Presentation 2020-03-05
Applying Deep Metric Learning to Periocular Biometrics
Tomoki Nukata, Hiroshi Yoshiura, Masatsugu Ichino,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Periocular biometrics has been studied in recent years due to spread of surveillance cameras and smartphones. Zhao et. al. proposed the convolutional neural network that extracts texture and shape features of an eyebrow and an eye based on knowledge that their shapes are important for authentication. This convolutional neural network is trained by DSC Loss that is one of the loss functions used in Deep Metric Learning. This study improved Zhao’s methods and showed their e?ectiveness.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Periocular Biometrics / Deep Metric Learning
Paper # BioX2019-73,CNR2019-56
Date of Issue 2020-02-26 (BioX, CNR)

Conference Information
Committee BioX / CNR
Conference Date 2020/3/4(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Akira Otsuka(IISEC) / Kazunori Takashio(Keio Univ.)
Vice Chair Tetsushi Ohki(Shizuoka Univ.) / Takahiro Aoki(Fujitsu Labs.) / Masayuki Kanbara(NAIST) / Yoshihiko Murakawa(Fujitsu Labs.)
Secretary Tetsushi Ohki(Univ. of Electro-Comm.) / Takahiro Aoki(SECOM) / Masayuki Kanbara(Shibaura Inst. of Tech.) / Yoshihiko Murakawa(Panasonic)
Assistant Daishi Watabe(Saitama Inst. of Tech.) / Ryota Horie(Shibaura Inst. of Tech.) / Yuka Kobayashi(Toshiba) / Masanori Yokoyama(NTT)

Paper Information
Registration To Technical Committee on Biometrics / Technical Committee on Cloud Network Robotics
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Applying Deep Metric Learning to Periocular Biometrics
Sub Title (in English)
Keyword(1) Periocular Biometrics
Keyword(2) Deep Metric Learning
1st Author's Name Tomoki Nukata
1st Author's Affiliation The University of Electro-Communications(UEC)
2nd Author's Name Hiroshi Yoshiura
2nd Author's Affiliation The University of Electro-Communications(UEC)
3rd Author's Name Masatsugu Ichino
3rd Author's Affiliation The University of Electro-Communications(UEC)
Date 2020-03-05
Paper # BioX2019-73,CNR2019-56
Volume (vol) vol.119
Number (no) BioX-445,CNR-446
Page pp.pp.65-70(BioX), pp.65-70(CNR),
#Pages 6
Date of Issue 2020-02-26 (BioX, CNR)