Deportation of constant amplitude impulsive outlier (CAIO) through novel repetitive new switching-based median filtering approach

Abstract

This research paper nominates a novel repetitive new switching-based median filtering approach (R-NSBMF) for outlier deportation on computer numerical pictures that are surpassingly subverted by constant amplitude impulsive outlier (CAIO) or Salt & Pepper noise. This approach reestablishes the outlier numerical pictorial feature (which has the minimum amplitude or the maximum amplitude) by the median filter of the finite impulse response (FIR) linear predictor of all the non-outlier numerical pictorial feature in the calculating numerical pictorial division under the repetitive groundwork. The proposed R-NSBMF approach is investigated on numerous computer numerical pictures (Girl, Lena, Pepper and F16) on spacious outlier percentage and the proposed R-NSBMF approach exposes admirable outlier-deportation numerical pictures than the mean filter (mf), standard median filter (SMF), adaptive median filter (AMF), weight median filter (WMF) and original NSBMF and it professes admirable peak signal-to-noise ratio (PSNR) and pictorial quality.