Presentation 2012-03-01
Image Attribute Class Detection by Using the EMD
Hironobu FUKAI, Yasue MITSUKURA, Nozomu HAMADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we describe a novel age and gender estimation using an empirical mode decomposition. Recently, an empirical mode decomposition that is a time-frequency analysis method are attracting attention. This algorithm do not have time-frequency trade-off such as short-time Fourier transform and wavelet transform, and decompose as summation of narrow band signal. These are merits and features of this algorithm. However, discussions of the effectiveness of this algorithm are still few. Therefore, we verify the effectiveness by actual example that are age and gender estimation using facial images.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) time-frequency analysis / empirical mode decomposition / facial image / age estimation / gender estimation
Paper # SIS2011-53
Date of Issue

Conference Information
Committee SIS
Conference Date 2012/2/23(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 Smart Info-Media Systems (SIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Image Attribute Class Detection by Using the EMD
Sub Title (in English)
Keyword(1) time-frequency analysis
Keyword(2) empirical mode decomposition
Keyword(3) facial image
Keyword(4) age estimation
Keyword(5) gender estimation
1st Author's Name Hironobu FUKAI
1st Author's Affiliation College of Information Science & Engineering, Ritsumeikan University()
2nd Author's Name Yasue MITSUKURA
2nd Author's Affiliation Faculty of Science and Technology, Keio University
3rd Author's Name Nozomu HAMADA
3rd Author's Affiliation Faculty of Science and Technology, Keio University
Date 2012-03-01
Paper # SIS2011-53
Volume (vol) vol.111
Number (no) 457
Page pp.pp.-
#Pages 4
Date of Issue