Finger vein secure biometric template generation based on deep learning
- 542 Downloads
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.
KeywordsSecure biometric template Random projection Deep belief network
This work is supported by the National Natural Science Foundation of China (61572144), the Natural Science Foundation of Guangdong (2014A030313517), the Science and Technology Planning Project of Guangdong Province (2015B010129015, 2013B040500009), the Zhejiang Sicence Fund No. LY16F020016 and the Innovation Team Project of Guangdong Universities (No 2015KCXTD014).
Compliance with ethical standards
Conflict of interest
Yi Liu, Jie Lin, Zhusong Liu, Jian Shen and Chongzhi Gao all declare that they have no conflict of interest.
- Ang R, Safavi-Naini R, Mcaven L (2005) Cancelable key-based fingerprint templates. In: Proceedings of the Australasian conference information security and privacy (ACISP 2005), Brisbane, Australia, July 4–6, 2005, pp 242–252Google Scholar
- Chen C, Wu Z, Li P, Zhang J, Wang Y, Li H (2015) A finger vein recognition algorithm using feature block fusion and depth neural network. In: International symposium on intelligence computation and applications, Springer, Berlin, pp 572–583Google Scholar
- Hinton GE (2010) A practical guide to training restricted Boltzmann machines. Momentum 9(1):599–619Google Scholar
- Jain AK, Ross A, Uludag U (2005) Biometric template security: Challenges and solutions. In: 2005 13th European signal processing conference. IEEE, pp 1–4Google Scholar
- Li X, Guo S, Gao F, Li Y (2007) Vein pattern recognitions by moment invariants. In: The international conference on bioinformatics and biomedical engineering, pp 612–615Google Scholar
- Pankanti S, Jain A, Hong L (2000) Biometrics: promising frontiers for emerging identification market. Comm ACM 43:91–98Google Scholar
- Quan F, Fei S, Anni C, Feifei Z (2008) Cracking cancelable fingerprint template of ratha. In: International symposium on computer science and computational technology, pp 572–575Google Scholar
- Shen J, Tan H, Wang J, Wang J, Lee S (2015) A novel routing protocol providing good transmission reliability in underwater sensor networks. J Internet Technol 16(1):171–178Google Scholar
- Wang KJ (2007) Finger vein recognition based on wavelet moment fused with PCA transform. Pattern Recognit Artif Intell 20(5):692–697Google Scholar
- Zheng Y, Byeungwoo J, Xu D, Wu QMJ, Zhang H (2015) Image segmentation by generalized hierarchical fuzzy c-means algorithm. J Intell Fuzzy Syst 28(2):4024–4028Google Scholar