Extraction of arbitrary text in natural scene image based on stroke width transform

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

Abstract

Text extraction plays an important role in numerous applications. Research on its method still need to be improved in order to achieve better performance, to increase the reliability of text extraction system and to deal with complex cases of text extraction. The majority of the text extraction methods are focusing on horizontal and near horizontal text lines; however, text in natural scene might be in arbitrary line in real time. Thus, this paper aims to solve the issue of extracting the arbitrary oriented text by suggesting a method for text detection and localization based on the Stroke Width Transform. The proposed method is tested on an arbitrary text dataset and ICDAR dataset. The result of the experiment shows that the proposed method adapts well to the arbitrary text.

Original languageEnglish
Title of host publicationInternational Conference on Intelligent Systems Design and Applications, ISDA
PublisherIEEE Computer Society
Pages124-128
Number of pages5
Volume2015-January
ISBN (Print)9781479979387
DOIs
Publication statusPublished - 23 Mar 2015
Event2014 14th International Conference on Intelligent Systems Design and Applications, ISDA 2014 - Okinawa, Japan
Duration: 28 Nov 201430 Nov 2014

Other

Other2014 14th International Conference on Intelligent Systems Design and Applications, ISDA 2014
CountryJapan
CityOkinawa
Period28/11/1430/11/14

Fingerprint

Mathematical transformations
Experiments

Keywords

  • Scene understanding
  • Stroke Width Transform
  • Text detection and localization
  • Text extraction

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Signal Processing
  • Control and Systems Engineering

Cite this

Jameson, J., & Sheikh Abdullah, S. N. H. (2015). Extraction of arbitrary text in natural scene image based on stroke width transform. In International Conference on Intelligent Systems Design and Applications, ISDA (Vol. 2015-January, pp. 124-128). [7066257] IEEE Computer Society. https://doi.org/10.1109/ISDA.2014.7066257

Extraction of arbitrary text in natural scene image based on stroke width transform. / Jameson, Jinjuli; Sheikh Abdullah, Siti Norul Huda.

International Conference on Intelligent Systems Design and Applications, ISDA. Vol. 2015-January IEEE Computer Society, 2015. p. 124-128 7066257.

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

Jameson, J & Sheikh Abdullah, SNH 2015, Extraction of arbitrary text in natural scene image based on stroke width transform. in International Conference on Intelligent Systems Design and Applications, ISDA. vol. 2015-January, 7066257, IEEE Computer Society, pp. 124-128, 2014 14th International Conference on Intelligent Systems Design and Applications, ISDA 2014, Okinawa, Japan, 28/11/14. https://doi.org/10.1109/ISDA.2014.7066257
Jameson J, Sheikh Abdullah SNH. Extraction of arbitrary text in natural scene image based on stroke width transform. In International Conference on Intelligent Systems Design and Applications, ISDA. Vol. 2015-January. IEEE Computer Society. 2015. p. 124-128. 7066257 https://doi.org/10.1109/ISDA.2014.7066257
Jameson, Jinjuli ; Sheikh Abdullah, Siti Norul Huda. / Extraction of arbitrary text in natural scene image based on stroke width transform. International Conference on Intelligent Systems Design and Applications, ISDA. Vol. 2015-January IEEE Computer Society, 2015. pp. 124-128
@inproceedings{85372f3129b145e494c63125f1350906,
title = "Extraction of arbitrary text in natural scene image based on stroke width transform",
abstract = "Text extraction plays an important role in numerous applications. Research on its method still need to be improved in order to achieve better performance, to increase the reliability of text extraction system and to deal with complex cases of text extraction. The majority of the text extraction methods are focusing on horizontal and near horizontal text lines; however, text in natural scene might be in arbitrary line in real time. Thus, this paper aims to solve the issue of extracting the arbitrary oriented text by suggesting a method for text detection and localization based on the Stroke Width Transform. The proposed method is tested on an arbitrary text dataset and ICDAR dataset. The result of the experiment shows that the proposed method adapts well to the arbitrary text.",
keywords = "Scene understanding, Stroke Width Transform, Text detection and localization, Text extraction",
author = "Jinjuli Jameson and {Sheikh Abdullah}, {Siti Norul Huda}",
year = "2015",
month = "3",
day = "23",
doi = "10.1109/ISDA.2014.7066257",
language = "English",
isbn = "9781479979387",
volume = "2015-January",
pages = "124--128",
booktitle = "International Conference on Intelligent Systems Design and Applications, ISDA",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Extraction of arbitrary text in natural scene image based on stroke width transform

AU - Jameson, Jinjuli

AU - Sheikh Abdullah, Siti Norul Huda

PY - 2015/3/23

Y1 - 2015/3/23

N2 - Text extraction plays an important role in numerous applications. Research on its method still need to be improved in order to achieve better performance, to increase the reliability of text extraction system and to deal with complex cases of text extraction. The majority of the text extraction methods are focusing on horizontal and near horizontal text lines; however, text in natural scene might be in arbitrary line in real time. Thus, this paper aims to solve the issue of extracting the arbitrary oriented text by suggesting a method for text detection and localization based on the Stroke Width Transform. The proposed method is tested on an arbitrary text dataset and ICDAR dataset. The result of the experiment shows that the proposed method adapts well to the arbitrary text.

AB - Text extraction plays an important role in numerous applications. Research on its method still need to be improved in order to achieve better performance, to increase the reliability of text extraction system and to deal with complex cases of text extraction. The majority of the text extraction methods are focusing on horizontal and near horizontal text lines; however, text in natural scene might be in arbitrary line in real time. Thus, this paper aims to solve the issue of extracting the arbitrary oriented text by suggesting a method for text detection and localization based on the Stroke Width Transform. The proposed method is tested on an arbitrary text dataset and ICDAR dataset. The result of the experiment shows that the proposed method adapts well to the arbitrary text.

KW - Scene understanding

KW - Stroke Width Transform

KW - Text detection and localization

KW - Text extraction

UR - http://www.scopus.com/inward/record.url?scp=84940478545&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84940478545&partnerID=8YFLogxK

U2 - 10.1109/ISDA.2014.7066257

DO - 10.1109/ISDA.2014.7066257

M3 - Conference contribution

SN - 9781479979387

VL - 2015-January

SP - 124

EP - 128

BT - International Conference on Intelligent Systems Design and Applications, ISDA

PB - IEEE Computer Society

ER -