Presentation 2020-07-20
Development of Feature Extractor for Visible Light Iris Recognition Using Deep Learning
Tetsuya Honda, Hironobu Takano,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Biometric authentication is superior to other personal authentication methods in terms of securityagainst theft and counterfeiting. Among biometric authentications, iris authentication can perform contactless authentication and has a higher authentication accuracy than other biometric modalities. When an iris image captured by a visible camera is used for authentication, the authentication accuracy may be decreased compared to that of a near-infrared iris image. Thus, it is required that the performance of visible iris authentication method is the same as those of personal authentication methods using the near-infrared iris image. We proposed the feature extractor using the multi-task CNN (Convolutional Neural Network) and compared with the authentication accuracy of the single-task CNN. From the experimental results, the EER (Equal Error Rate) of multi-task CNN was 0.9% lower than that of single-task CNN. The authentication performance was slightly improved by using the feature extractor of multi-task CNN.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) visible right iris authentication / CNN / multi-task
Paper # ISEC2020-16,SITE2020-13,BioX2020-19,HWS2020-9,ICSS2020-3,EMM2020-13
Date of Issue 2020-07-13 (ISEC, SITE, BioX, HWS, ICSS, EMM)

Conference Information
Committee SITE / ISEC / HWS / EMM / BioX / IPSJ-CSEC / IPSJ-SPT / ICSS
Conference Date 2020/7/20(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Security, etc.
Chair Masaru Ogawa(Kobe Gakuin Univ.) / Shoichi Hirose(Univ. of Fukui) / Makoto Ikeda(Univ. of Tokyo) / Masaki Kawamura(Yamaguchi Univ.) / Akira Otsuka(AIST) / / / Hiroki Takakura(NII)
Vice Chair Takushi Otani(Kibi International Univ.) / Takeo Tatsumi(Open Univ. of Japan) / Tetsuya Izu(Fujitsu Labs.) / Noboru Kunihiro(Univ. of Tokyo) / Yasuhisa Shimazaki(Renesas Electronics) / Makoto Nagata(Kobe Univ.) / Motoi Iwata(Osaka Prefecture Univ.) / Masaaki Fujiyoshi(Tokyo Metropolitan Univ.) / Takahiro Aoki(Fujitsu Labs.) / Masatsugu Ichino(Univ. of Electro-Comm.) / / / Katsunari Yoshioka(Yokohama National Univ.) / Kazunori Kamiya(NTT)
Secretary Takushi Otani(KDDI Research) / Takeo Tatsumi(Yamaguchi Pref Univ.) / Tetsuya Izu(Tsukuba Univ.) / Noboru Kunihiro(Fujitsu Labs.) / Yasuhisa Shimazaki(Kyushu Univ.) / Makoto Nagata(NTT) / Motoi Iwata(Tokyo Denki Univ.) / Masaaki Fujiyoshi(Kansai Univ.) / Takahiro Aoki(SECOM) / Masatsugu Ichino(KDDI Research) / / / Katsunari Yoshioka(NICT) / Kazunori Kamiya(KDDI labs.)
Assistant Daisuke Suzuki(Hokuriku Univ.) / Hideyuki Fujii(NRI-Secure) / Kazuki Yoneyama(Ibaraki Univ.) / / Madoka Hasegawa(Utsunomiya Univ.) / Maki Yoshida(NICT) / Emiko Sano(MitsubishiElectric) / Akihiro Hayasaka(NEC) / / / Keisuke Kito(Mitsubishi Electric) / Toshihiro Yamauchi(Okayama Univ.)

Paper Information
Registration To Technical Committee on Social Implications of Technology and Information Ethics / Technical Committee on Information Security / Technical Committee on Hardware Security / Technical Committee on Enriched MultiMedia / Technical Committee on Biometrics / Special Interest Group on Computer Security / Special Interest Group on Security Psychology and Trust / Technical Committee on Information and Communication System Security
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Development of Feature Extractor for Visible Light Iris Recognition Using Deep Learning
Sub Title (in English)
Keyword(1) visible right iris authentication
Keyword(2) CNN
Keyword(3) multi-task
1st Author's Name Tetsuya Honda
1st Author's Affiliation Toyama Prefectural University(Toyama Pref. Univ.)
2nd Author's Name Hironobu Takano
2nd Author's Affiliation Toyama Prefectural University(Toyama Pref. Univ.)
Date 2020-07-20
Paper # ISEC2020-16,SITE2020-13,BioX2020-19,HWS2020-9,ICSS2020-3,EMM2020-13
Volume (vol) vol.120
Number (no) ISEC-112,SITE-113,BioX-114,HWS-115,ICSS-116,EMM-117
Page pp.pp.15-19(ISEC), pp.15-19(SITE), pp.15-19(BioX), pp.15-19(HWS), pp.15-19(ICSS), pp.15-19(EMM),
#Pages 5
Date of Issue 2020-07-13 (ISEC, SITE, BioX, HWS, ICSS, EMM)