سال انتشار: ۱۳۷۹

محل انتشار: اولین کنفرانس ماشین بینایی و پردازش تصویر

تعداد صفحات: ۶

نویسنده(ها):

mahmood fathy – associate professor dept narmak.tehran
k bararsani – computer eng . Dep iran university and tech

چکیده:

in this paper we present a new algorithm for vector quantization the algorithm is based on neural networks . Performance of this algorithm and other conventional neural network based algorithm for vector quantization are compared the proposed method has better performance in codebooks with compressin above 0.5bpp.