| Hi-index | 35.68 |
A class of nonlinear moving window filters is investigated for restoration and detection of signals embedded in additive white Gaussian and non-Gaussian noise. The filters of this class, called combination filters (C-filters), use both rank-order and temporal-order information from the input observation sequence within finite processing windows to produce the outputs. A C-filter combines the characteristics of linear FIR (finite impulse response) filters and nonlinear filters of the order statistics type. The output of a C-filter in each processing window is defined to be the rank-order-dependent weighting of temporal-order data. Both analytical and training procedures for designing the C-filters are considered. To get further improvement in overall performance, the authors extend the concept of C-filters and introduce a class of generalized C-filters (GC filters) which are shown to have desirable properties. Performance characteristics of C- and GC filters in signal restoration are considered through computer simulation