Finger-knuckle-print Recognition Based on Local and Global Feature Sets

A new biometrics recognition, finger-knuckle-print (FKP), has attractive interests of researchers. Based on the results of psychophysics and neurophysiology studies, both local and global information is crucial for the image perception, Therefore we present a novel approach for finger-knuckle-print recognition combining classifiers based on both micro texture in spatial domain provided by local binary pattern (LBP) and macro information in frequency domain acquired from the discrete cosine transform (DCT) to represent FKP image. The classification of these two feature sets is performed by using support vector machines (SVMs), which had been shown to be superior to traditional pattern classifiers. The experiments clearly show the superiority of the proposed classifier combination approaches over individual classifiers on the recently published PolyU knuckle database.