Abstract. We introduce a noise-tolerant segmentation algorithm efficient on 3D multiscale granular materials. The approach uses a graphbased version of the stochastic watershed and relies on the morphological granulometry of the image to achieve a content-driven unsupervised segmentation. We present results on both a virtual material and a real X-ray microtomographic image of solid propellant.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.