GIACOMO BORACCHI - TEACHING
 

Computer Vision and Pattern Recognition  
Spring 2020, Master in Artificial Intelligence, USI Lugano, Switzerland.

Mission and Goals:
The purpose of the course is to introduce basic problems in image processing, computer vision, and patter recognition, and to provide the students with an understanding of fundamental principles underlying the most important solutions. Topics include: image formation (from both a photometric and geometric perspective), low-level imaging methods (filtering and edge detection), image restoration and inverse problems (in particular denoising), single and multi-view geometry for 3D reconstruction, feature extraction for object recognition, 3D surfaces and their registration. Lectures are accompanied by various examples of applications where these methods apply, and hands-on programming exercise to solve real-world problems. Prerequisites are linear algebra, basic probability and statistics.
More information on the Course webpage

Course Materials:

Course Introduction  slides;

Geometric Image Formation and Camera Calibration  slides;

Single View Geometry  slides;

Multi View Geometry  slides;

Photometric Image Formation  slides;

Linear Filters  slides;

Nonlinear Filters  slides;

Edge and Line Detection  slides;

Corners and Image Features  slides;

Feature Matching, Template Detection and Robust Fit  slides;

Deep Learning for Visual Recognition  slides;

Image Restoration  slides;