Information Fusion and Person Authentication Using Face and Fingerprint Data

Abstract

Due to the increase in security requirements, biometric systems have been commonly utilized in many recognition applications. Present multimodal face and finger veins biometric verification system to improve the performance. The presented approach is divided into two parts: Face authentication and fusion Finger veins authentication, and fusion with fused face result at first level. For finger veins, we used the Gabor filter to enhance the finger vein image and then thinning operation is performed to obtain the skeleton for feature extraction. Presented multilevel fuzzy fusion of face and finger veins to provide better accuracy. Here performed weighted Fuzzy fusion on the fused result of face and finger veins. The score level fusion within CSLDA for face recognition and fusion of fused face result and finger veins result is performed. For fusion of face and finger veins, we performed weighted Fuzzy fusion on the fused result of face and finger veins. Simulation results shows that proposed multimodal recognition system is very efficient to reduce the false rejection rate.