Image Analysis and Learning

Lab members


We develop machine learning methods to solve difficult computer vision problems mainly from the Life Sciences. Our ambition is to make the machine learning process as robust and user-friendly as possible: we hence develop algorithms for active and weakly supervised learning that can benefit from small or only partially annotated training sets.

Our primary applications are segmentation (decomposing an image into its constituent parts) and tracking. We also seek to make machine learning algorithms available to practitioners in the guise of the ilastik program.

We enjoy and cultivate close collaboration with our experimental partners from biology and engineering and are grateful for the constant flow of challenging problems they provide. A long-standing partner of our lab is the Robert Bosch company that has implemented some of our algorithms to run in a production environment, 24/7 and all year round.


  • 17.10.2016: Winning the CREMI segmentation challenge. Constantin Pape, Nasim Rahaman, Thorsten Beier and Anna Kreshuk were key to this success.
  • 28.01.2016: We are now on top of the Connectomics Challenge Leaderboards both for the ISBI 2012 and the SNEMI 3D challenges. Congratulations to the whole team, and Constantin Pape in particular!
  • Anna Kreshuk will advise her first own PhD students thanks to funding she won from the Baden-Wurttemberg "Elite PostDoc program". Congratulations!
  • Jens Kleesiek, Gregor Urban and others win the 1st and 3rd prize at the MICCAI BraTS (Brain Tumor Segmentation) Challenge.
  • Two orals at CVPR 2014
  • Alumnus Bjoern Menze now Assistant Professor at TU München
  • Papers at NIPS, CVPR (x3), ICML, ECCV (x3), UAI, ICPR
  • Xinghua Lou and Luca Fiaschi have won the best paper award at the MICCAI-Workshop on Machine Learning in Medical Imaging. Congratulations!