Adaptive Neuro-Fuzzy Inference System Based Impulse Denoising

摘要

Removing impulse noise from images is a critical issue in image processing because it may occur frequently during acquisition or transmission of images. We propose an anfis based impulse denoising algorithm to preserve the intrinsic geometric details of an image. The main target of this project is to restore the features of an image without losing any information from the degraded image. This method is more suitable to preserve the features of an image with scale invariant properties of an image. Here we are performing the training the noisy image with ANFIS and testing the image to retain the features of an original image.