关键词: 生物识别技术, 手背静脉, 小波分解, 核二维主成分分析, 二维线性判别式分析

Abstract: Dorsal hand vein recognition based on wavelet decomposition and K2DPCA-2DLDA was proposed in this paper, and db4 wavelet was used to decompose the original image. K2DPCA transformation was used for the subimage of low frequency to obtain low dimensional space characteristics. Then, 2DLDA transformation was used to further reduce the dimension for obtaining the final feature expression. Finally, the features were classified according to the nearest neighbor classification rule. The experimental results show that the method can improve the hand dorsal vein recognition rate and reduce the recognition time effectively.

Key words: biometrics, dorsal hand vein, wavelet decomposition, Kernel Two-Dimensional Principal Component Analysis (K2DPCA), Two-Dimensional Linear Discriminant Analysis (2DLDA)