An effective multi-biometrics solution for embedded device

Biometric solution for embedded device gained significant attention in the commercial and research sectors over recent years. Combining multiple biometrics may enhance the performance of personal verification system in accuracy and reliability. This paper presents a new multi-biometric verification solution aimed at implementing on an embedded system within a wide range of applications. The system combines the voiceprint and fingerprint biometrics and makes decision at score level. Fusion strategy is based on score normalization and support vector machine (SVM) classifier. We tested the performances of SVM using three kernel functions for system adaptation. Experimental result demonstrates that proposed multi-biometric verification approach achieves 1.0067% equal error rate (EER) that can be deployed in majority of embedded devices such as PDA and smart cell phone for user´s identity verification.