Palmprint recognition using Gabor feature-based two-directional two-dimensional linear discriminant analysis

In this paper, we propose a novel palmprint recognition approach using Gabor feature-based two-directional two-dimensional linear discriminant analysis (GB(2D)2LDA). Three main steps are involved in the proposed GB(2D)2LDA: (i) Gabor features of different scales and orientations are extracted by the convolution of Gabor filter banks and original gray palmprint images; (ii) (2D)2LDA is used for dimensionality reduction of Gabor feature space; (iii) Euclidean distance and the nearest neighbor classifier are finally used for classification. The method is not only robust to illumination and rotation, but also efficient in feature matching. Simulation results on PolyU Palmprint Database show that the effectiveness of our proposed GB(2D)2LDA in both accuracy and speed.