Presentation | 2014-02-17 A Generation Scheme of Protected Templates for Sparse Representation-based Face Recognition Masakazu FURUKAWA, Yuichi MURAKI, Masaaki FUJIYOSHI, Yoshihide TONOMURA, Hitoshi KIYA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In face recognition systems, facial images are recognized by comparing features (template) extracted from them. This paper proposes a generation scheme of protected templates which are tolerant to template leakage and applies the scheme to the sparse representation-based face recognition. Template leakage leads to disclose users' personal information so that templates should be protected. The proposed scheme for template protection consists of random pixel permutation and downsampling. It is difficult to reconstruct visual information of facial images from the templates protected with the proposed scheme even though parameters for random pixel permutation and down-sampling are disclosed to the public. Furthermore, the templates protected with the proposed scheme can be more effectively compressed in terms of the data size than those with the conventional scheme using random projection because the histogram of the templates protected with the proposed scheme is denser than that with the conventional scheme. Experimental results with two major database of facial images demonstrate the effectiveness of the proposed scheme in terms of recognition performance, difficulty of visual information reconstruction, and data compression. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Template protection / cancelable biometrics / biometrics / JPEG-LS / image compression / l^1-norm |
Paper # | ITS2013-42,IE2013-107 |
Date of Issue |
Conference Information | |
Committee | IE |
---|---|
Conference Date | 2014/2/10(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Image Engineering (IE) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Generation Scheme of Protected Templates for Sparse Representation-based Face Recognition |
Sub Title (in English) | |
Keyword(1) | Template protection |
Keyword(2) | cancelable biometrics |
Keyword(3) | biometrics |
Keyword(4) | JPEG-LS |
Keyword(5) | image compression |
Keyword(6) | l^1-norm |
1st Author's Name | Masakazu FURUKAWA |
1st Author's Affiliation | Dept. of Information and Communication Systems, Tokyo Metropolitan University() |
2nd Author's Name | Yuichi MURAKI |
2nd Author's Affiliation | Dept. of Information and Communication Systems, Tokyo Metropolitan University |
3rd Author's Name | Masaaki FUJIYOSHI |
3rd Author's Affiliation | Dept. of Information and Communication Systems, Tokyo Metropolitan University |
4th Author's Name | Yoshihide TONOMURA |
4th Author's Affiliation | NTT Network Innovation Laboratories, Nippon Telegraph and Telephone Corp. |
5th Author's Name | Hitoshi KIYA |
5th Author's Affiliation | Dept. of Information and Communication Systems, Tokyo Metropolitan University |
Date | 2014-02-17 |
Paper # | ITS2013-42,IE2013-107 |
Volume (vol) | vol.113 |
Number (no) | 434 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |