W.Y. Choi, D. Moon, K.Y. Moon, and Y. Chung (Korea)
Crypto-biometrics, Fuzzy Vault, Fingerprint Recognition
Biometric based authentication can provide strong security guarantee about the identity of users. However, security of biometric data is particularly important as compromise of the data will be permanent. Cancelable biometrics stores a non-invertible transformed version of the biometric data. Thus, even if the storage is compromised, the biometric data remains safe. Recently, a cryptographic construct, called fuzzy vault, has been proposed, which aims to secure critical data (e.g., secret encryption key) with the biometric data in a way that only the authorized user can access the secret by providing the valid biometric. An automatic fin gerprint alignment in fuzzy fingerprint vault is challenging, however, because aligning two fingerprints is more difficult than other biometrics and should be performed in a non invertible transformed domain. In this paper, we propose a new alignment algorithm for fuzzy fingerprint vault, which needs no extra information, such as geometric hash tables, helper data, and so on. The experiments were performed on FVC2002 database, and the results showed the excellence of the proposed algorithm.
Important Links:
Go Back
