A robust algorithm for text detection in color images

Yangxing Liu, Satoshi Goto, Takeshi Ikenaga

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

28 Citations (Scopus)

Abstract

Text detection in color images has become an active research area since recent decades. In this paper, we present a novel approach to accurately detect text in color images possibly with a complex background. First, we use an elaborate edge detection algorithm to extract all possible text edge pixels. Second connected component analysis is employed to construct text candidate region and classify part non-text regions. Third each text candidate region is verified with texture features derived from wavelet domain. Finally, the Expectation maximization algorithm is introduced to binarize text regions to prepare data for recognition. In contrast to previous approach, our algorithm combines both the efficiency of connected component based method and robustness of texture based analysis. Experimental results show that our algorithm is robust in text detection with respect to different character size, orientation, color and language and can provide reliable text binarization result.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Document Analysis and Recognition, ICDAR
Pages399-403
Number of pages5
Volume2005
DOIs
Publication statusPublished - 2005
Externally publishedYes
Event8th International Conference on Document Analysis and Recognition - Seoul
Duration: 2005 Aug 312005 Sep 1

Other

Other8th International Conference on Document Analysis and Recognition
CitySeoul
Period05/8/3105/9/1

Fingerprint

Color
Textures
Edge detection
Pixels

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Liu, Y., Goto, S., & Ikenaga, T. (2005). A robust algorithm for text detection in color images. In Proceedings of the International Conference on Document Analysis and Recognition, ICDAR (Vol. 2005, pp. 399-403). [1575577] https://doi.org/10.1109/ICDAR.2005.29

A robust algorithm for text detection in color images. / Liu, Yangxing; Goto, Satoshi; Ikenaga, Takeshi.

Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. Vol. 2005 2005. p. 399-403 1575577.

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

Liu, Y, Goto, S & Ikenaga, T 2005, A robust algorithm for text detection in color images. in Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. vol. 2005, 1575577, pp. 399-403, 8th International Conference on Document Analysis and Recognition, Seoul, 05/8/31. https://doi.org/10.1109/ICDAR.2005.29
Liu Y, Goto S, Ikenaga T. A robust algorithm for text detection in color images. In Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. Vol. 2005. 2005. p. 399-403. 1575577 https://doi.org/10.1109/ICDAR.2005.29
Liu, Yangxing ; Goto, Satoshi ; Ikenaga, Takeshi. / A robust algorithm for text detection in color images. Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. Vol. 2005 2005. pp. 399-403
@inproceedings{3a4c344b70354c9c99ef4794bcc3466e,
title = "A robust algorithm for text detection in color images",
abstract = "Text detection in color images has become an active research area since recent decades. In this paper, we present a novel approach to accurately detect text in color images possibly with a complex background. First, we use an elaborate edge detection algorithm to extract all possible text edge pixels. Second connected component analysis is employed to construct text candidate region and classify part non-text regions. Third each text candidate region is verified with texture features derived from wavelet domain. Finally, the Expectation maximization algorithm is introduced to binarize text regions to prepare data for recognition. In contrast to previous approach, our algorithm combines both the efficiency of connected component based method and robustness of texture based analysis. Experimental results show that our algorithm is robust in text detection with respect to different character size, orientation, color and language and can provide reliable text binarization result.",
author = "Yangxing Liu and Satoshi Goto and Takeshi Ikenaga",
year = "2005",
doi = "10.1109/ICDAR.2005.29",
language = "English",
isbn = "0769524206",
volume = "2005",
pages = "399--403",
booktitle = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",

}

TY - GEN

T1 - A robust algorithm for text detection in color images

AU - Liu, Yangxing

AU - Goto, Satoshi

AU - Ikenaga, Takeshi

PY - 2005

Y1 - 2005

N2 - Text detection in color images has become an active research area since recent decades. In this paper, we present a novel approach to accurately detect text in color images possibly with a complex background. First, we use an elaborate edge detection algorithm to extract all possible text edge pixels. Second connected component analysis is employed to construct text candidate region and classify part non-text regions. Third each text candidate region is verified with texture features derived from wavelet domain. Finally, the Expectation maximization algorithm is introduced to binarize text regions to prepare data for recognition. In contrast to previous approach, our algorithm combines both the efficiency of connected component based method and robustness of texture based analysis. Experimental results show that our algorithm is robust in text detection with respect to different character size, orientation, color and language and can provide reliable text binarization result.

AB - Text detection in color images has become an active research area since recent decades. In this paper, we present a novel approach to accurately detect text in color images possibly with a complex background. First, we use an elaborate edge detection algorithm to extract all possible text edge pixels. Second connected component analysis is employed to construct text candidate region and classify part non-text regions. Third each text candidate region is verified with texture features derived from wavelet domain. Finally, the Expectation maximization algorithm is introduced to binarize text regions to prepare data for recognition. In contrast to previous approach, our algorithm combines both the efficiency of connected component based method and robustness of texture based analysis. Experimental results show that our algorithm is robust in text detection with respect to different character size, orientation, color and language and can provide reliable text binarization result.

UR - http://www.scopus.com/inward/record.url?scp=33846431096&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846431096&partnerID=8YFLogxK

U2 - 10.1109/ICDAR.2005.29

DO - 10.1109/ICDAR.2005.29

M3 - Conference contribution

AN - SCOPUS:33846431096

SN - 0769524206

SN - 9780769524207

VL - 2005

SP - 399

EP - 403

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

ER -