An improved feature extraction method of palmprint

摘要

In this paper, an improved feature extraction method of palmprint is proposed. A linear discriminate method of palmprint identification based on two-dimensional Gabor wavelet (2DGLD) which constructs a new linear criterion function. This method can avoid the bleaching process, less between class distance limitations, and reduce the computational complexity. In order to increase palmprint identification accuracy, Gabor wavelets first capture the properties of spatial localization, orientation, spatial frequency and phase relationship. Then 2DPCA is adopted to reduce dimension. Finally, the I2DLDA method is then applied to project palmprints from the high-dimensional palmprint space to a significantly lower-dimensional feature space, in which the palmprints from the different palms can be discriminated much more efficiently.