The Benefit Of Using More Than One Elman Neural Network For Off-Line Signature Recognition System
This paper presents a methodology for off-line signature recognition system; this method consists of image preprocessing, features extraction by using Centroid Distance Function, finally build Elman neural network. In general this work displays the compared to the application of Elman neural network in two major cases:
The first case (the traditional way): This is the way of the common methods to train neural networks, and through the construction of neural network and one for all people.
The second case (the proposed method): This method includes several networks by building a neural network for each person (the number of networks is equal to the persons number).
This system has been tested and gives %89.3 recognition rate. In this system we prove that the using of one neural network for each person is better than the using of one neural network for all persons. This signature recognition system is designed using MATLAB.
Keywords: Signature Recognition; Elman Neural Networks; Centroid Distance Function; Biometrics
Download Full-Text
ABOUT THE AUTHORS
Shatha M.
Department of Software Engineering, Mosul University, College of Computer Sciences & Mathematics Mosul, Ninawa +964, Iraq
Manar Al-Abaji
Department of Computer Sciences, Mosul University, College of Education for pure science Mosul, Ninawa +964, Iraq
Maher Hussien
Department of Computer Sciences, College of Al Hadbaa University Mosul, Ninawa +964, Iraq
Shatha M.
Department of Software Engineering, Mosul University, College of Computer Sciences & Mathematics Mosul, Ninawa +964, Iraq
Manar Al-Abaji
Department of Computer Sciences, Mosul University, College of Education for pure science Mosul, Ninawa +964, Iraq
Maher Hussien
Department of Computer Sciences, College of Al Hadbaa University Mosul, Ninawa +964, Iraq