An improved logo detection method with learning-based verification for video classification

Hyo Young Kim, Mun Cheon Kang, Sung Ho Chae, Dae Hwan Kim, Sung-Jea Ko

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

Abstract

With the growth of cloud services, concerns have been raised regarding illegal sharing of the commercial video. To prevent the illegal sharing automatically, the method for classifying video as 'commercial' or 'noncommercial' is essentially required. Since most commercial video has a logo as a visible watermark, automatic logo detection can be an efficient method for the video classification. In this paper, we present an improved logo detection method which correctly detects the logo in any types of video using learning-based logo verification. Experimental results show that the proposed method achieves improved detection performance as compared with the existing method, and thus can be effectively used for classifying the video.

Original languageEnglish
Title of host publicationIEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin
PublisherIEEE Computer Society
Pages192-193
Number of pages2
Volume2015-February
EditionFebruary
DOIs
Publication statusPublished - 2015 Feb 5
Event2014 4th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin - Berlin, Germany
Duration: 2014 Sep 72014 Sep 10

Other

Other2014 4th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin
CountryGermany
CityBerlin
Period14/9/714/9/10

Keywords

  • copyright protection
  • feature extraction
  • logo detection
  • SVM
  • Video classification

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering
  • Media Technology

Cite this

Kim, H. Y., Kang, M. C., Chae, S. H., Kim, D. H., & Ko, S-J. (2015). An improved logo detection method with learning-based verification for video classification. In IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin (February ed., Vol. 2015-February, pp. 192-193). [7034299] IEEE Computer Society. https://doi.org/10.1109/ICCE-Berlin.2014.7034299

An improved logo detection method with learning-based verification for video classification. / Kim, Hyo Young; Kang, Mun Cheon; Chae, Sung Ho; Kim, Dae Hwan; Ko, Sung-Jea.

IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin. Vol. 2015-February February. ed. IEEE Computer Society, 2015. p. 192-193 7034299.

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

Kim, HY, Kang, MC, Chae, SH, Kim, DH & Ko, S-J 2015, An improved logo detection method with learning-based verification for video classification. in IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin. February edn, vol. 2015-February, 7034299, IEEE Computer Society, pp. 192-193, 2014 4th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin, Berlin, Germany, 14/9/7. https://doi.org/10.1109/ICCE-Berlin.2014.7034299
Kim HY, Kang MC, Chae SH, Kim DH, Ko S-J. An improved logo detection method with learning-based verification for video classification. In IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin. February ed. Vol. 2015-February. IEEE Computer Society. 2015. p. 192-193. 7034299 https://doi.org/10.1109/ICCE-Berlin.2014.7034299
Kim, Hyo Young ; Kang, Mun Cheon ; Chae, Sung Ho ; Kim, Dae Hwan ; Ko, Sung-Jea. / An improved logo detection method with learning-based verification for video classification. IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin. Vol. 2015-February February. ed. IEEE Computer Society, 2015. pp. 192-193
@inproceedings{f5ab03e0b3c14789b98809a4ae4a7741,
title = "An improved logo detection method with learning-based verification for video classification",
abstract = "With the growth of cloud services, concerns have been raised regarding illegal sharing of the commercial video. To prevent the illegal sharing automatically, the method for classifying video as 'commercial' or 'noncommercial' is essentially required. Since most commercial video has a logo as a visible watermark, automatic logo detection can be an efficient method for the video classification. In this paper, we present an improved logo detection method which correctly detects the logo in any types of video using learning-based logo verification. Experimental results show that the proposed method achieves improved detection performance as compared with the existing method, and thus can be effectively used for classifying the video.",
keywords = "copyright protection, feature extraction, logo detection, SVM, Video classification",
author = "Kim, {Hyo Young} and Kang, {Mun Cheon} and Chae, {Sung Ho} and Kim, {Dae Hwan} and Sung-Jea Ko",
year = "2015",
month = "2",
day = "5",
doi = "10.1109/ICCE-Berlin.2014.7034299",
language = "English",
volume = "2015-February",
pages = "192--193",
booktitle = "IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin",
publisher = "IEEE Computer Society",
edition = "February",

}

TY - GEN

T1 - An improved logo detection method with learning-based verification for video classification

AU - Kim, Hyo Young

AU - Kang, Mun Cheon

AU - Chae, Sung Ho

AU - Kim, Dae Hwan

AU - Ko, Sung-Jea

PY - 2015/2/5

Y1 - 2015/2/5

N2 - With the growth of cloud services, concerns have been raised regarding illegal sharing of the commercial video. To prevent the illegal sharing automatically, the method for classifying video as 'commercial' or 'noncommercial' is essentially required. Since most commercial video has a logo as a visible watermark, automatic logo detection can be an efficient method for the video classification. In this paper, we present an improved logo detection method which correctly detects the logo in any types of video using learning-based logo verification. Experimental results show that the proposed method achieves improved detection performance as compared with the existing method, and thus can be effectively used for classifying the video.

AB - With the growth of cloud services, concerns have been raised regarding illegal sharing of the commercial video. To prevent the illegal sharing automatically, the method for classifying video as 'commercial' or 'noncommercial' is essentially required. Since most commercial video has a logo as a visible watermark, automatic logo detection can be an efficient method for the video classification. In this paper, we present an improved logo detection method which correctly detects the logo in any types of video using learning-based logo verification. Experimental results show that the proposed method achieves improved detection performance as compared with the existing method, and thus can be effectively used for classifying the video.

KW - copyright protection

KW - feature extraction

KW - logo detection

KW - SVM

KW - Video classification

UR - http://www.scopus.com/inward/record.url?scp=84937899983&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937899983&partnerID=8YFLogxK

U2 - 10.1109/ICCE-Berlin.2014.7034299

DO - 10.1109/ICCE-Berlin.2014.7034299

M3 - Conference contribution

VL - 2015-February

SP - 192

EP - 193

BT - IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin

PB - IEEE Computer Society

ER -