سال انتشار: ۱۳۷۹

محل انتشار: اولین کنفرانس ماشین بینایی و پردازش تصویر

تعداد صفحات: ۷

نویسنده(ها):

javad haddadnia – dept.of electrical engineering amirkabir university
karim faez –

چکیده:

one of the important key requirements in face recognition technology is feature extraction method in this paper a neural network based face recognition system is presented the system consists of two main procedures. The first one is face localization based on multiresolution template matching MTM and the second one is face features extraction using statistical feature such as pseudo zernike moments PZM simulation results indicate that for accurate face feature extraction face localization is very important process then we also propose a method for face localization using multiresolution template matching technique.