| Presentation | 2018-07-27 Personal Authentication by Eye Blink Using Time-series Directional Features Keisuke Takano, Azusa Takano, Hironobu Takano, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The continuous authentication using biometric information is required for the anti-spoofing after recognition. In this study, we propose the personal authentication method using characteristics of eye blink. The time-series variations of gradient directional intensity are adopted as the features for recognition. The features for recognition are obtained in three eye regions which are surrounds of the inner corner of one’s eye, iris, and the corner of an eye. The matching of registration and recognition features is performed with the dynamic time warping (DTW). From the experimental results, the equal error rate decreased by 3.82% when the score level fusion is introduced to calculate the degree of similarity. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Biometrics / Eye blink / Gradient feature / Score-level fusion / EER |
| Paper # | BioX2018-14,MBE2018-22 |
| Date of Issue | 2018-07-19 (BioX, MBE) |
| Conference Information | |
| Committee | MBE / BioX |
|---|---|
| Conference Date | 2018/7/26(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Masaki Kyoso(TCU) / Kazuhiko Sumi(AGU) |
| Vice Chair | Taishin Nomura(Osaka Univ.) / Hitoshi Imaoka(NEC) / Tetsushi Ohki(Shizuoka Univ.) |
| Secretary | Taishin Nomura(Kindai Univ.) / Hitoshi Imaoka(Fujitsu Labs.) / Tetsushi Ohki(Univ. of Electro-Comm.) |
| Assistant | Takumi Kobayashi(YNU) / Yasuyuki Suzuki(Osaka Univ.) / Norihiro Okui(KDDI Research) / Daishi Watabe(Saitama Inst. of Tech.) |
| Paper Information | |
| Registration To | Technical Committee on ME and Bio Cybernetics / Technical Committee on Biometrics |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Personal Authentication by Eye Blink Using Time-series Directional Features |
| Sub Title (in English) | |
| Keyword(1) | Biometrics |
| Keyword(2) | Eye blink |
| Keyword(3) | Gradient feature |
| Keyword(4) | Score-level fusion |
| Keyword(5) | EER |
| 1st Author's Name | Keisuke Takano |
| 1st Author's Affiliation | Toyama Prefectural University(Toyama Pref. Univ.) |
| 2nd Author's Name | Azusa Takano |
| 2nd Author's Affiliation | Toyama Prefectural University(Toyama Pref. Univ.) |
| 3rd Author's Name | Hironobu Takano |
| 3rd Author's Affiliation | Toyama Prefectural University(Toyama Pref. Univ.) |
| Date | 2018-07-27 |
| Paper # | BioX2018-14,MBE2018-22 |
| Volume (vol) | vol.118 |
| Number (no) | BioX-156,MBE-157 |
| Page | pp.pp.39-43(BioX), pp.39-43(MBE), |
| #Pages | 5 |
| Date of Issue | 2018-07-19 (BioX, MBE) |