Abstract
With an ever-increasing emphasis on security and the new dimensions in security challenges facing the world today, the need for automated personal identification/verification system based on multimodal biometrics has increased. This paper addresses the issue of multiple biometric fusion to enhance the security of recognition. The paper utilizes iris, speech,and speech for the novel fusion. A segregated classification mechanism for each biometric is also presented. The fusion is done on the base of features extracted at the time of individual classification of biometrics. Different feature extraction algorithms are applied for different biometrics. The paper has utilized 2-Dimensional Principle Component Analysis (2DPCA) for Iris, Scale Invariant Feature Transform (SIFT) for signature and Mel-frequency cepstral coefficients for speech biometric. This paper utilizes Genetic Algorithm for the optimization of the evaluated features. The classification is done using Artificial Neural Network (ANN).