Research On Optimization Design And Algorithms Of Stack Filters

Signal processing technology was applied widely in many fields, such as country economy, military affairs and national defence, science technology and family life, however, most of signal processing problems appearing from phenomenon of nature and society are nonlinear, and with the rapid improvement of the precision, flexibility and real time requirement for signal processing, linear filtering technology has not been able to meet the demand of information processing perfectly. The theory and technology of nonlinear digital filter, which is the one of based search, have developed step by step since 1970's. Nonlinear digital filters work well in these situations where the linear filters may fail.Nonlinear digital filter is the main tool of nonlinear filtering, which have been widely used in many signal and image processing applications since they can effectively deal with noise-corrupted situation that involve impulsive, speckle, or signal-dependent noise. Stack filters that are a kind of nonlinear digital filters, have received considerable attention during recent years when their theory was presented, its virtues lie in: applying the architecture of threshold decomposition, suitable to parallel processing and VLSI realization; including many kinds of nonlinear filters, being an important tool for nonlinear research.In this paper, based on stack filters' fundamental theory and Boolean function correlative theory, stack filters' statistical characteristic and optimization design are researched. Connection between stack filters and rank order filters is analyzed, based on the Boolean functions, output distribution of stack filters and rank order filters is researched. Furthermore, mathematical optimization models of MAE and MSE error criterion are established, based on which, intelligent optimization algorithm and stack filters design combined to form new design algorithm in order to improve stack filters' filtering capability. Stack filters' optimal estimation algorithms are systematically validated by theory and simulation results.