Multimodal Biometrics Using Palm and Iris

Biometrics based personal identification is regarded as an effective method for automatically recognizing a person’s identity with high confidence. Multimodal biometric systems consolidates the evidence presented by multiple biometric sources and typically give better recognition performance compared to the system based on a single biometric modality. This paper proposes an authentication method for a multimodal biometric system identification using two traits i.e. Iris and palm print. In order to enhance the accuracy of the iris localization, we use the algorithm that combines the merits of wavelet analysis and Hough transform. For Palm print image we use Sequential modified Haar transform that is applied to the resized Palm print image to obtain Modified Haar Energy (MHE) feature. Matching score level fusion is used because matching scores are easily available and contain sufficient information to distinguish between a genuine and an impostor case. Both trait can be matched with the help of Hamming Distance based matching .The receiver operating curve (Roc) is drawn between False Acceptance Rate (FAR) vs False Rejection Rate (FRR).The accuracy can be improved significantly.