Binarization Free Layout Analysis for Arabic Historical Documents Using Fully Convolutional Networks

Berat Kurar Barakat; Jihad El-Sana

doi:10.1109/ASAR.2018.8480333

Binarization Free Layout Analysis for Arabic Historical Documents Using Fully Convolutional Networks

Berat Kurar Barakat, Jihad El-Sana

Department of Computer Science

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

27 Scopus citations

Abstract

We present a Fully Convolutional Network based method for layout analysis of non-binarized historical Arabic manuscripts. The document image is segmented into main text and side text regions by dense pixel prediction. Convolutional part of the network can learn useful features from the non-binarized document images and is robust to degradation and uncontrained layouts. We have evaluated the proposed method on a private dataset containing challenging historical Arabic manuscripts to demonstrate it effectiveness.

Original language	English
Title of host publication	2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018
Publisher	Institute of Electrical and Electronics Engineers
Pages	151-155
Number of pages	5
ISBN (Electronic)	9781538614594
DOIs	https://doi.org/10.1109/ASAR.2018.8480333
State	Published - 2 Oct 2018
Event	2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018 - London, United Kingdom Duration: 12 Mar 2018 → 14 Mar 2018

Publication series

Name	2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018

Conference

Conference	2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018
Country/Territory	United Kingdom
City	London
Period	12/03/18 → 14/03/18

ASJC Scopus subject areas

Signal Processing
Linguistics and Language
Computer Vision and Pattern Recognition

Access to Document

10.1109/ASAR.2018.8480333

Cite this

Barakat, B. K., & El-Sana, J. (2018). Binarization Free Layout Analysis for Arabic Historical Documents Using Fully Convolutional Networks. In 2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018 (pp. 151-155). Article 8480333 (2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ASAR.2018.8480333

Barakat, Berat Kurar ; El-Sana, Jihad. / Binarization Free Layout Analysis for Arabic Historical Documents Using Fully Convolutional Networks. 2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018. Institute of Electrical and Electronics Engineers, 2018. pp. 151-155 (2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018).

@inproceedings{ec59d2bd527949dbb775bce95077a172,

title = "Binarization Free Layout Analysis for Arabic Historical Documents Using Fully Convolutional Networks",

abstract = "We present a Fully Convolutional Network based method for layout analysis of non-binarized historical Arabic manuscripts. The document image is segmented into main text and side text regions by dense pixel prediction. Convolutional part of the network can learn useful features from the non-binarized document images and is robust to degradation and uncontrained layouts. We have evaluated the proposed method on a private dataset containing challenging historical Arabic manuscripts to demonstrate it effectiveness.",

author = "Barakat, {Berat Kurar} and Jihad El-Sana",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018 ; Conference date: 12-03-2018 Through 14-03-2018",

year = "2018",

month = oct,

day = "2",

doi = "10.1109/ASAR.2018.8480333",

language = "English",

series = "2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "151--155",

booktitle = "2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018",

address = "United States",

}

Barakat, BK & El-Sana, J 2018, Binarization Free Layout Analysis for Arabic Historical Documents Using Fully Convolutional Networks. in 2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018., 8480333, 2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018, Institute of Electrical and Electronics Engineers, pp. 151-155, 2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018, London, United Kingdom, 12/03/18. https://doi.org/10.1109/ASAR.2018.8480333

Binarization Free Layout Analysis for Arabic Historical Documents Using Fully Convolutional Networks. / Barakat, Berat Kurar; El-Sana, Jihad.
2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018. Institute of Electrical and Electronics Engineers, 2018. p. 151-155 8480333 (2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018).

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

TY - GEN

T1 - Binarization Free Layout Analysis for Arabic Historical Documents Using Fully Convolutional Networks

AU - Barakat, Berat Kurar

AU - El-Sana, Jihad

PY - 2018/10/2

Y1 - 2018/10/2

N2 - We present a Fully Convolutional Network based method for layout analysis of non-binarized historical Arabic manuscripts. The document image is segmented into main text and side text regions by dense pixel prediction. Convolutional part of the network can learn useful features from the non-binarized document images and is robust to degradation and uncontrained layouts. We have evaluated the proposed method on a private dataset containing challenging historical Arabic manuscripts to demonstrate it effectiveness.

AB - We present a Fully Convolutional Network based method for layout analysis of non-binarized historical Arabic manuscripts. The document image is segmented into main text and side text regions by dense pixel prediction. Convolutional part of the network can learn useful features from the non-binarized document images and is robust to degradation and uncontrained layouts. We have evaluated the proposed method on a private dataset containing challenging historical Arabic manuscripts to demonstrate it effectiveness.

UR - http://www.scopus.com/inward/record.url?scp=85056183861&partnerID=8YFLogxK

U2 - 10.1109/ASAR.2018.8480333

DO - 10.1109/ASAR.2018.8480333

M3 - Conference contribution

AN - SCOPUS:85056183861

T3 - 2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018

SP - 151

EP - 155

BT - 2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018

PB - Institute of Electrical and Electronics Engineers

T2 - 2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018

Y2 - 12 March 2018 through 14 March 2018

ER -

Barakat BK, El-Sana J. Binarization Free Layout Analysis for Arabic Historical Documents Using Fully Convolutional Networks. In 2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018. Institute of Electrical and Electronics Engineers. 2018. p. 151-155. 8480333. (2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018). doi: 10.1109/ASAR.2018.8480333

Binarization Free Layout Analysis for Arabic Historical Documents Using Fully Convolutional Networks

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this