Abstract:
Markov Random Fields (MRFs) are widely used for modelling image analysis problems, such as segmentation, denoising, and motion estimation. In this presentation, I will provide a brief overview of different applications of MRFs and some of the commonly used energy models and optimization methods. In particular, recent advances in higher-order MRF optimization seem a promising direction for modelling more complex and sophisticated energies. However, computational performance could be a limiting factor when scaling those models to large image databases. A potential solution could be to employ efficient discrete-continuous optimization methods.
Bio:
Ben Glocker is a Lecturer in Medical Image Computing at the Department of Computing, Imperial College London. Before joining Imperial in October 2013, he has been working as a post-doctoral researcher in the Machine Learning & Perception Group at Microsoft Research Cambridge. He has been appointed as Researcher Fellow of Darwin College, University of Cambridge, from 2010-2012. Ben received his doctoral degree from the Technical University of Munich, in 2011. Ben is a member of the Biomedical Image Analysis group. His research focus is on advanced methods and tools for biomedical image computing and computer vision. In particular, he is interested in semantic understanding and automatic analysis of images using machine learning techniques.