Presentation 2017-10-12
Face identification based on shape spaces randomly generated from facial minute feature points
Kazuki Takasaka, Kazuhiro Fukui,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a face identification method based on the 3-d structure of facial minute feature points. The proposed method realizes high accuracy identification by introducing random sampling, even when detection of minute feature points is unstable. In the proposed method, we acquire feature points by random sampling from detected candidate points. Next, we generate a shape space from the obtained feature points. The shape space represents the 3-d structure of feature points. Identification is performed based on similarity between the corresponding shape spaces. We introduce Grassmann discriminant analysis upon identification. The effectiveness of the proposed method is demonstrated by experiment.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Random Sampling / Face Identification / Shape Space / Canonical Angle
Paper # PRMU2017-66
Date of Issue 2017-10-05 (PRMU)

Conference Information
Committee PRMU
Conference Date 2017/10/12(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Shinichi Sato(NII)
Vice Chair Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron)
Secretary Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST)
Assistant Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Face identification based on shape spaces randomly generated from facial minute feature points
Sub Title (in English)
Keyword(1) Random Sampling
Keyword(2) Face Identification
Keyword(3) Shape Space
Keyword(4) Canonical Angle
1st Author's Name Kazuki Takasaka
1st Author's Affiliation Tsukuba University(Tsukuba Univ.)
2nd Author's Name Kazuhiro Fukui
2nd Author's Affiliation Tsukuba University(Tsukuba Univ.)
Date 2017-10-12
Paper # PRMU2017-66
Volume (vol) vol.117
Number (no) PRMU-238
Page pp.pp.19-24(PRMU),
#Pages 6
Date of Issue 2017-10-05 (PRMU)