AdaBoost for text detection in natural scene

Jung Jin Lee, Pyoung Hean Lee, Seong Whan Lee, Alan Yuille, Christof Koch

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

126 Citations (Scopus)

Abstract

Detecting text regions in natural scenes is an important part of computer vision. We propose a novel text detection algorithm that extracts six different classes features of text, and uses Modest AdaBoost with multi-scale sequential search. Experiments show that our algorithm can detect text regions with a f= 0.70, from the ICDAR 2003 datasets which include images with text of various fonts, sizes, colors, alphabets and scripts.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Document Analysis and Recognition, ICDAR
Pages429-434
Number of pages6
DOIs
Publication statusPublished - 2011 Dec 2
Event11th International Conference on Document Analysis and Recognition, ICDAR 2011 - Beijing, China
Duration: 2011 Sep 182011 Sep 21

Other

Other11th International Conference on Document Analysis and Recognition, ICDAR 2011
CountryChina
CityBeijing
Period11/9/1811/9/21

Fingerprint

Adaptive boosting
Computer vision
Color
Experiments

Keywords

  • AdaBoost
  • text detection
  • text location

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Lee, J. J., Lee, P. H., Lee, S. W., Yuille, A., & Koch, C. (2011). AdaBoost for text detection in natural scene. In Proceedings of the International Conference on Document Analysis and Recognition, ICDAR (pp. 429-434). [6065348] https://doi.org/10.1109/ICDAR.2011.93

AdaBoost for text detection in natural scene. / Lee, Jung Jin; Lee, Pyoung Hean; Lee, Seong Whan; Yuille, Alan; Koch, Christof.

Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. 2011. p. 429-434 6065348.

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

Lee, JJ, Lee, PH, Lee, SW, Yuille, A & Koch, C 2011, AdaBoost for text detection in natural scene. in Proceedings of the International Conference on Document Analysis and Recognition, ICDAR., 6065348, pp. 429-434, 11th International Conference on Document Analysis and Recognition, ICDAR 2011, Beijing, China, 11/9/18. https://doi.org/10.1109/ICDAR.2011.93
Lee JJ, Lee PH, Lee SW, Yuille A, Koch C. AdaBoost for text detection in natural scene. In Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. 2011. p. 429-434. 6065348 https://doi.org/10.1109/ICDAR.2011.93
Lee, Jung Jin ; Lee, Pyoung Hean ; Lee, Seong Whan ; Yuille, Alan ; Koch, Christof. / AdaBoost for text detection in natural scene. Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. 2011. pp. 429-434
@inproceedings{3ebb41a3cce345e3892579e92ab7a9a3,
title = "AdaBoost for text detection in natural scene",
abstract = "Detecting text regions in natural scenes is an important part of computer vision. We propose a novel text detection algorithm that extracts six different classes features of text, and uses Modest AdaBoost with multi-scale sequential search. Experiments show that our algorithm can detect text regions with a f= 0.70, from the ICDAR 2003 datasets which include images with text of various fonts, sizes, colors, alphabets and scripts.",
keywords = "AdaBoost, text detection, text location",
author = "Lee, {Jung Jin} and Lee, {Pyoung Hean} and Lee, {Seong Whan} and Alan Yuille and Christof Koch",
year = "2011",
month = "12",
day = "2",
doi = "10.1109/ICDAR.2011.93",
language = "English",
isbn = "9780769545202",
pages = "429--434",
booktitle = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",

}

TY - GEN

T1 - AdaBoost for text detection in natural scene

AU - Lee, Jung Jin

AU - Lee, Pyoung Hean

AU - Lee, Seong Whan

AU - Yuille, Alan

AU - Koch, Christof

PY - 2011/12/2

Y1 - 2011/12/2

N2 - Detecting text regions in natural scenes is an important part of computer vision. We propose a novel text detection algorithm that extracts six different classes features of text, and uses Modest AdaBoost with multi-scale sequential search. Experiments show that our algorithm can detect text regions with a f= 0.70, from the ICDAR 2003 datasets which include images with text of various fonts, sizes, colors, alphabets and scripts.

AB - Detecting text regions in natural scenes is an important part of computer vision. We propose a novel text detection algorithm that extracts six different classes features of text, and uses Modest AdaBoost with multi-scale sequential search. Experiments show that our algorithm can detect text regions with a f= 0.70, from the ICDAR 2003 datasets which include images with text of various fonts, sizes, colors, alphabets and scripts.

KW - AdaBoost

KW - text detection

KW - text location

UR - http://www.scopus.com/inward/record.url?scp=82355168569&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=82355168569&partnerID=8YFLogxK

U2 - 10.1109/ICDAR.2011.93

DO - 10.1109/ICDAR.2011.93

M3 - Conference contribution

AN - SCOPUS:82355168569

SN - 9780769545202

SP - 429

EP - 434

BT - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

ER -