Presentation 2018-11-10
Discussion of a facial authentication method using estimation of time series facial image in e-Testing
Taisuke Kawamata, Takako Akakura,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) One problem in e-testing is cheating easily by impersonation. In our previous work, a facial authentication was proposed for e-testing. Traditional biometrics identify a student with comparing pre-registered with input information, but this procedure cannot authenticate any students who often tend to write the posture during e-Testing. Therefore, we report the authentication focused on the variation of face pose with the machine learning. As a result of the evaluation, the accuracy of examinated authentication method is about 90% and we found the proposed method is useful for an unknown attacker.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) e-testing / proxy test-taking / biometrics / examinee authentication
Paper # ET2018-62
Date of Issue 2018-11-03 (ET)

Conference Information
Committee ET
Conference Date 2018/11/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Tokyo Polytechnic University
Topics (in Japanese) (See Japanese page)
Topics (in English) Sessions for Young Researchers (Young Researcher Awards Selection), etc.
Chair Yozo Miyadera(Tokyo Gakugei Univ.)
Vice Chair Ryo Takaoka(Yamaguchi Univ.)
Secretary Ryo Takaoka(Open Univ. of Japan)
Assistant Megumi Kurayama(National Inst. of Tech., Hakodate College) / Masaru Okamoto(Hiroshima City Univ.)

Paper Information
Registration To Technical Committee on Educational Technology
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Discussion of a facial authentication method using estimation of time series facial image in e-Testing
Sub Title (in English)
Keyword(1) e-testing
Keyword(2) proxy test-taking
Keyword(3) biometrics
Keyword(4) examinee authentication
1st Author's Name Taisuke Kawamata
1st Author's Affiliation Tokyo University of Science(TUS)
2nd Author's Name Takako Akakura
2nd Author's Affiliation Tokyo University of Science(TUS)
Date 2018-11-10
Paper # ET2018-62
Volume (vol) vol.118
Number (no) ET-294
Page pp.pp.47-50(ET),
#Pages 4
Date of Issue 2018-11-03 (ET)