Constructing cancellable template with synthetic minutiae
Qinghai Gao, Cheng Zhang · IET Biometrics · 2017
Security measures have to be taken to protect the privacy of biometric data. Cancellablebiometrics is proposed as an effective mechanism of using and protectingbiometrics. The authors propose a new approach of constructing cancellablefingerprint template by mapping real minutiae to randomly generated minutiae ina synthetic template. The synthetic minutiae are selected based on the k ‐nearest neighbour method. One synthetic neighbour of eachreal minutia is utilised to construct the verification template (VT). Since thesynthetic template is determined by a user‐specific PIN and a random salt, theproposed method is in fact a two‐factor authentication scheme. Multiple VTs canbe generated easily by applying different PINs and salts to a real template. Toprove the validity of the scheme, testing is carried out on three databases. Afew factors affecting matching are also investigated. The results show that theconstructed templates satisfy the requirements of cancellable biometrics. Falsenon‐match rate and False matching rate with the transformed templates can bemuch lower than those with the original templates by properly selecting the sizeof the synthetic templates and the ordinal number of the nearest neighbours. Theproposed approach can also be utilised for multi‐generation templatetransformation.