Palmprint recognition using dual-tree complex wavelet transform and compressed sensing

In this paper, based on the dual-tree complex wavelet transform (DT-CWT) and compressed sensing (CS), a novel and high palmprint recognition performance algorithm is proposed. Firstly, DT-CWT, which provide both approximate shift invariance and good directional selectivity, is employed to represent the palmprint image with better preserving the discriminable features with less redundant and computationally efficient. Then the PCA (Principal Component Analysis), based on linearly projecting the image subband coefficients space to a low dimensional feature subspace, is employed to extract the feature of the palmprint images. At last, the robust compressed sensing classification algorithm is used to distinguish the palmprint images from different hands. The experimental results carried on PolyU palmprint database show that the proposed algorithm has better recognition performance than traditional Nearest Neighbor Classification algorithm.