Research of Finger Vein Recognition Based on Fusion of Wavelet Moment and Horizontal and Vertical 2DPCA
Fengxu Guan, Kejun Wang, Hongwei Mo, Hui Ma, Jingyu Liu · 2009
Based on the characteristics of wavelet transform (WT), wavelet moment (WM), horizontal and vertical two-dimensional principal component analysis ((2D)2PCA), a new method of finger vein recognition is proposed. Firstly, the original images are decomposed into high-frequency and low-frequency components through WT, and the wavelet moment is extracted. Secondly the image feature matrix of low-frequency components after WT is extracted by (2D)2PCA. Finally, the match scores of the WM and the feature matrixes of the test samples and training samples are judged by the nearest neighbor rule. And finger vein recognition is finished by match scores of weighted the WM and the feature matrixes. The experiment results show that the method of WM and WT-(2D)2PCA has high recognition rate and robustness, and compensate the disadvantage of the low recognition rate through single feature recognition. The recognition rate of the proposed method is higher than those of 2DPCA, (2D)2PCA, WT-(2D)2PCA respectively.