Detail Preserving Fast Median Based Filter

Abstract

In this paper, a new nonlinear median based filtering technique is introduced for the enhancement of grey scale images that are highly contaminated by impulse noise. The proposed Detail Preserving Fast Median Filtering (DPFMF) technique is more effective in eliminating fixed value impulse noise and preserving the image details. The filter replaces a corrupted pixel by the median value of the fast median filter or by the value computed based on a unique criterion applied to the processed neighboring pixel values. The uncorrupted pixels are left undisturbed. Simulation studies show that the proposed filter can eliminate impulse noise of densities up to 80% while preserving the edges and fine details satisfactorily. The performance is evaluated by applying the proposed filter on various grey scale images and the superior results obtained in terms of subjective and objective evaluation are presented.

Index Terms—Impulse Noise, Fast Median Filtering, Nonlinear Filter, Order Statistics Filter, Detail preservation, Image Enhancement