Presentation 2005-12-15
A Comparison between a Local Feature and a Global Feature for Identical Video Segment Detection
Fuminori YAMAGISHI, Shin'ichi SATOH, Alexis JOLY, Olivier BUISSON, Nozha BOUJEMAA, Masao SAKAUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Some kind of video footage is repeatedly used in a video archive. Identical Video Segment Deteciton, which is a detection of those video footages in a large video database, can be used for video data mining or copyright protection. For the detection, usually feature vectors extracted from each frame image are used. Those features can roughly devided into local features and global features. In this paper, we use two different features for Identical Video Segment Detection. They are (1) a local feature which is extracted from pixels around a Harris interest point, and (2) a global feature which is an intensity histogram extracted from a whole frame image. We apply them to a video archive and discuss about them.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Identical Video Segment Detection / Large-scale Broadcast Video Archive / Video Datamining / Global Features / Local Features
Paper # PRMU2005-124
Date of Issue

Conference Information
Committee PRMU
Conference Date 2005/12/8(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Comparison between a Local Feature and a Global Feature for Identical Video Segment Detection
Sub Title (in English)
Keyword(1) Identical Video Segment Detection
Keyword(2) Large-scale Broadcast Video Archive
Keyword(3) Video Datamining
Keyword(4) Global Features
Keyword(5) Local Features
1st Author's Name Fuminori YAMAGISHI
1st Author's Affiliation Graduate School of Information Science and Technology, The University of Tokyo()
2nd Author's Name Shin'ichi SATOH
2nd Author's Affiliation National Institute of Informatics
3rd Author's Name Alexis JOLY
3rd Author's Affiliation INRIA-IMEDIA
4th Author's Name Olivier BUISSON
4th Author's Affiliation INA
5th Author's Name Nozha BOUJEMAA
5th Author's Affiliation INRIA-IMEDIA
6th Author's Name Masao SAKAUCHI
6th Author's Affiliation National Institute of Informatics
Date 2005-12-15
Paper # PRMU2005-124
Volume (vol) vol.105
Number (no) 477
Page pp.pp.-
#Pages 5
Date of Issue