Adaptive Median Filtering with Modified BDND Algorithm for the Removal of High-Density Impulse and Random Noise?

The impact of noise on image will degrade its feature. Suppression or removal of noise in 2D images would be very worth in medical image processing, satellite image processing and various other domains. Switching median filters outperform standard median filters in the removal of impulse noise due to their capability of filtering candidate noisy pixels and leaving other pixels intact. The BDND - boundary discriminative noise detection is a great example in this class of filters. Certain issues in BDND algorithms are evaluated and enhanced by increasing the window size of the filter. In this project, we propose modifications to the filtering step of the BDND algorithm by increasing the window size one step higher to existing size to address those problems. The evaluation shows that the proposed modifications produce sharper image than the image produced by using BDND algorithm. The noise elimination with around 70% of noise has been proposed and implemented using MATLAB 7.12 using image processing tool box.