Invariant feature extraction for finger vein matching using fuzzy logic inference

Abstract

Finger vein is a new member in the biometrics family. In the recent years, as a biometric trait finger vein has been achieved success and attracted lots of attention from the researchers. Current finger vein recognition algorithms provide high accuracy in good quality images. Most of the finger vein recognition systems utilize based on minutiae points. In this paper, we propose a method for finger vein matching using scale-invariant feature transformation (SIFT) key points which are determining the rules using fuzzy inference system and the matching scores are delivered by Euclidean distance. The fuzzy logic system provides the more adequate description of the proposed algorithm. The algorithm has been formulated based on SIFT key points which examine n number of images. MATLAB 7:14:0 is used to implement this technique.