International Journal of Advanced Research in Computer and Communication Engineering

A monthly peer-reviewed online and print journal

ISSN Online 2278-1021
ISSN Print 2319-5940

Abstract: For person recognition, we use different physiological and behavioural features such as iris, fingerprint, face, voice etc. Biometric Identification is one of the areas related to this. The biometric data of the user are usually stored in biometric template. So the protection of biometric template is necessary because the biometric features cannot be modified like traditional username and passwords. Biometric cryptosystems can be used to protect the biometric template in an efficient manner. Single Biometric Cryptosystem which uses a single biometric feature suffers the problem of noisy data and spoofs attacks. Multi-Biometric Cryptosystem uses two or more biometric features for the protection of biometric template. Multi-Biometric Cryptosystem are of different types which uses different fusion methods. A Multi-Biometric Cryptosystem based on Hybrid Fusion is implemented with the help of biometric features such as fingerprints and iris. Delaunay Triangulation is used to extract the fingerprint feature vector and Gabor Filter is used to extract the iris feature vector. AES Encryption is used to encrypt the data of the user using the keys generated from the biometric feature. Also, Hash Function is used to further protect each biometric feature. The FAR and FRR curve of this system shows that it provides high security to the user’s data

Keywords: Biometric, Cryptosystem, Delaunay Triangulation, Gabor Filter, Hybrid Fusion, Iris, Minutiae