Improved finger-knuckle-print authentication based on orientation enhancement

Abstract

Presented is a new approach to person verification using finger-knuckle-prints (FKPs). It applies a Gabor filter to enhance the FKP information and a scale invariant feature transform (SIFT) to extract the features. Experiments with the most representative FKP public database confirm that the SIFT features obtained after Gabor enhancement of the principal finger knuckle lines improve the performance of the person identifier.