Characterization and Statistics of Distance-Based Elementary Morphological Operators

Abstract

Mathematical morphology (MM) is a powerful theory widely used for image processing and analysis. Distance-based morphological operators are parametrized by a reference value so that a dilation enlarges regions of an image similar to the reference while an erosion shrinks them. In this paper, we first characterize distance-based erosions, dilations, and gradients as a function of the reference. Then, assuming the reference is a sample from a random variable, we use a descriptive statistic to obtain relevant information on a certain distance-based morphological operator. We validate our approach by presenting a successful application of some statistics of distance-based morphological operators for edge detection in color images.