Presentation | 2021-12-16 Low-Resolution Iris Recognition with Image Super-Resolution for arbitrary magnification Tsubasa Bora, Takahiro Toizumi, Yuho Shoji, Yuka Ogino, Masato Tsukada, Masatsugu Ichino, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | A low-resolution iris image reduces iris recognition accuracy. Some conventional researches tackle low-resolution iris recognition using image super-resolution techniques. However, general image super-resolution methods drop personal identity information, and these regard super-resolution of different scales as independent tasks. In this paper, we propose low-resolution iris recognition based on super-resolution of arbitrary scale factors keeping a recognition accuracy. Our method utilizes a probability distribution to control a scale selection during training to suppress differences in recognition performance from different scale super-resolution. We show that our proposed method keeps the recognition accuracy by lower resolution than the conventional methods. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Biometrics / Iris recognition / Deep learning / Image super-resolution / CNN |
Paper # | PRMU2021-26 |
Date of Issue | 2021-12-09 (PRMU) |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2021/12/16(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Seiichi Uchida(Kyushu Univ.) |
Vice Chair | Masakazu Iwamura(Osaka Pref. Univ.) / Mitsuru Anpai(Denso IT Lab.) |
Secretary | Masakazu Iwamura(NTT) / Mitsuru Anpai(Tottori Univ.) |
Assistant | Kouta Yamaguchi(CyberAgent) / Yusuke Matsui(Univ. of Tokyo) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Low-Resolution Iris Recognition with Image Super-Resolution for arbitrary magnification |
Sub Title (in English) | |
Keyword(1) | Biometrics |
Keyword(2) | Iris recognition |
Keyword(3) | Deep learning |
Keyword(4) | Image super-resolution |
Keyword(5) | CNN |
1st Author's Name | Tsubasa Bora |
1st Author's Affiliation | The University of Electro-Communications(UEC) |
2nd Author's Name | Takahiro Toizumi |
2nd Author's Affiliation | NEC Corporation(NEC) |
3rd Author's Name | Yuho Shoji |
3rd Author's Affiliation | NEC Corporation(NEC) |
4th Author's Name | Yuka Ogino |
4th Author's Affiliation | NEC Corporation(NEC) |
5th Author's Name | Masato Tsukada |
5th Author's Affiliation | NEC Corporation(NEC) |
6th Author's Name | Masatsugu Ichino |
6th Author's Affiliation | The University of Electro-Communications(UEC) |
Date | 2021-12-16 |
Paper # | PRMU2021-26 |
Volume (vol) | vol.121 |
Number (no) | PRMU-304 |
Page | pp.pp.13-18(PRMU), |
#Pages | 6 |
Date of Issue | 2021-12-09 (PRMU) |