Switching-based filter based on Dempster's combination rule for image processing

In this work, a two-pass switching rank-ordered arithmetic mean (TSRAM) filter that preserves image details while effectively suppressing impulse noise is proposed to improve the performance of switching-based median filters. The proposed filter mechanism includes an efficient impulse detector based on the Dempster-Shafer (D-S) evidence theory and a rank-ordered arithmetic mean filter that works by estimating the noise-free ordered mean values excluding the current pixel. A modified Dempster's combination rule is applied to the impulse detector. To improve filtering performance, a simple switching median filter is included to perform second-pass filtering. Experimental results show that the proposed filter outperforms many well-accepted switching-based median filters in terms of both noise suppression and detail preservation, providing excellent robustness at various percentages of impulse noise. (C) 2010 Elsevier Inc. All rights reserved.