Topographie metrics for image segmentation

Abstract

Algorithms designed for machine vision applications such as medical imaging, surveillance, etc., very often require some kind of comparison between images. While the brain can compare complex objects with ease, the same is usually a very difficult task for algorithm designers. Comparison between objects requires a proper definition of a metric that determines the similarity of the objects. This paper briefly investigates the problems about commonly used metrics (Hamming, Hsausdorff), and shows another method: the nonlinear wave metric, describing its advantages, and its application in practice.