Detection and removal of impulse noise by a neural network guided adaptive median filter

We introduce a novel adaptive median filter for the removal of impulse noise in images. Using pixel classification by a self-organising neural network to detect the positions of the noisy pixels, we are able to effectively eliminate the impulses while retaining image integrity. Detailed statistical analysis and comparison of the proposed method with traditional median filters are provided. A visual example is given to demonstrate the performance of the proposed filter