Computer Vision

Faculteit Science and Engineering
Jaar 2021/22
Vakcode WMCS015-05
Vaknaam Computer Vision
Niveau(s) master
Voertaal Engels
Periode semester II a
ECTS 5
Rooster rooster.rug.nl

Uitgebreide vaknaam Computer Vision
Leerdoelen Presentation of the basic principles of computer vision, in particular multiscale analysis, deformable models, ‘shape from X’ and video analysis, building on the knowledge acquired in Image Processing. Promote understanding of the theoretical (mathematical) backgrounds in modelling higher order vision processes.
Omschrijving This course develops the theoretical basis as well as practical algorithms for automatically extracting useful information about the world by carrying out computations on images or image sequences. First, a number of basic image processing concepts are briefly reviewed, such as digitization, preprocessing, image restoration and segmentation. Standard linear image processing algorithms are discussed as well as some concepts and algorithms from nonlinear morphological image processing. Also, some recent results on multiscale image analysis are presented. Then we move to higher level operations, such as object recognition, pattern recognition and three-dimensional scene analysis. Making inferences of a 3D world from 2D pictures requires the analysis of projection methods, geometric transformations and illumination models. We study the shape recovery problem, that is, the question of how object properties such as shape can be reconstructed from features which can be measured in images. As an illustration of the theory we discuss shape from texture, shape from shading, shape from stereo and shape from motion. Practical Information: Lab assignments using an image processing package. As an alternative to the regular practicals, students can elect to do a short research project.
Uren per week
Onderwijsvorm Hoorcollege (LC), Practisch werk (PRC), Werkcollege (T)
Toetsvorm Opdracht (AST), Practisch werk (PR), Schriftelijk tentamen (WE)
(G1=average grade for practicals, G2=grade for written exam,final grade (G1+2*G2)/3 if both Gi>=5, else min((G1+2*G2)/3,5).)
Vaksoort master
Coördinator Dr. M.H.F. Wilkinson
Docent(en) Dr. M.H.F. Wilkinson
Verplichte literatuur
Titel Auteur ISBN Prijs
Computer Vision (Springer Verlag, 2011) ISBN E-book 9781848829350
R. Szeliski Paper 9781848829343
Syllabus Lab Sessions Computer Vision
Entreevoorwaarden Recommended prior knowledge: Image Processing and/or Signals and Systems
Opmerkingen This course has limited enrollment:
- CS students can always enter the course, regardless of whether the course is mandatory for them or not.
- The number of enrolments for other non-CS students is limited. These students need to meet the course prerequisite requirements as mentioned on Ocasys. Priority is given to students for which the course is an official elective (see list below).
- An exception can be made for exchange students, if they have a CS background: please contact the FSE International Office. See here for more info about the enrollment procedure.
Opgenomen in
Opleiding Jaar Periode Type
MSc Artificial Intelligence  (C - Elective Course Units) - semester II a keuze
MSc Computing Science: Intelligent Systems and Visual Computing  (Compulsory course units) 1 semester II a verplicht
MSc Computing Science: Science Business and Policy  (Elective course units) 1 semester II a keuze
MSc Courses for Exchange Students: AI - Computing Science - Mathematics - semester II a