期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2014
卷号：5
期号：3
页码：3638-3640
出版社：TechScience Publications
摘要：Palmprint recognition algorithms are useful in a wide range of applications like security control, crime investigation, and entrance control in buildings, access control in computer system, access control at automatic teller machines, passport verification, identifying the individuals in a given databases. Personal authentication using palmprint is a promising approach suggested by various researchers. However, most of the techniques suffer from high computational requirements and cost. This paper proposes an approach that makes use PCA (Principal Component Analysis) with reduced dimensionality based feature extraction and the use of Eigen palmprints in the experimentation. The PCA based features significantly minimize the noise, minimizes the memory usage and computational time of authentication. The proposed approach provides better performances in terms of sensitivity, specificity and accuracy
