Wavelet based Multimodal Biometrics with Score Level Fusion Using Mathematical Normalization

Biometric based authentication is playing a very important role in various security related applications. A novel multimodal biometric verification based on fingerprint, palmprint and iris with matching score level fusion using Mathematical Normalization is proposed in this paper. In feature extraction stage of unimodal, features of each modality are extracted by applying wavelet decomposition using 6 different wavelet families and 35 respective wavelet family members. Further, the three optimal combinations of unimodal systems based on equal error rate achieved by wavelet(s) are chosen for development of multimodal biometric system. In matching score level fusion, along with wellknown normalization techniquesMin-max, Tan-h and Zscore, the performance of multimodal systems are also analyzed using Mathematical Normalization (Math-norm) followed by product, weighted product, sum and average fusion rule. The experiments are conducted on database of 100 different subjects from publically available FVC2006, CASIA V1 and IITD database of fingerprint, palmprint and iris, respectively. The experimental results clearly show that Mathematical Normalization followed by weighted product has given promising accuracy with equal error rate (EER) of 0.325%.