preprocessing, training or tuning steps. Extensive testing on complex Arabic handwritten manuscripts shows the effectiveness of the proposed approach.

Original language	English
Title of host publication	Image Analysis and Recognition: Proceedings of the 13th International Conference, ICIAR 2016, in Memory of Mohamed Kamel
Editors	Aurélio Campilho, Fakhri Karray
Place of Publication	London
Publisher	Springer
Pages	753-762
Volume	9730
ISBN (Print)	9783319415000
DOIs	https://doi.org/10.1007/978-3-319-41501-7_84
Publication status	Published - 2016

Publication series

Name	Lecture notes in computer science
Publisher	Springer
ISSN (Electronic)	0302-9743

Keywords

text line extraction
segmentation
DCT
Historical manuscripts
color image processing

Access to Document

10.1007/978-3-319-41501-7_84

Cite this

Baig, A., Al-Maadeed, S., Bouridane, A., & Cheriet, M. (2016). Direct unsupervised text line extraction from colored historical manuscript images using DCT. In A. Campilho, & F. Karray (Eds.), Image Analysis and Recognition: Proceedings of the 13th International Conference, ICIAR 2016, in Memory of Mohamed Kamel (Vol. 9730, pp. 753-762). (Lecture notes in computer science). Springer. https://doi.org/10.1007/978-3-319-41501-7_84

Baig, Asim ; Al-Maadeed, Somaya ; Bouridane, Ahmed et al. / Direct unsupervised text line extraction from colored historical manuscript images using DCT. Image Analysis and Recognition: Proceedings of the 13th International Conference, ICIAR 2016, in Memory of Mohamed Kamel. editor / Aurélio Campilho ; Fakhri Karray. Vol. 9730 London : Springer, 2016. pp. 753-762 (Lecture notes in computer science).

@inbook{91876236254a444c989a6681a4517ee7,

title = "Direct unsupervised text line extraction from colored historical manuscript images using DCT",

abstract = "Extracting lines of text from a manuscript is an important preprocessing step in many digital paleography applications. These extracted lines play a fundamental part in the identification of the author and/or age of the manuscript. In this paper we present an unsupervised approach to text line extraction in historical manuscripts that can be applied directly to a color manuscript image. Each of the red, green and blue channels are processed separately by applying DCT on them individually. One of the key advantages of this approach is that it can be applied directly to the manuscript image without any preprocessing, training or tuning steps. Extensive testing on complex Arabic handwritten manuscripts shows the effectiveness of the proposed approach.",

keywords = "text line extraction, segmentation, DCT, Historical manuscripts, color image processing",

author = "Asim Baig and Somaya Al-Maadeed and Ahmed Bouridane and Mohamed Cheriet",

year = "2016",

doi = "10.1007/978-3-319-41501-7_84",

language = "English",

isbn = "9783319415000",

volume = "9730",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "753--762",

editor = "Aur{\'e}lio Campilho and Fakhri Karray",

booktitle = "Image Analysis and Recognition: Proceedings of the 13th International Conference, ICIAR 2016, in Memory of Mohamed Kamel",

address = "Germany",

}

Baig, A, Al-Maadeed, S, Bouridane, A & Cheriet, M 2016, Direct unsupervised text line extraction from colored historical manuscript images using DCT. in A Campilho & F Karray (eds), Image Analysis and Recognition: Proceedings of the 13th International Conference, ICIAR 2016, in Memory of Mohamed Kamel. vol. 9730, Lecture notes in computer science, Springer, London, pp. 753-762. https://doi.org/10.1007/978-3-319-41501-7_84

Direct unsupervised text line extraction from colored historical manuscript images using DCT. / Baig, Asim; Al-Maadeed, Somaya; Bouridane, Ahmed et al.
Image Analysis and Recognition: Proceedings of the 13th International Conference, ICIAR 2016, in Memory of Mohamed Kamel. ed. / Aurélio Campilho; Fakhri Karray. Vol. 9730 London: Springer, 2016. p. 753-762 (Lecture notes in computer science).

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

TY - CHAP

T1 - Direct unsupervised text line extraction from colored historical manuscript images using DCT

AU - Baig, Asim

AU - Al-Maadeed, Somaya

AU - Bouridane, Ahmed

AU - Cheriet, Mohamed

PY - 2016

Y1 - 2016

N2 - Extracting lines of text from a manuscript is an important preprocessing step in many digital paleography applications. These extracted lines play a fundamental part in the identification of the author and/or age of the manuscript. In this paper we present an unsupervised approach to text line extraction in historical manuscripts that can be applied directly to a color manuscript image. Each of the red, green and blue channels are processed separately by applying DCT on them individually. One of the key advantages of this approach is that it can be applied directly to the manuscript image without any preprocessing, training or tuning steps. Extensive testing on complex Arabic handwritten manuscripts shows the effectiveness of the proposed approach.

AB - Extracting lines of text from a manuscript is an important preprocessing step in many digital paleography applications. These extracted lines play a fundamental part in the identification of the author and/or age of the manuscript. In this paper we present an unsupervised approach to text line extraction in historical manuscripts that can be applied directly to a color manuscript image. Each of the red, green and blue channels are processed separately by applying DCT on them individually. One of the key advantages of this approach is that it can be applied directly to the manuscript image without any preprocessing, training or tuning steps. Extensive testing on complex Arabic handwritten manuscripts shows the effectiveness of the proposed approach.

KW - text line extraction

KW - segmentation

KW - DCT

KW - Historical manuscripts

KW - color image processing

U2 - 10.1007/978-3-319-41501-7_84

DO - 10.1007/978-3-319-41501-7_84

M3 - Chapter

SN - 9783319415000

VL - 9730

T3 - Lecture notes in computer science

SP - 753

EP - 762

BT - Image Analysis and Recognition: Proceedings of the 13th International Conference, ICIAR 2016, in Memory of Mohamed Kamel

A2 - Campilho, Aurélio

A2 - Karray, Fakhri

PB - Springer

CY - London

ER -

Baig A, Al-Maadeed S, Bouridane A, Cheriet M. Direct unsupervised text line extraction from colored historical manuscript images using DCT. In Campilho A, Karray F, editors, Image Analysis and Recognition: Proceedings of the 13th International Conference, ICIAR 2016, in Memory of Mohamed Kamel. Vol. 9730. London: Springer. 2016. p. 753-762. (Lecture notes in computer science). doi: 10.1007/978-3-319-41501-7_84

Direct unsupervised text line extraction from colored historical manuscript images using DCT

Abstract

Publication series

Keywords

Access to Document

Fingerprint

Cite this