Chinese signature verification with moment invariants

Zernike moment invariants have been widely used in pattern recognition and image processing. In this paper, Chinese signature verification using normalized Zernike moment invariants (NZMI) is proposed. Different orders of moment invariants are studied. Simulation results show that the proposed approach for signature verification is rotation-invariant and scale-invariant, and the preliminary results we got are very promising. Furthermore experiments using projection are also carried out. The results are compared with those of NZMI.