SM/0169 - COMPUTER VISION
Academic Year 2022/2023
Free text for the University
GIOVANNI PUGLISI (Tit.)
- Teaching style
- Lingua Insegnamento
|[60/73] INFORMATICS||[73/00 - Ord. 2017] PERCORSO COMUNE||6||48|
Knowledge and understanding: The course focuses on methods for acquiring, processing, analyzing, and understanding images.
Ability to apply knowledge and understanding: the student will be able to implement specific modules of a computer vision system. To this end during the course will be used several computer vision libraries.
Making judgements: Through concrete examples and case studies, the student will be able to select independently the algorithms to be used for a specific computer vision problem and make the tuning of the involved parameters.
Communication skills: the student will acquire technical communication skills related to computer vision field.
Ability to learn independently: starting from the basic concepts provided in the course, the student will be able to learn advanced computer vision techniques.
Linear algebra, basic calculus, basic probability.
Programming skills (Matlab)
Image Formation and Camera Calibration
Edge Detection, Lines, Hough transform
Interest Point Detection
Scale Invariant Feature Transform (SIFT)
Bag of Visual Words
Local Binary Pattern (LBP)
Deep Learning for Computer Vision
Frontal lectures and exercises
Verification of learning
The final grade is computed as weighted average of:
-oral exam related to the methods for acquiring, processing, analyzing, and understanding images (2/3);
-implementation of a computer vision algorithm (1/3).
E. Trucco, A. Verri, “Introductory Techniques for 3-D Computer Vision”, Prentice Hall, 1998;
Richard Szeliski, "Computer Vision: Algorithms and Application", Springer 2010
Ian Goodfellow, Yoshua Bengio, Aaron Courville, "Deep Learning", MIT Press, 2016.
Richard Hartley, Andrew Zisserman, "Multiple View Geometry in Computer Vision 2nd Edition", Cambridge University Press, 2004.
Auxiliary learning material: lecture slides.