Deep Arabic document layout analysis

Ibrahim M. Amer, Salma Hamdy, Mostafa G. M. Mostafa

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

1 Citation (Scopus)
44 Downloads (Pure)

Abstract

Document layout analysis (DLA) is an essential step for Optical Character Recognition Systems (OCR). The text of the document fed to the OCR must be extracted first and isolated from images if exist. The DLA task is difficult as there is no fixed layout for all documents, but instead, there are several layouts. There are various approaches for DLA for various different languages. In this paper, some of the previous techniques used in this field will be listed and then we will discuss the proposed method that depends on deep learning for documents’ text localization. We used Arabic Printed Text Image database (APTI [19]), ImageNet [18] and a dataset collected from different Arabic newspapers for training and evaluation.
Original languageEnglish
Title of host publicationProceedings of the 2017 IEEE Eighth International Conference on Intelligent Computing and Information Systems (ICICIS 2017)
Place of PublicationCairo, Egypt
PublisherIEEE
Pages224-231
Number of pages8
ISBN (Electronic)9781538608210
ISBN (Print)9781538608227, 9772371723
DOIs
Publication statusPublished - 5 Dec 2017
Externally publishedYes
Event8th International Conference on Intelligent Computing and Information Systems - Cairo, Egypt
Duration: 5 Dec 20177 Dec 2017
Conference number: 8

Conference

Conference8th International Conference on Intelligent Computing and Information Systems
Abbreviated titleICICIS 2017
CountryEgypt
CityCairo
Period5/12/177/12/17

Fingerprint

Optical character recognition
Deep learning

Cite this

Amer, I. M., Hamdy, S., & Mostafa, M. G. M. (2017). Deep Arabic document layout analysis. In Proceedings of the 2017 IEEE Eighth International Conference on Intelligent Computing and Information Systems (ICICIS 2017) (pp. 224-231). Cairo, Egypt: IEEE . https://doi.org/10.1109/INTELCIS.2017.8260051
Amer, Ibrahim M. ; Hamdy, Salma ; Mostafa, Mostafa G. M. . / Deep Arabic document layout analysis. Proceedings of the 2017 IEEE Eighth International Conference on Intelligent Computing and Information Systems (ICICIS 2017). Cairo, Egypt : IEEE , 2017. pp. 224-231
@inproceedings{82f74966025d44a9afd2bbceeb9d5781,
title = "Deep Arabic document layout analysis",
abstract = "Document layout analysis (DLA) is an essential step for Optical Character Recognition Systems (OCR). The text of the document fed to the OCR must be extracted first and isolated from images if exist. The DLA task is difficult as there is no fixed layout for all documents, but instead, there are several layouts. There are various approaches for DLA for various different languages. In this paper, some of the previous techniques used in this field will be listed and then we will discuss the proposed method that depends on deep learning for documents’ text localization. We used Arabic Printed Text Image database (APTI [19]), ImageNet [18] and a dataset collected from different Arabic newspapers for training and evaluation.",
author = "Amer, {Ibrahim M.} and Salma Hamdy and Mostafa, {Mostafa G. M.}",
year = "2017",
month = "12",
day = "5",
doi = "10.1109/INTELCIS.2017.8260051",
language = "English",
isbn = "9781538608227",
pages = "224--231",
booktitle = "Proceedings of the 2017 IEEE Eighth International Conference on Intelligent Computing and Information Systems (ICICIS 2017)",
publisher = "IEEE",

}

Amer, IM, Hamdy, S & Mostafa, MGM 2017, Deep Arabic document layout analysis. in Proceedings of the 2017 IEEE Eighth International Conference on Intelligent Computing and Information Systems (ICICIS 2017). IEEE , Cairo, Egypt, pp. 224-231, 8th International Conference on Intelligent Computing and Information Systems, Cairo, Egypt, 5/12/17. https://doi.org/10.1109/INTELCIS.2017.8260051

Deep Arabic document layout analysis. / Amer, Ibrahim M. ; Hamdy, Salma; Mostafa, Mostafa G. M. .

Proceedings of the 2017 IEEE Eighth International Conference on Intelligent Computing and Information Systems (ICICIS 2017). Cairo, Egypt : IEEE , 2017. p. 224-231.

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

TY - GEN

T1 - Deep Arabic document layout analysis

AU - Amer, Ibrahim M.

AU - Hamdy, Salma

AU - Mostafa, Mostafa G. M.

PY - 2017/12/5

Y1 - 2017/12/5

N2 - Document layout analysis (DLA) is an essential step for Optical Character Recognition Systems (OCR). The text of the document fed to the OCR must be extracted first and isolated from images if exist. The DLA task is difficult as there is no fixed layout for all documents, but instead, there are several layouts. There are various approaches for DLA for various different languages. In this paper, some of the previous techniques used in this field will be listed and then we will discuss the proposed method that depends on deep learning for documents’ text localization. We used Arabic Printed Text Image database (APTI [19]), ImageNet [18] and a dataset collected from different Arabic newspapers for training and evaluation.

AB - Document layout analysis (DLA) is an essential step for Optical Character Recognition Systems (OCR). The text of the document fed to the OCR must be extracted first and isolated from images if exist. The DLA task is difficult as there is no fixed layout for all documents, but instead, there are several layouts. There are various approaches for DLA for various different languages. In this paper, some of the previous techniques used in this field will be listed and then we will discuss the proposed method that depends on deep learning for documents’ text localization. We used Arabic Printed Text Image database (APTI [19]), ImageNet [18] and a dataset collected from different Arabic newspapers for training and evaluation.

U2 - 10.1109/INTELCIS.2017.8260051

DO - 10.1109/INTELCIS.2017.8260051

M3 - Conference contribution

SN - 9781538608227

SN - 9772371723

SP - 224

EP - 231

BT - Proceedings of the 2017 IEEE Eighth International Conference on Intelligent Computing and Information Systems (ICICIS 2017)

PB - IEEE

CY - Cairo, Egypt

ER -

Amer IM, Hamdy S, Mostafa MGM. Deep Arabic document layout analysis. In Proceedings of the 2017 IEEE Eighth International Conference on Intelligent Computing and Information Systems (ICICIS 2017). Cairo, Egypt: IEEE . 2017. p. 224-231 https://doi.org/10.1109/INTELCIS.2017.8260051