No Detail Found!

Finger-knuckle-print recognition based on local and global feature sets.

Author(s)
Mounir Amraoui RT-LARIT, FSK, Morocco Department of Electrical Engineering, EHTP, Morocco
Mohamed El-Aroussi RT-LARIT, FSK, Morocco Department of Electrical Engineering, EHTP, Morocco
Rachid Saadane RT-LARIT, FSK, Morocco Department of Electrical Engineering, EHTP, Morocco
Mohammed Wahbi RT-LARIT, FSK, Morocco Department of Electrical Engineering, EHTP, Morocco
Abstract
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.
Publication Details
Page(s) 54-60
DOI DOI not available
Published Journal: Journal of Theoretical and Applied Information Technology, Volume: 46, Issue: 1, Year: 2012

Request the full text from PASTIC

0

Citations

0

Downloads

97

Views