ASAR 2018 Competition Page Layout Analysis Using Fully Convolutional Networks

Ahmad Droby; Berat Kurar Barakat; Jihad El-Sana

doi:10.1109/ASAR.2018.8480326

ASAR 2018 Competition Page Layout Analysis Using Fully Convolutional Networks

Ahmad Droby, Berat Kurar Barakat, Jihad El-Sana

Department of Computer Science

Ben-Gurion University of the Negev

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

Abstract

This technical report presents a Fully Convolutional Network based method for layout analysis of benchmarking dataset provided by the competition. The document image is segmented into text and non-text zones by dense pixel prediction. Convolutional part of the network can learn useful features from the document images and is robust to uncontrained layouts. We have evaluated the zone segmentation with average black pixel rate, over-segmentation error, under-segmentation error, correct-segmentation, missed-segmentation error, false alarm error, overall block error rate whereas the zone classification with precision, recall, F1-measure and average class accuracy on both pixel and block levels.

Original language	American English
Title of host publication	2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018
Pages	161-164
Number of pages	4
ISBN (Electronic)	9781538614594
DOIs	https://doi.org/10.1109/ASAR.2018.8480326
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

All Science Journal Classification (ASJC) codes

Signal Processing
Linguistics and Language
Computer Vision and Pattern Recognition

Access to Document

10.1109/ASAR.2018.8480326

Cite this

Droby, A., Barakat, B. K., & El-Sana, J. (2018). ASAR 2018 Competition Page Layout Analysis Using Fully Convolutional Networks. In 2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018 (pp. 161-164). Article 8480326 (2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018). https://doi.org/10.1109/ASAR.2018.8480326

@inproceedings{93581118c2934d069acf685b070782b5,

title = "ASAR 2018 Competition Page Layout Analysis Using Fully Convolutional Networks",

abstract = "This technical report presents a Fully Convolutional Network based method for layout analysis of benchmarking dataset provided by the competition. The document image is segmented into text and non-text zones by dense pixel prediction. Convolutional part of the network can learn useful features from the document images and is robust to uncontrained layouts. We have evaluated the zone segmentation with average black pixel rate, over-segmentation error, under-segmentation error, correct-segmentation, missed-segmentation error, false alarm error, overall block error rate whereas the zone classification with precision, recall, F1-measure and average class accuracy on both pixel and block levels.",

author = "Ahmad Droby and 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.2018.8480326",

language = "American English",

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

pages = "161--164",

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

}

Droby, A, Barakat, BK & El-Sana, J 2018, ASAR 2018 Competition Page Layout Analysis Using Fully Convolutional Networks. in 2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018., 8480326, 2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018, pp. 161-164, 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.2018.8480326

ASAR 2018 Competition Page Layout Analysis Using Fully Convolutional Networks. / Droby, Ahmad; Barakat, Berat Kurar; El-Sana, Jihad.
2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition, ASAR 2018. 2018. p. 161-164 8480326 (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 - ASAR 2018 Competition Page Layout Analysis Using Fully Convolutional Networks

AU - Droby, Ahmad

AU - Barakat, Berat Kurar

AU - El-Sana, Jihad

PY - 2018/10/2

Y1 - 2018/10/2

N2 - This technical report presents a Fully Convolutional Network based method for layout analysis of benchmarking dataset provided by the competition. The document image is segmented into text and non-text zones by dense pixel prediction. Convolutional part of the network can learn useful features from the document images and is robust to uncontrained layouts. We have evaluated the zone segmentation with average black pixel rate, over-segmentation error, under-segmentation error, correct-segmentation, missed-segmentation error, false alarm error, overall block error rate whereas the zone classification with precision, recall, F1-measure and average class accuracy on both pixel and block levels.

AB - This technical report presents a Fully Convolutional Network based method for layout analysis of benchmarking dataset provided by the competition. The document image is segmented into text and non-text zones by dense pixel prediction. Convolutional part of the network can learn useful features from the document images and is robust to uncontrained layouts. We have evaluated the zone segmentation with average black pixel rate, over-segmentation error, under-segmentation error, correct-segmentation, missed-segmentation error, false alarm error, overall block error rate whereas the zone classification with precision, recall, F1-measure and average class accuracy on both pixel and block levels.

UR - http://www.scopus.com/inward/record.url?scp=85056205806&partnerID=8YFLogxK

U2 - 10.1109/ASAR.2018.8480326

DO - 10.1109/ASAR.2018.8480326

M3 - Conference contribution

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

SP - 161

EP - 164

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

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

Y2 - 12 March 2018 through 14 March 2018

ER -

ASAR 2018 Competition Page Layout Analysis Using Fully Convolutional Networks

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this