In the last decades more and more all-sky-surveys created an enormous amount of data which is publicly available on the internet. Crowd-sourcing projects like Galaxy-Zoo or Radio-Galaxy-Zoo used encouraged users from all over the world to manually conduct various classification tasks. The combination of the pattern-recognition capabilities of thousands of volunteers enabled scientists to do the data-analysis within acceptable time. For upcoming surveys with billions of sources, however, this approach is not feasible anymore. In this work, we present an unsupervised method that can automatically process large amounts of galaxy data and generates a set of prototypes. This resulting modle can be used to both, visualise the given galaxy as well as to classify new, yet unseen images.
People involved: Kai Polsterer, Kai.Polsterer@h-its.org