Palm Print Recognition Based on PCA and Its Variants

Abstract

In present era, automatic personal recognition is a serious problem that needs to be overcome properly. Palm print recognition is one of the most reliable and successful biometric solutions due to its numerous advantages such as stable line features, low resolution imaging, low cost capturing device, being non-intrusive and user friendly. In this article, performance comparisons of palm print recognition techniques based on subspace approaches (PCA, 2DPCA, 2D²PCA) have been presented. The experimental results are evaluated on three benchmark databases (CASIA, Cropped palm images and IIT Delhi) in terms of recognition rate and computation time.