This paper explores a new 3D palmprint recognition mehthod. We aim to improve the accuracy and robustness of existing 2D palmprint authentication using 3D palmprint curvature information. First

the curvature is an important characterization of 3D Objects

which can present the shape of local surface has nothing to do with the view point. No matter how the palm rotates or translates

the curvature is stable. So the mean curvature of 3D palmprint is used to depict the surface feature of 3D palmprint. Next

we obtain the surface curvature map as 2D gray images mean curvature image (MCI). Then

using the RLDA method extracts the second feature in order to eliminate the existing problems of traditional LDA—small sample size problem and the problem that optimization criterion function is not directly related to recognition rate. Experiments

show method presented in this paper has a higher accuracy compared with traditional LDA

PCA

ICA and LPP etc.