Computing kernel in spatial filtering domain, using genetic algorithm and discrete wavelet transform

In this paper we propose a new approach based on computing weights of kernel in spatial filtering domain. In order to do this, genetic algorithm is used to find best weights of kernel and also discrete wavelet transform as fitness function in genetic algorithm. Finally, we convolve a noisy image with proposed kernel to enhance quality image. We evaluate the performance of the proposed method using three standard test images and use fitness function value to measure accuracy; the result shows the efficiency of the proposed method