A method of impulse noise detection by using Laplacian Gaussian filter adapted with Genetic Algorithm

Abstract EN

In this paper, impulse noise detector found in an image by using Laplacian-Gaussian filter is proposed.

The LG filter used for smoothing the noise in image.

The flat parts of contour, detected by a set of different threshold for noise detected to perform the task of removing impulse noise.

Finally, based on the genetic algorithm, the genetic learning the process adjusts the parameters of image base.

Based on the criteria of Peak Signal to Noise Ratio (PSNR), Mean Square Error (MSE) and Mean Absolute Error (MAE) to achieves a better performance that proposed method performs significantly better than traditional methods.