Impulse noise detection and removal by modified boundary discriminative noise detection technique

摘要

An efficient technique is implemented which is a nonlinear decision based filter used to remove salt and pepper impulse noise. This type of filter is a two stage filter that uses a well built impulse noise detection method, called the Modified Boundary Discriminative Noise Detection (MBDND) [1] which decides whether the current pixel is corrupted with impulse noise or not. Then apply Euclidean distance algorithm [2] to restore the corrupted pixels in second stage. From experimental results, it demonstrate that this filter performs significantly better than many existing, well accepted median and decision based filters for gray scale images which are corrupted up to 70% of Salt and Pepper noise.