Video copy detection based on segment feature extraction

Jaekwang Kim, Jae Hyung Jang, Tae Yeon Kim, Jee Hyong Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Video has recently been commonly used for transferring information due to the continuous growth of the Internet. Because of this, illegal video copy detection is one of the most needed technologies. Existing video copy detection methods compare the whole video frames, so it may take a long time to detect a copy among many reference videos. In this paper, we propose a video copy detection method based on segment feature extraction. Our method groups similar frames as a segment, and then compares the similarity between two videos based on the segments. To evaluate our method, we used 100-hour quantity reference videos and 50 video files. We measured the video copy detection time and the detection accuracy by comparing with these sources. The result of these tests confirms that our method is 60 times more time-cost effective than, and just as accurate as, the existing method.

Original languageEnglish
Title of host publicationProceedings of the 10th IASTED International Conference on Artificial Intelligence and Applications, AIA 2010
Pages224-228
Number of pages5
StatePublished - 2010
Externally publishedYes
Event10th IASTED International Conference on Artificial Intelligence and Applications, AIA 2010 - Innsbruck, Austria
Duration: 15 Feb 201017 Feb 2010

Publication series

NameProceedings of the 10th IASTED International Conference on Artificial Intelligence and Applications, AIA 2010

Conference

Conference10th IASTED International Conference on Artificial Intelligence and Applications, AIA 2010
Country/TerritoryAustria
CityInnsbruck
Period15/02/1017/02/10

Keywords

  • Multimedia
  • Segment feature extraction
  • Video copy detection

Fingerprint

Dive into the research topics of 'Video copy detection based on segment feature extraction'. Together they form a unique fingerprint.

Cite this