سال انتشار: ۱۳۸۴

محل انتشار: هشتمین کنفرانس دانشجویی مهندسی برق

تعداد صفحات: ۶

نویسنده(ها):

Mahyabadi – Islamic Azad University of Kerman
Naderi – Islamic Azad University of Kerman
Kalantari – Islamic Azad University of Kerman
Dashti – Islamic Azad University of Kerman

چکیده:

In this article , we investigate the performance of MLP (Multilayer Perceptron) network acting as a classifier in a signature recognition system. For this purpose, a data of 100 signature image of 10 people (10signatures for each person) is used for training and evaluation. The principal components of images have been used asinputs for the proposed network. The experimental results reveal that the MLP network exhibits appropriate performance with the recognition accuracy of 98.5%.