Persistent homology and the GrabCut algorithm

  • Wann:
  • Wo: SR 2.07

Zieliński will present his current research on persistent homology and the GrabCut algorithm (used separately and in combination). First, he will talk about using persistent homology for depth image segmentation, a research line conducted together with Matthias Zeppelzauer from the St. Pölten University of Applied Sciences in the course of the 3D Pitoti Project. Next he will explain how persistent homology can be used in the GrabCut algorithm and what the benefits of such combination are.

The last topic of his talk will be about the shape prior segmentation of multiple objects with Graph Cuts. This algorithm published by Vu and Manjunath requires a large number of processing parameters which he is trying to determine automatically in his work. At the end of the presentation, he will present work in the area of biomedical image analysis that he currently performs in cooperation with atherosclerosis scientists.

Bartosz Zieliński received the master degree in computer science from the Jagiellonian University (Poland) in 2007. He received Ph.D. in 2012 in computer science from the Institute of Fundamental Technological Research, Polish Academy of Sciences. He works at the Computer Science and Computer Mathematics Institute of the Jagiellonian University. His scientific interests are medical image analysis, computer vision and machine learning.

Jetzt teilen: