A method based on wavelet transform and discrete K-L transform for color image filtering

A new method of removing random noises in color images is described in this paper. It is based on wavelet transform combines with discrete K-L transform. The basic principle of the new method is that a color image is transformed from the RGB color space into a new space (JKL space) by discrete K-L transform in which the three components J, K and L are irrelevant; Then the color image is filtered in JKL space by wavelet transform; Finally, the color image after filtering is transformed into RGB space to display. Based on this method, the removing random noise from color image is simulated by Matlab. The experiment results show that the new method is better than the traditional transform method and can improve the effect of disposal.