سال انتشار: ۱۳۹۰

محل انتشار: سومین کنفرانس مهندسی برق و الکترونیک ایران

تعداد صفحات: ۴

نویسنده(ها):

H Moslemi – Engineering Dept,Tarbiat Moallem University of Sabzevar
A Khakzadian –
J Haddadnia –

چکیده:

In this paper a new method is presented to reduce the noise of images using Fourier transform. This method is based on fast Fourier transform (FFT) operation. The quality of our methods is better than other methods in noise reduction. Here we do not apply statistical methods which are time consuming and instead we use membership degrees in each part of the image to normalize and separate the main part of the image from noise. The magnitude of membership degrees in different parts of the image are determined using proper Gaussian function P0 (cut-off frequency) and different variances for them are calculated. Then the image is convoluted using a proper filter to reduce the noise of image. Different parts of mask are determined for calculating the membership degrees.