Presentation 2019-03-13
[Poster Presentation] Face Anti-spoofing Using Optical Flow
Fujimkai Shohei, Hyunho Kang,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this research, we introduce the approach to prevent attack by machine learning, using the motion information of the object called optical flow, against the spoofing attack occurring at face authentication. In previous studies, classification was often performed using only pixel information, but recently, classification methods using feature quantities including time information have come to be seen more frequently. And this time we used optical flow as an alternative time information option. By doing this, HTER (Half Total Error Rate) can be reduced by using the feature amount by multiplying with the optical flow rather than using the conventional LBP alone.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Optical Flow / LBP / spoofing
Paper # EMM2018-102
Date of Issue 2019-03-06 (EMM)

Conference Information
Committee EMM
Conference Date 2019/3/13(2days)
Place (in Japanese) (See Japanese page)
Place (in English) TBD
Topics (in Japanese) (See Japanese page)
Topics (in English) Image and Sound Quality, Metrics for Perception and Recognition, Human Auditory and Visual System, etc.
Chair Keiichi Iwamura(TUC)
Vice Chair Minoru Kuribayashi(Okayama Univ.) / Tetsuya Kojima(NIT,Tokyo College)
Secretary Minoru Kuribayashi(NIT, Tokyo) / Tetsuya Kojima(Tyukyo Univ.)
Assistant Hiroko Akiyama(NIT, Nagano College) / キタヒロ カネダ(CANON)

Paper Information
Registration To Technical Committee on Enriched MultiMedia
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Poster Presentation] Face Anti-spoofing Using Optical Flow
Sub Title (in English)
Keyword(1) Optical Flow
Keyword(2) LBP
Keyword(3) spoofing
1st Author's Name Fujimkai Shohei
1st Author's Affiliation National Institute of Technology ,Tokyo College(NITTC)
2nd Author's Name Hyunho Kang
2nd Author's Affiliation National Institute of Technology ,Tokyo College(NITTC)
Date 2019-03-13
Paper # EMM2018-102
Volume (vol) vol.118
Number (no) EMM-494
Page pp.pp.57-61(EMM),
#Pages 5
Date of Issue 2019-03-06 (EMM)