Secure Multimodal Biometric Authentication Using Face, Palmprint and Ear: A Feature Level Fusion Approach
Gayatri S. Ambadkar, Rajendra D. Kanphade · 2019
Widespread of biometric technology for identity management in many nations has given rise to new means for biometric research. Due to the cumulative requirement of higher security schemes, multiple biometrics are preferred over single biometric to generate most accurate authentication result. Involving multiple biometric traits comes up with challenges to combine the feature data by selecting proper level of fusion. This paper proposes reduced dimension feature vector concatenation method for three biometric traits like Face, Palmprint and Ear. The use of only one algorithm of Principal Component Analysis for feature extraction and Euclidean distance for final matching make the system robust by reducing the computational complexity. The resultant biometric template is also protected by using intermixing of feature vector scheme.