Text detection in color scene images based on unsupervised clustering of multi-channel wavelet features

Tomoyuki Saoi; Hideaki Goto; Hiroaki Kobayashi

doi:10.1109/ICDAR.2005.227

Text detection in color scene images based on unsupervised clustering of multi-channel wavelet features

Tomoyuki Saoi, Hideaki Goto, Hiroaki Kobayashi

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

17 Citations (Scopus)

Abstract

Texts in natural scenes provide us with much useful information. In order to use such information automatically, it is necessary to make computers detect text regions in the images. Gllavata et al. proposed a method based on unsupervised classification of high frequency wavelet coefficients for text detection in video frames [1]. Although the method is very accurate, it does not work so well with some color images, since it lacks the ability of discriminating color difference. This paper proposes an enhanced version of the method. We develop a new unsupervised clustering technique for the classification of multi-channel wavelet features to deal with color images. Experimental results show that the new method yields better results for color scene images.

Original language	English
Title of host publication	Proceedings of the Eighth International Conference on Document Analysis and Recognition
Pages	690-694
Number of pages	5
DOIs	https://doi.org/10.1109/ICDAR.2005.227
Publication status	Published - 2005 Dec 1
Event	8th International Conference on Document Analysis and Recognition - Seoul, Korea, Republic of Duration: 2005 Aug 31 → 2005 Sept 1

Publication series

Name	Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
Volume	2005
ISSN (Print)	1520-5363

Other

Other	8th International Conference on Document Analysis and Recognition
Country/Territory	Korea, Republic of
City	Seoul
Period	05/8/31 → 05/9/1

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Access to Document

10.1109/ICDAR.2005.227

Cite this

Saoi, T., Goto, H., & Kobayashi, H. (2005). Text detection in color scene images based on unsupervised clustering of multi-channel wavelet features. In Proceedings of the Eighth International Conference on Document Analysis and Recognition (pp. 690-694). [1575633] (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR; Vol. 2005). https://doi.org/10.1109/ICDAR.2005.227

Text detection in color scene images based on unsupervised clustering of multi-channel wavelet features. / Saoi, Tomoyuki; Goto, Hideaki ; Kobayashi, Hiroaki.
Proceedings of the Eighth International Conference on Document Analysis and Recognition. 2005. p. 690-694 1575633 (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR; Vol. 2005).

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

Saoi, T, Goto, H & Kobayashi, H 2005, Text detection in color scene images based on unsupervised clustering of multi-channel wavelet features. in Proceedings of the Eighth International Conference on Document Analysis and Recognition., 1575633, Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, vol. 2005, pp. 690-694, 8th International Conference on Document Analysis and Recognition, Seoul, Korea, Republic of, 05/8/31. https://doi.org/10.1109/ICDAR.2005.227

Saoi T, Goto H , Kobayashi H. Text detection in color scene images based on unsupervised clustering of multi-channel wavelet features. In Proceedings of the Eighth International Conference on Document Analysis and Recognition. 2005. p. 690-694. 1575633. (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR). doi: 10.1109/ICDAR.2005.227

@inproceedings{ad4f6d663ddc4d868aba738019059fb3,

title = "Text detection in color scene images based on unsupervised clustering of multi-channel wavelet features",

abstract = "Texts in natural scenes provide us with much useful information. In order to use such information automatically, it is necessary to make computers detect text regions in the images. Gllavata et al. proposed a method based on unsupervised classification of high frequency wavelet coefficients for text detection in video frames [1]. Although the method is very accurate, it does not work so well with some color images, since it lacks the ability of discriminating color difference. This paper proposes an enhanced version of the method. We develop a new unsupervised clustering technique for the classification of multi-channel wavelet features to deal with color images. Experimental results show that the new method yields better results for color scene images.",

author = "Tomoyuki Saoi and Hideaki Goto and Hiroaki Kobayashi",

year = "2005",

month = dec,

day = "1",

doi = "10.1109/ICDAR.2005.227",

language = "English",

isbn = "0769524206",

series = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",

pages = "690--694",

booktitle = "Proceedings of the Eighth International Conference on Document Analysis and Recognition",

note = "8th International Conference on Document Analysis and Recognition ; Conference date: 31-08-2005 Through 01-09-2005",

}

TY - GEN

T1 - Text detection in color scene images based on unsupervised clustering of multi-channel wavelet features

AU - Saoi, Tomoyuki

AU - Goto, Hideaki

AU - Kobayashi, Hiroaki

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Texts in natural scenes provide us with much useful information. In order to use such information automatically, it is necessary to make computers detect text regions in the images. Gllavata et al. proposed a method based on unsupervised classification of high frequency wavelet coefficients for text detection in video frames [1]. Although the method is very accurate, it does not work so well with some color images, since it lacks the ability of discriminating color difference. This paper proposes an enhanced version of the method. We develop a new unsupervised clustering technique for the classification of multi-channel wavelet features to deal with color images. Experimental results show that the new method yields better results for color scene images.

AB - Texts in natural scenes provide us with much useful information. In order to use such information automatically, it is necessary to make computers detect text regions in the images. Gllavata et al. proposed a method based on unsupervised classification of high frequency wavelet coefficients for text detection in video frames [1]. Although the method is very accurate, it does not work so well with some color images, since it lacks the ability of discriminating color difference. This paper proposes an enhanced version of the method. We develop a new unsupervised clustering technique for the classification of multi-channel wavelet features to deal with color images. Experimental results show that the new method yields better results for color scene images.

UR - http://www.scopus.com/inward/record.url?scp=33947381382&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33947381382&partnerID=8YFLogxK

U2 - 10.1109/ICDAR.2005.227

DO - 10.1109/ICDAR.2005.227

M3 - Conference contribution

AN - SCOPUS:33947381382

SN - 0769524206

SN - 9780769524207

T3 - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

SP - 690

EP - 694

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

T2 - 8th International Conference on Document Analysis and Recognition

Y2 - 31 August 2005 through 1 September 2005

ER -

Text detection in color scene images based on unsupervised clustering of multi-channel wavelet features

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this