Lecture: Probabilistic Shape Modelling
|Time and Location||Tue 14:15 - 16:00; Seminarraum 00.003, Spiegelgasse 1|
|Exercises||Tue 16:15 - 18:00; Seminarraum 05.001, Spiegelgasse 5|
|Prerequisites||Open to Master and PhD students with basic knowledge in probability theory and statistics, linear algebra as well as programming experience in a modern programming language (e.g. Java or C++)|
|Objectives||At the end of the course the students should
- understand the mathematical concept of a Gaussian process and how it can be used for shape modelling
- know the basic concepts behind the open source software scalismo
- be able to apply the mathematical concepts and the scalismo software in order to solve simple image segmentation problems.
|Contents||Statistical shape models are one of the most important technologies in computer vision and medical image analysis. With this technology, the computer learns the characteristic shape variations of an object or organ. The model resulting from this analysis may then be used in implant design, image analysis, surgery planning and many other fields.
In this course, you will get insights from mathematics, statistics and machine learning, in order to address practical problems, as well as a theoretical and practical introduction to the open source software Scalismo. This software is used today for the automatic detection of organs in medical images or the design of medical implants. You will come to a point where you can use your acquired skills and knowledge for real-world professional applications or academic research.
|Literature||Links to related literature will be given as part of the online course.|
Please note: The final grade will be computed based on the result of a practical project and an oral exam.
Oral exam: 12/13 June 2017, 9 am - 4 pm, Spiegelgasse 1, room 00.003.
|Modules||Wahlbereich Master Informatik: Empfehlungen (Master Informatik 10)
Modul Praxis aktueller Informatikmethoden (MSF - Informatik (Studienbeginn vor 01.08.2016))
Modul Applications of Distributed Systems (Master Computer Science 16)
Modul Methods of Machine Intelligence (Master Computer Science 16)
Modul Concepts of Machine Intelligence (MSF - Computer Science)
|Registration||Services (Requires login)|
- Week 1: General information (classroom teaching)
- Week 2 - 8: Statistical Shape Modelling
(online course on FutureLearn )
- Week 9 - 14: Model fitting and advanced topics in Modelling (classroom teaching)
Week 1: General Information ( slides)
Week 2: Project information / Scala Crashcourse ( slides)
Week 9: Analysis by synthesis ( slides)
Bayesian fitting ( slides)
Week 10: Registration ( slides)
Week 11: Probabilistic fitting ( slides)
Week 12: Computer graphics basics ( slides)
Week 13: 2D Face image analysis ( slides)