Stasticial Methods and Learning in Computer Vision
SS 2011, TU München
Location: 02.09.023
Time and Date: every Thursday, 3.15 pm
Lecturer: Dr. Claudia Nieuwenhuis
Start: 5th of May
Statistics is the foundation of many powerful tools in computer vision. This lecture will cover a number of widely used and important techniques for the analysis of images. We will discuss a selected number of approaches concerning their mathematical theory and implementation details. Topics will cover
- necessary basics in measure theory and statistics, e.g. measures, distributions, densities, conditional distributions, marginal distributions, cumulative distribution functions, statistical tests, p-values
- density estimation (parametric and non-parametric) and sampling methods such as Parzen density estimation, mixture of Gaussians, EM-algorithm, particle filtering, e.g. with application to image segmentation and tracking
- subspace methods such as principal component analysis, idependent component analysis, linear discriminant analysis, e.g. with application to face recognition
- learning and classification approaches such as Support Vector Machines, Neural Networks, Graphical Models and Dictionary Learning
The lectures will be held in English.
Exercises:
Location: 02.09.023
Time and Date: every other Tuesday, 2.15 pm
Organization: Eno Töppe
Start: 17th of May