Multimodal Biometric Fusion of Face and Palmprint at Various Levels

Recent years have witnessed researchers paying enormous attention to design efficient multi-modal biometric systems because of their ability to withstand spoof attacks. Single biometric sometimes fails to extract adequate information for verifying the identity of a person [7]. On the other hand, by combining multiple modalities, enhanced performance reliability could be achieved. In this paper, we have fused face and palmprint modalities at all levels of fusion viz sensor level, feature level, decision level and score level. For this purpose, we have selected modality specific feature extraction algorithms for face and palmprint such as LDA and LPQ respectively. Popular databases AR (for face) and PolyU (for Palmprint) were considered for evaluation purposes. Rigorous experiments were conducted both under clean and noisy conditions to ascertain robust level of fusion and impact of fusion strategies at various levels of fusion for these two modalities. Results are substantiated with appropriate analysis.