Abstract In this paper generalized weighted order statistic (GWOS) filters are introduced. As a subclassof generalized stack filters, GWOS filters can be implemented using a sorting operation in the realdomain. Based on the relationship between GWOS filters and neural networks, two efficient adaptivealgorithms are derived for finding optimal GWOS filters under the mean absolute error (MAE) and the mean squared error (MSE) criteria. Simulation results in image processing demonstrate that GWOS filters, like generalized stack filters, can suppress both impulsive noise and Gaussian noisemore effectively than standard stack filters.1. Introduction The class of stack filters, which includes all rank order filters, weighted median filters, andweighted order statistic (WOS) filters, is the set of non-linear sliding window filters characterized by two properties: (1) the week superposition property known as threshold decomposition, and (2)the ordering property known as the stacking property. An analytical technique, linear programming