Title: An efficient offline signature identification method based on Fourier Descriptor and chain codes

Authors: Ismail A. Ismail, Mohammed A. Ramadan, Talaat S. El-Danaf, Ahmed H. Samak

Addresses: College of Computers and informatics, Misr International University, 32511, Egypt. ' Faculty of Science, Department of Mathematics, Menofia University, 32511, Egypt. ' Faculty of Science, Department of Mathematics, Menofia University, 32511, Egypt. ' Faculty of Science, Department of Mathematics, Menofia University, 32511, Egypt

Abstract: This paper proposes a novel offline signature identification method based on Fourier Descriptor (FD) and Chain Codes features. Signature identification was classified into two different problems: recognition and verification. In recognition process, we used Principle Component Analysis. In verification process, we designed a multilayer feed forward artificial neural network. The main steps of constructing a signature identification system are discussed and experiments on real data sets show that the average error rate can reach 3.8%.

Keywords: offline signature recognition; Fourier descriptor; principle component analysis; PCA; personal verification; chain codes; artificial neural networks; ANNs.

DOI: 10.1504/IJBET.2011.038469

International Journal of Biomedical Engineering and Technology, 2011 Vol.5 No.1, pp.1 - 10

Published online: 21 Jan 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article