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%.