Robust fingerprinting method for webtoon identification in large-scale databases

Doyoung Kim, Sang Hoon Lee, Sagar Jadhav, Hyuck Joo Kwon, Sanghoon Lee

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Webtoon, a portmanteau of web and cartoon, denotes a cartoon that has been published on a website. Recently, webtoons have become popular in the global Internet market. Unfortunately, the copyright infringement has emerged as a new challenge resulting in illegal profit gains. Moreover, it is difficult to apply watermarking to published webtoons, because they need to be watermarked prior to publication. In order to deal with a large number of published webtoons, it is necessary to identify each webtoon using fingerprints extracted from its webtoon image. In this paper, we propose an identification framework to detect copyright infringement due to the illegal copying and sharing of webtoons. The proposed identification framework consists of the following main stages: Fingerprint generation, indexing, and fingerprint matching. In the fingerprint generation stage, the translation invariant and temporally localized fingerprints are created for distortion-robust identification. An inverted indexing of the database is implemented, using the visual word clustering method and the MapReduce framework, to store the fingerprints efficiently and to minimize the searching time. In addition, we propose a two-step matching process for faster implementation. Moreover, we measured the identification accuracy and the matching time of a large-scale database in the presence of various distortions. Through rigorous simulations, we achieved an identification accuracy of 97.5% within 10 s for each webtoon.

Original languageEnglish
Article number8403906
Pages (from-to)37932-37946
Number of pages15
JournalIEEE Access
Volume6
DOIs
Publication statusPublished - 2018 Jul 4

Fingerprint

Copying
Watermarking
Websites
Profitability
Internet

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Kim, Doyoung ; Lee, Sang Hoon ; Jadhav, Sagar ; Kwon, Hyuck Joo ; Lee, Sanghoon. / Robust fingerprinting method for webtoon identification in large-scale databases. In: IEEE Access. 2018 ; Vol. 6. pp. 37932-37946.
@article{25c2049b03bb4b2b95732ff539d6826c,
title = "Robust fingerprinting method for webtoon identification in large-scale databases",
abstract = "Webtoon, a portmanteau of web and cartoon, denotes a cartoon that has been published on a website. Recently, webtoons have become popular in the global Internet market. Unfortunately, the copyright infringement has emerged as a new challenge resulting in illegal profit gains. Moreover, it is difficult to apply watermarking to published webtoons, because they need to be watermarked prior to publication. In order to deal with a large number of published webtoons, it is necessary to identify each webtoon using fingerprints extracted from its webtoon image. In this paper, we propose an identification framework to detect copyright infringement due to the illegal copying and sharing of webtoons. The proposed identification framework consists of the following main stages: Fingerprint generation, indexing, and fingerprint matching. In the fingerprint generation stage, the translation invariant and temporally localized fingerprints are created for distortion-robust identification. An inverted indexing of the database is implemented, using the visual word clustering method and the MapReduce framework, to store the fingerprints efficiently and to minimize the searching time. In addition, we propose a two-step matching process for faster implementation. Moreover, we measured the identification accuracy and the matching time of a large-scale database in the presence of various distortions. Through rigorous simulations, we achieved an identification accuracy of 97.5{\%} within 10 s for each webtoon.",
author = "Doyoung Kim and Lee, {Sang Hoon} and Sagar Jadhav and Kwon, {Hyuck Joo} and Sanghoon Lee",
year = "2018",
month = "7",
day = "4",
doi = "10.1109/ACCESS.2018.2845540",
language = "English",
volume = "6",
pages = "37932--37946",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Robust fingerprinting method for webtoon identification in large-scale databases. / Kim, Doyoung; Lee, Sang Hoon; Jadhav, Sagar; Kwon, Hyuck Joo; Lee, Sanghoon.

In: IEEE Access, Vol. 6, 8403906, 04.07.2018, p. 37932-37946.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Robust fingerprinting method for webtoon identification in large-scale databases

AU - Kim, Doyoung

AU - Lee, Sang Hoon

AU - Jadhav, Sagar

AU - Kwon, Hyuck Joo

AU - Lee, Sanghoon

PY - 2018/7/4

Y1 - 2018/7/4

N2 - Webtoon, a portmanteau of web and cartoon, denotes a cartoon that has been published on a website. Recently, webtoons have become popular in the global Internet market. Unfortunately, the copyright infringement has emerged as a new challenge resulting in illegal profit gains. Moreover, it is difficult to apply watermarking to published webtoons, because they need to be watermarked prior to publication. In order to deal with a large number of published webtoons, it is necessary to identify each webtoon using fingerprints extracted from its webtoon image. In this paper, we propose an identification framework to detect copyright infringement due to the illegal copying and sharing of webtoons. The proposed identification framework consists of the following main stages: Fingerprint generation, indexing, and fingerprint matching. In the fingerprint generation stage, the translation invariant and temporally localized fingerprints are created for distortion-robust identification. An inverted indexing of the database is implemented, using the visual word clustering method and the MapReduce framework, to store the fingerprints efficiently and to minimize the searching time. In addition, we propose a two-step matching process for faster implementation. Moreover, we measured the identification accuracy and the matching time of a large-scale database in the presence of various distortions. Through rigorous simulations, we achieved an identification accuracy of 97.5% within 10 s for each webtoon.

AB - Webtoon, a portmanteau of web and cartoon, denotes a cartoon that has been published on a website. Recently, webtoons have become popular in the global Internet market. Unfortunately, the copyright infringement has emerged as a new challenge resulting in illegal profit gains. Moreover, it is difficult to apply watermarking to published webtoons, because they need to be watermarked prior to publication. In order to deal with a large number of published webtoons, it is necessary to identify each webtoon using fingerprints extracted from its webtoon image. In this paper, we propose an identification framework to detect copyright infringement due to the illegal copying and sharing of webtoons. The proposed identification framework consists of the following main stages: Fingerprint generation, indexing, and fingerprint matching. In the fingerprint generation stage, the translation invariant and temporally localized fingerprints are created for distortion-robust identification. An inverted indexing of the database is implemented, using the visual word clustering method and the MapReduce framework, to store the fingerprints efficiently and to minimize the searching time. In addition, we propose a two-step matching process for faster implementation. Moreover, we measured the identification accuracy and the matching time of a large-scale database in the presence of various distortions. Through rigorous simulations, we achieved an identification accuracy of 97.5% within 10 s for each webtoon.

UR - http://www.scopus.com/inward/record.url?scp=85049440531&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049440531&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2845540

DO - 10.1109/ACCESS.2018.2845540

M3 - Article

AN - SCOPUS:85049440531

VL - 6

SP - 37932

EP - 37946

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8403906

ER -