A Hadamard Transform-Based Method for the Design of Cancellable Fingerprint Templates

Cancelable biometrics is an important biometric template protection scheme and can effectively address privacy and security concerns in the case of stored biometric templates being compromised. This paper presents a Hadamard transform-based approach to the design of cancelable fingerprint templates. The proposed cancelable templates are alignment-free and hence do not suffer from inaccurate fingerprint registration. The proposed method aims to protect the binary string's frequency-domain samples because they include essential information about original fingerprint minutiae. The protection of the binary string's frequency-domain samples is achieved by the proposed partial Hadamard transform. The non-invertible transformation involved in our approach features a partial Hadamard matrix, which can be readily formed by a randomly generated index vector. A compromised template can be canceled and a new one be produced by generating a different index vector. The proposed approach is evaluated over the publicly available databases FVC2002 DB2 and DB3. The experimental results demonstrate that the performance of the new method is satisfactory compared to those of the existing alignment-free cancelable fingerprint templates.