Feature level Fusion for Multi-biometric with identical twins

Abstract

The power of multi-biometric fusion for identical twins at the feature-level with Dis-Mean algorithm is addressed in this work. A feature-fusion framework is geared toward improving identical twins identification accuracy for multiple biometrics. A novel multi-biometric system is thus designed based on the framework, which serves as fusion guidelines for multi-biometric applications that fuse at the feature-level with identical twins. This framework was applied to the twin handwriting and fingerprint to 30 twins with 480 images, when using MAE for intra-class and inter-class for accuracy. The result provides an alternative mechanism to detect identical twin besides using the traditional methods.