Fuzzy Vault for Face Based Cryptographic Key Generation

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