Presentation 1999/5/20
Supervised Independent Component Analysis and Its Applications to Face Image Analysis
shinji Umeyama, Shotaro Akaho, Yasuko Sugase,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Independent Component analysis is a new data analysis method, and its computation algorithms and applications are widely studied recently. ICA decomposes observed data into several components bu using a criterion of statistical independence. However, observed data are sometimes obtained through some control signal, for ecample a visual stimulus in fMRI measurements. In this case it may be effective to use a control signal to salvage a independent component correlated woth it. We propose here such a method by extending ICA, and name it SICA (Supervised Independent Component Analysis). We also give several results of human face image analysis as an application of SICA.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) independent component analysis / Principal component analysis / supervised / face image
Paper # NC99-2
Date of Issue

Conference Information
Committee NC
Conference Date 1999/5/20(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) Supervised Independent Component Analysis and Its Applications to Face Image Analysis
Sub Title (in English)
Keyword(1) independent component analysis
Keyword(2) Principal component analysis
Keyword(3) supervised
Keyword(4) face image
1st Author's Name shinji Umeyama
1st Author's Affiliation Electrotechnical Laboratory()
2nd Author's Name Shotaro Akaho
2nd Author's Affiliation Electrotechnical Laboratory
3rd Author's Name Yasuko Sugase
3rd Author's Affiliation National Institute of Bioscience and Human-Technology
Date 1999/5/20
Paper # NC99-2
Volume (vol) vol.99
Number (no) 58
Page pp.pp.-
#Pages 8
Date of Issue