Multi-Modal Biometric Recognition of Face and Palm-Print Using Matching Score Level Fusion

This paper proposes a multi-modal biometric recognition system using Face and Palm-print as biometric modalities. The main aim of this paper is to increase robustness of the recognition systems. Both modalities are combined using various biometric fusion techniques. Multi-modal biometric fusion can be implemented by using importantly two approaches i.e. Classification approach and Combination approach. Classification approach include techniques like k-Nearest Neighbors (kNN), Random Forest, etc. Confidence based approach include techniques like wavelet transformation, HOG, DCT, etc. Biometric fusion was implemented on matching score level. Experiments were conducted on faces94, faces95, faces96 and IITD Palmprint Database using various Face recognition and Palm recognition algorithms. Results of which are discussed further in the paper. The experimental results infer that biometric fusion greatly increase the robustness of a biometric recognition system.