Locally adaptable binary mathematical morphology using distance transformations

Abstract — We investigate how common binary mathe-matical morphology operators can be adapted so that the size of the structuring element can vary across the image pixels. We show that when the structuring elements are balls of a metric, locally adaptable erosion and dilation can be efficiently implemented as a variant of distance transformation algorithms. Opening and closing are ob-tained by a local threshold of a distance transformation, followed by the adaptable dilation. I