Presentation 2012-03-30
Automatic Extraction of Appearance Information of Characters in a Movie Based on Shot Detection
Hiroyuki KANOMATA, Ikuko SHIMIZU,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Metadata is indexing information about a video data, and is useful in presentation of the information that a user desires out of a lot of videos. Especially, metadata of characters in a movie is important information for video analysis. However, manually creating of metadata requires a great deal of labor. In this paper, we propose a method for automatic extraction of metadata of characters in a movie. In face detection and tracking process, we extract face images which are effective for face recognition. In face recognition process, we classify face images according to character based on shot change information extracted by cut detection. Experiments using video data of TV shows and movies demonstrate the effectivity of proposed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Metadata / Cut Detection / Face Detection / Face Tracking / Face Recognition
Paper # PRMU2011-277,HIP2011-105
Date of Issue

Conference Information
Committee HIP
Conference Date 2012/3/22(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 Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Automatic Extraction of Appearance Information of Characters in a Movie Based on Shot Detection
Sub Title (in English)
Keyword(1) Metadata
Keyword(2) Cut Detection
Keyword(3) Face Detection
Keyword(4) Face Tracking
Keyword(5) Face Recognition
1st Author's Name Hiroyuki KANOMATA
1st Author's Affiliation Tokyo University of Agri. and Tech.()
2nd Author's Name Ikuko SHIMIZU
2nd Author's Affiliation Tokyo University of Agri. and Tech.
Date 2012-03-30
Paper # PRMU2011-277,HIP2011-105
Volume (vol) vol.111
Number (no) 500
Page pp.pp.-
#Pages 6
Date of Issue