Support vector machines for text location in news video images

Keechul Jung, Junghyun Han, Kwang In Kim, Se Hyun Park

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

9 Citations (Scopus)

Abstract

The aim of this paper is to show the applicability of support vector machines (SVMs) for the problem of text location and to propose a SVM-based method for locating texts in news video images. The proposed method is based on observations that texts in digital video have distinct textural properties that can be used to discriminate texts from the background and a SVM can be trained to be a texture classifier. A SVM is used for classifying a pixel into text or non-text by analyzing the textural properties of video image. To achieve multi-scale location, the video image is incrementally resized and the location process is performed over each of these resized images.

Original languageEnglish
Title of host publicationIEEE Region 10 Annual International Conference, Proceedings/TENCON
Volume2
Publication statusPublished - 2000 Dec 1
Externally publishedYes
Event2000 TENCON Proceedings - Kuala Lumpur, Malaysia
Duration: 2000 Sep 242000 Sep 27

Other

Other2000 TENCON Proceedings
CityKuala Lumpur, Malaysia
Period00/9/2400/9/27

Fingerprint

Support vector machines
Classifiers
Textures
Pixels

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Jung, K., Han, J., Kim, K. I., & Park, S. H. (2000). Support vector machines for text location in news video images. In IEEE Region 10 Annual International Conference, Proceedings/TENCON (Vol. 2)

Support vector machines for text location in news video images. / Jung, Keechul; Han, Junghyun; Kim, Kwang In; Park, Se Hyun.

IEEE Region 10 Annual International Conference, Proceedings/TENCON. Vol. 2 2000.

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

Jung, K, Han, J, Kim, KI & Park, SH 2000, Support vector machines for text location in news video images. in IEEE Region 10 Annual International Conference, Proceedings/TENCON. vol. 2, 2000 TENCON Proceedings, Kuala Lumpur, Malaysia, 00/9/24.
Jung K, Han J, Kim KI, Park SH. Support vector machines for text location in news video images. In IEEE Region 10 Annual International Conference, Proceedings/TENCON. Vol. 2. 2000
Jung, Keechul ; Han, Junghyun ; Kim, Kwang In ; Park, Se Hyun. / Support vector machines for text location in news video images. IEEE Region 10 Annual International Conference, Proceedings/TENCON. Vol. 2 2000.
@inproceedings{f8cf4c315bcc4471afcb5e879c15209f,
title = "Support vector machines for text location in news video images",
abstract = "The aim of this paper is to show the applicability of support vector machines (SVMs) for the problem of text location and to propose a SVM-based method for locating texts in news video images. The proposed method is based on observations that texts in digital video have distinct textural properties that can be used to discriminate texts from the background and a SVM can be trained to be a texture classifier. A SVM is used for classifying a pixel into text or non-text by analyzing the textural properties of video image. To achieve multi-scale location, the video image is incrementally resized and the location process is performed over each of these resized images.",
author = "Keechul Jung and Junghyun Han and Kim, {Kwang In} and Park, {Se Hyun}",
year = "2000",
month = "12",
day = "1",
language = "English",
volume = "2",
booktitle = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",

}

TY - GEN

T1 - Support vector machines for text location in news video images

AU - Jung, Keechul

AU - Han, Junghyun

AU - Kim, Kwang In

AU - Park, Se Hyun

PY - 2000/12/1

Y1 - 2000/12/1

N2 - The aim of this paper is to show the applicability of support vector machines (SVMs) for the problem of text location and to propose a SVM-based method for locating texts in news video images. The proposed method is based on observations that texts in digital video have distinct textural properties that can be used to discriminate texts from the background and a SVM can be trained to be a texture classifier. A SVM is used for classifying a pixel into text or non-text by analyzing the textural properties of video image. To achieve multi-scale location, the video image is incrementally resized and the location process is performed over each of these resized images.

AB - The aim of this paper is to show the applicability of support vector machines (SVMs) for the problem of text location and to propose a SVM-based method for locating texts in news video images. The proposed method is based on observations that texts in digital video have distinct textural properties that can be used to discriminate texts from the background and a SVM can be trained to be a texture classifier. A SVM is used for classifying a pixel into text or non-text by analyzing the textural properties of video image. To achieve multi-scale location, the video image is incrementally resized and the location process is performed over each of these resized images.

UR - http://www.scopus.com/inward/record.url?scp=0034427998&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034427998&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

BT - IEEE Region 10 Annual International Conference, Proceedings/TENCON

ER -