Morphological bilateral filtering and spatially-variant adaptive structuring functions

Abstract : Development of spatially-variant filtering is well established in the theory and practice of Gaussian filtering. The aim of the paper is to study how to generalize these linear approaches in order to introduce adaptive nonlinear filters which asymptotically correspond to spatially-variant morphological dilation and erosion. In particular, starting from the bilateral filtering framework and using the notion counter-harmonic mean, our goal is to propose a new low complexity approach to define spatially-variant bilateral structuring functions. Then, the adaptive structuring elements are obtained by thresholding the bilateral structuring functions. The methodological results of the paper are illustrated with various comparative examples.