Presentation 2001/6/21
High-speed face picture reference using the neural network
Yoshihiko Fukuta, Minoru Fukumi, Norio Akamatsu,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In order to recognize automatically faces with unknown position and size in a picture, the processing which takes out faces domain is required before face recognition. This research focuses on the skin color that is the prominent feature of faces. The method of finding skin color threshold using a neural network is proposed in this paper. A neural network gives threshold values corresponding to each picture, incorrect recognition under different light conditions is reduced, and high-speed skin color extraction is performed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neural network / threshold processing / skin color extraction / high-speed face detection
Paper # NC2001-16
Date of Issue

Conference Information
Committee NC
Conference Date 2001/6/21(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) High-speed face picture reference using the neural network
Sub Title (in English)
Keyword(1) neural network
Keyword(2) threshold processing
Keyword(3) skin color extraction
Keyword(4) high-speed face detection
1st Author's Name Yoshihiko Fukuta
1st Author's Affiliation Department of Information science and Intelligent systems Faculty of Engineering, University of Tokushima()
2nd Author's Name Minoru Fukumi
2nd Author's Affiliation Department of Information science and Intelligent systems Faculty of Engineering, University of Tokushima
3rd Author's Name Norio Akamatsu
3rd Author's Affiliation Department of Information science and Intelligent systems Faculty of Engineering, University of Tokushima
Date 2001/6/21
Paper # NC2001-16
Volume (vol) vol.101
Number (no) 153
Page pp.pp.-
#Pages 6
Date of Issue