Special Topics in Computer Science:
Random Fields and Active Contours in Image Segmentation
There are two main approaches to image segmentation: Contour-based methods aim at
detecting the boundary between regions, while region-based methods try to identify
the regions directly. In this course we will address modern techniques of both approaches.
Dr. Zoltan Kato
Part I: Variational methods
Part II: Markov Random Fields
Students will have to do a project and send it to the lecturer. The marks for this course will be based on the project.
Some brief lecture notes are available for part I:
For part II the following PhD thesis covers most of the material presented: