An Efficient Boosting Approach for Score Level Fusion of Face and Palmprint Biometrics in Human Recognition

Biometrics based personal identification is regarded as an effective method for automatically recognizing a person’s identity with confidence. A multimodal biometric system consolidates the evidence presented by multiple biometric sources and typically better recognition performance compare to systems based on a single biometric modality. This paper proposes a novel multipartite algorithm for score level fusion of multimodal biometric system identification using two biometric features i.e. face and palmprint. Multimodal biometric system is developed through fusion of face and palmprint recognition system. Further, to evaluate the performance of boosting-based fusion methods, experimental tests are carried over PolyU and CASIA databases. A comparative study is done by using different classification techniques on two databases.