期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2015
卷号：6
期号：4
页码：3280-3284
出版社：TechScience Publications
摘要：Finger vein detection is a physiological characteristics-based biometric technique, and it uses vein patterns of human finger to perform identity authentication. Even in the case of identical twins the finger-vein patterns are believed to be quite unique [1]. Moreover finger vein has many more advantages as compare to other biometric system as result its application area becoming wider day by day. In this paper, following techniques are analyzed i.e., Repeated Line Tracking, Gabor Filter and Multilinear discriminant analysis (MDA). Both Repeated Line Tracking, Gabor Filter are efficient method for feature extraction but, combination of these two techniques with MDA Classifier increases the performance and average accuracy as compare to existing systems. In proposed work some important parameters like Peak Signal to Noise Ratio (PSNR),MSE,Genuine Acceptance Rate (GAR) and False Acceptance Rate (FAR) are calculated for Performance evaluation. When tested on a finger vein images database this system provides more accurate results and it is less time consuming as compared with existing.
