An efficient multispectral palmprint identification system using radial basis function

Several studies for palmprint-based personal identification have focused on improving the performance of palmprint images captured under visible light. However, during the past few years, some researchers have considered multispectral images to improve the effect of these systems. Compared with color images, multispectral images provide additional information due to its variety of spectral bands. In this paper, we propose an efficient online personal identification system based on MultiSpectral Palmprint (MSP) using the Radial Basis Function (RBF) and two-dimensional Block based Discrete Cosine Transform (2D-BDCT). In this study, a segmented MSP is firstly divided into non-overlapping and equal-sized blocks, and then, applies the 2D-BDCT over each block. By using zigzag scan order (starting at the top-left) each transform block is reordered to produce the feature vector. Subsequently, RBF method is used for modeling and so for classifying the feature vectors. The proposed method is validated for their efficacy on the available PolyU MSP Database of 300 users. Our experimental results show the effectiveness and reliability of the proposed approach, which brings both high identification and accuracy rate.