We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Finger vein secure biometric template generation based on deep learning.
- Authors
Liu, Yi; Ling, Jie; Liu, Zhusong; Shen, Jian; Gao, Chongzhi
- Abstract
Leakage of unprotected biometric authentication data has become a high-risk threat for many applications. Lots of researchers are investigating and designing novel authentication schemes to prevent such attacks. However, the biggest challenge is how to protect biometric data while keeping the practical performance of identity verification systems. For the sake of tackling this problem, this paper presents a novel finger vein recognition algorithm by using secure biometric template scheme based on deep learning and random projections, named FVR-DLRP. FVR-DLRP preserves the core biometric information even with the user’s password cracked, whereas the original biometric information is still safe. The results of experiment show that the algorithm FVR-DLRP can maintain the accuracy of biometric identification while enhancing the uncertainty of the transformation, which provides better protection for biometric authentication.
- Subjects
BIOMETRIC identification; DEEP learning; COMPUTER security; RANDOM projection method; COMPUTER passwords
- Publication
Soft Computing - A Fusion of Foundations, Methodologies & Applications, 2018, Vol 22, Issue 7, p2257
- ISSN
1432-7643
- Publication type
Article
- DOI
10.1007/s00500-017-2487-9