Title :
Chinese signature verification with moment invariants
Author :
Lin, Hai ; Li, Hai-Zhou
Author_Institution :
Dept. of Electr. Eng., South China Univ. of Technol., Guangzhou, China
Abstract :
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
Keywords :
handwriting recognition; Chinese signature verification; NZMI; image processing; normalized Zernike moment invariants; pattern recognition; rotation-invariant approach; scale-invariant approach; Data mining; Euclidean distance; Feature extraction; Forgery; Handwriting recognition; Image processing; Libraries; Pattern recognition; Shape; Skeleton;
Conference_Titel :
Systems, Man, and Cybernetics, 1996., IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-3280-6
DOI :
10.1109/ICSMC.1996.561436
