Adaptive Boosting for Enhanced Vortex Visualization

摘要

In this paper, we demonstrate the use of machine learning techniques to enhance the robustness of vortex visualization algorithms. We combine several local feature detection algorithms, which we term weak classifiers into a robust compound classifier using adaptive boosting or AdaBoost. This compound classifier combines the advantages of each individual local classifier. Our primary application area is vortex detection in fluid dynamics datasets. We demonstrate the efficacy of our approach by applying the compound classifier to a variety of fluid dynamics datasets.