Fuzzy Vault for Face Based Cryptographic Key Generation
Yongjin Wang, Konstantinos N. Plataniotis · 2007
This paper presents a method for changeable cryptographic key generation using face biometrics signal. A previously introduced scheme, fuzzy vault, is utilized for secure binding of randomly generated key with extracted biometrics features. The major technical difficulty is to map noisy biometrics representation to the exactly correct key. In this paper, the proposed method is based on 2-dimensional quantization of distance vectors between biometrics features and pairs of random vectors. A windowing process is applied to tolerate the variations of biometrics signals. Further, we also introduce a two-factor scheme, where the quantized distance vectors are generated with user-dependent random vectors. By integrating a second factor, both the biometrics and the key are changeable, and zero error rate can be obtained.