期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2014
卷号：67
期号：1
出版社：Journal of Theoretical and Applied
摘要：Biometrics is identifying a person using their physiological/behavioral features. Recently, vein pattern biometrics attracted interest from research communities. Finger-vein recognition is a new biometrical identification procedure using the idea that different persons have differing finger-vein patterns. Multimodal biometrics is based on fingerprint and finger vein. Gabor features are extracted from finger vein using Gabor filter with orientation of 0, 15, 45, 60 and 75 degrees. For fingerprint images, energy coefficients are got using wavelet packet tree. Both obtained features are normalized with min max normalization and fused with concatenation. Feature selection is through use of PCA and kernel PCA. Classification is by using RBF Classifier and Euclidean distance. It is suggested that RBF kernel be optimized using BAT algorithm and hybrid BAT with local search.
