Weighted FMH filters

Abstract

In this paper, we introduce new weighted FIR median hybrid (FMH) filters consisting of combinations of averaging and ramp predicting FIR substructures, the input signal and the weighted median operation. We analyze two weighted FMH filter structures in detail. Due to the selection of subfilters the center weighted FMH (CWFMH) filter structure has low-pass characteristics and it preserves sinusoidal signals. It is shown that sinusoidal signals are root signals of the filter. An upper frequency bound for the preservation of sinusoids is derived. The subfilter weighted FMH (SWFMH) filter has the property of preserving edges while filtering high-frequency stationary signals. The characteristics of both filters are analyzed for sinusoidal and pulse shaped input signals. An efficient implementation structure for the weighted FMH filters with complexity independent of the filter length is shown. As examples, removal of artifacts and noise from the electroencephalogram (EEG) and electrooculogram (EOG) signals, respectively, is studied.