CAVIAR-Based Vortex Core Region Detection

This paper presents a novel algorithm to enhance the robustness of vortex core detection that automatically learns to build a strong compound classifier based on a locally weighted combination of weak detectors and the training samples. We use semi-supervised learning with domain expert input to develop strategies for guiding the selective refinement process. This compound detector combines the advantages of each individual local detector. Our main application area is vortex detection in turbulent flows. We demonstrate the efficacy of our approach by applying the compound detector to a variety of fluid data examples.