Probabilistic Morphable Models are a fully probabilistic approach to model-based image analysis, based on:
This course teaches the theoretical basis of shape modelling and model fitting and provides an introduction on how to use the software framework Scalismo. The participants have the chance to apply the learned concepts and methods in a guided real-world project from the area of computer vision or medical image analysis.
The course consists of two parts: An open online course and a summer school.
In the online course, participants learn the basic theory of shape modelling and are given a practical introduction to Scalismo. Participants of this course, who submit a solution to the course project, are invited to attend the summer school.
The summer school will focus on model-based image analysis. In theory lectures, participants will learn more about model-fitting and registration, with particular emphasis on probabilistic model-fitting using Markov Chain Monte Carlo methods. An important part of the summer-school is a project. Depending on their preference and background, the course participants can choose to work on a real-world problem from the field of medical image analysis or face image analysis.
The intended audience for the course is beginning graduate students and researchers in computer vision and medical image analysis, who plan to apply statistical shape models as part of their work.
Prerequisite is good knowledge of basic probability theory and statistics as well as linear algebra. Participants should have basic programming skills in at least one programming language (ideally Java, C++ or Python).
Classes will take place at the Department of Mathematics and Computer Science of the University of Basel.
Basel is the third largest town in Switzerland. It can be reached by plane, by either flying directly to Basel Airport or to Zurich Airport (1-hour train ride to Basel).
The summer school is free of charge, but all participants need to organize their stay (travel, accommodation, food) by themselves.
Our main recommendation is the Apaliving Basel Budget Hotel. The price per night for a single room is approximately Fr. 90.--. In the same neighborhood, you can also find the following slightly cheaper options:
|Mon 2/26||Sun 3/4||Basic concepts of shape modelling and the scalismo software.|
|Mon 3/5||Sun 3/11||Building shape models: fundamental concepts in theory and practice.|
|Mon 3/12||Sun 3/18||Probabilistic aspects of shape models.|
|Mon 3/19||Sun 3/25||Modelling with Gaussian Processes|
|Mon 3/26||Sun 4/1||Reconstructing missing parts|
|Mon 4/2||Sun 4/8||Fitting models to data|
|Mon 4/9||Sun 4/16||Model-based image analysis|
|Mon 4/16||Sun 4/25||Course Project|
|Mon 6/25||Morning||Theory: The Analysis by Synthesis framework. (slides)|
|Theory: Non-rigid registration (slides)|
|Exercise: Non-rigid registration|
|Mon 6/25||Afternoon||Plenum: Spotlight presentations by the participants|
|Setting up the IDE and the course projects.|
|Tue 6/26||Morning||Theory: Bayesian Inference and probabilistic model fitting (part 1) (slides)||Exercise: Markov Chain Monte Carlo in Scalismo|
|Tue 6/26||Afternoon||Project: Working on the course project|
|Wed 6/27||Morning||Theory: Analysis of 2D face images using MCMC (slides)|
|Wed 6/27||Afternoon||Project: Working on the course project|
|Thu 6/28||Morning||Theory: Face image analysis - loocking back (slides)|
|Theory: Understanding the Metropolis-Hastings Algorithm (slides)|
|Thu 6/28||Afternoon||Project: Working on the course project|
|Fri 6/29||Morning||Theory: Advanced Topics in Gaussian processes and model-based image analysis (slides)|
|Scala - essential concepts (slides)|
|Fri 6/29||Afternoon||Social Event|
To register for the summer school, fill in the registration form below. Deadline for the registration is April, 30. 2018. Notification of acceptance will be given beginning of May.
Please note: A prerequisite for acceptance is the submission of the course project, which is part of the online course . Please submit your solution via email no later than April, 30. 2018.
For additional questions please send us an email to the address given below.