True color distributions of scene text and background

Renwu Gao, Shoma Eguchi, Seiichi Uchida

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

3 Citations (Scopus)

Abstract

Color feature, as one of the low level features, plays important role in image processing, object recognition and other fields. For example, in the task of scene text detection and recognition, lots of methodologies employ features that utilize color contrast of text and the corresponding background for connected component extraction. However, the true distributions of text and its background, in terms of color, is still not examined because it requires an enough number of scene text database with pixel-level labelled text/non-text ground truth. To clarify the relationship between text and its background, in this paper, we aim at investigating the color non-parametric distribution of text and its background using a large database that contains 3018 scene images and 98,600 characters. The results of our experiments show that text and its background can be discriminated by means of color, therefore color feature can be used for scene text detection.

Original languageEnglish
Title of host publication13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Conference Proceedings
PublisherIEEE Computer Society
Pages506-510
Number of pages5
Volume2015-November
ISBN (Electronic)9781479918058
DOIs
Publication statusPublished - Nov 20 2015
Event13th International Conference on Document Analysis and Recognition, ICDAR 2015 - Nancy, France
Duration: Aug 23 2015Aug 26 2015

Other

Other13th International Conference on Document Analysis and Recognition, ICDAR 2015
CountryFrance
CityNancy
Period8/23/158/26/15

Fingerprint

Color
Object recognition
Image processing
Pixels
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Gao, R., Eguchi, S., & Uchida, S. (2015). True color distributions of scene text and background. In 13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Conference Proceedings (Vol. 2015-November, pp. 506-510). [7333813] IEEE Computer Society. https://doi.org/10.1109/ICDAR.2015.7333813

True color distributions of scene text and background. / Gao, Renwu; Eguchi, Shoma; Uchida, Seiichi.

13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Conference Proceedings. Vol. 2015-November IEEE Computer Society, 2015. p. 506-510 7333813.

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

Gao, R, Eguchi, S & Uchida, S 2015, True color distributions of scene text and background. in 13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Conference Proceedings. vol. 2015-November, 7333813, IEEE Computer Society, pp. 506-510, 13th International Conference on Document Analysis and Recognition, ICDAR 2015, Nancy, France, 8/23/15. https://doi.org/10.1109/ICDAR.2015.7333813
Gao R, Eguchi S, Uchida S. True color distributions of scene text and background. In 13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Conference Proceedings. Vol. 2015-November. IEEE Computer Society. 2015. p. 506-510. 7333813 https://doi.org/10.1109/ICDAR.2015.7333813
Gao, Renwu ; Eguchi, Shoma ; Uchida, Seiichi. / True color distributions of scene text and background. 13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Conference Proceedings. Vol. 2015-November IEEE Computer Society, 2015. pp. 506-510
@inproceedings{e709a5a7c1bd4adabaa65314483b6eeb,
title = "True color distributions of scene text and background",
abstract = "Color feature, as one of the low level features, plays important role in image processing, object recognition and other fields. For example, in the task of scene text detection and recognition, lots of methodologies employ features that utilize color contrast of text and the corresponding background for connected component extraction. However, the true distributions of text and its background, in terms of color, is still not examined because it requires an enough number of scene text database with pixel-level labelled text/non-text ground truth. To clarify the relationship between text and its background, in this paper, we aim at investigating the color non-parametric distribution of text and its background using a large database that contains 3018 scene images and 98,600 characters. The results of our experiments show that text and its background can be discriminated by means of color, therefore color feature can be used for scene text detection.",
author = "Renwu Gao and Shoma Eguchi and Seiichi Uchida",
year = "2015",
month = "11",
day = "20",
doi = "10.1109/ICDAR.2015.7333813",
language = "English",
volume = "2015-November",
pages = "506--510",
booktitle = "13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Conference Proceedings",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - True color distributions of scene text and background

AU - Gao, Renwu

AU - Eguchi, Shoma

AU - Uchida, Seiichi

PY - 2015/11/20

Y1 - 2015/11/20

N2 - Color feature, as one of the low level features, plays important role in image processing, object recognition and other fields. For example, in the task of scene text detection and recognition, lots of methodologies employ features that utilize color contrast of text and the corresponding background for connected component extraction. However, the true distributions of text and its background, in terms of color, is still not examined because it requires an enough number of scene text database with pixel-level labelled text/non-text ground truth. To clarify the relationship between text and its background, in this paper, we aim at investigating the color non-parametric distribution of text and its background using a large database that contains 3018 scene images and 98,600 characters. The results of our experiments show that text and its background can be discriminated by means of color, therefore color feature can be used for scene text detection.

AB - Color feature, as one of the low level features, plays important role in image processing, object recognition and other fields. For example, in the task of scene text detection and recognition, lots of methodologies employ features that utilize color contrast of text and the corresponding background for connected component extraction. However, the true distributions of text and its background, in terms of color, is still not examined because it requires an enough number of scene text database with pixel-level labelled text/non-text ground truth. To clarify the relationship between text and its background, in this paper, we aim at investigating the color non-parametric distribution of text and its background using a large database that contains 3018 scene images and 98,600 characters. The results of our experiments show that text and its background can be discriminated by means of color, therefore color feature can be used for scene text detection.

UR - http://www.scopus.com/inward/record.url?scp=84962561249&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962561249&partnerID=8YFLogxK

U2 - 10.1109/ICDAR.2015.7333813

DO - 10.1109/ICDAR.2015.7333813

M3 - Conference contribution

AN - SCOPUS:84962561249

VL - 2015-November

SP - 506

EP - 510

BT - 13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Conference Proceedings

PB - IEEE Computer Society

ER -