Gokulakumar.A.S, Venkataraghavan.C, Kavya priya.S, Suganya.T
The security is an important aspect in our daily life whichever the system we consider security plays vital role. The biometric person identification technique based on the pattern of the human Iris and face is well suited to be applied to access control and provides Strong security. In this paper we focus on an efficient methodology of fusion of iris and face for identification and verification with total success rate. In this method, the image of the face taken is normalized and converted into binaries. The iris is localized from the facial image and then series of operations such as segmentation, normalization, feature encoding is performed and it is converted into binaries. These bits are compressed and crossed over into a combined biometric key. This combined biometric key is used to bind the each bit of the cryptographic key. This binded version of the key is used for enrollment and to release the key. Instead of storing the actual key, its hashed version is stored in order to conceal the cryptographic key to provide a secure comparison method for key verification. This binded version of the key is released only if this matches with the one which is generated lively. During enrollment, these features are used to bind a cryptographic key. The operation involved is the binary XOR. Here, the goal of the system is to reject, an unauthorized subject who does not possess the original face features used during enrollment. In contrast, a genuine subject with the correct face features will be accepted. By this spoofing can be avoided, since two kinds of keys are needed to encrypt the data and these keys are generated at once. This reduces the false acceptance rate and false rejection rate thereby the total success rate seems to be high since the key preserves security level to high.