703104 PS Introduction to Computer Vision
winter semester 2018/2019 | Last update: 26.09.2018 | Place course on memo list703104
PS Introduction to Computer Vision
PS 1
2
weekly
annually
English
Computer Vision is a very broad field and as old as Computer Science itself. Why vision? Many of the most successful life forms have evolved incorporating visual information as one of the main sources of knowledge extraction to interact with the environment. In humans more than half of neurons in the brain dedicated to the senses are involved in analyzing information that comes through the eyes.
Many computer systems consider visual information as their input, needing to analyze and extract knowledge from static images or a succession of them. Iris and fingerprint recognition for identity, automatic camera surveillance, face and object recognition, motion tracking, robotics and humanoids, or developing devices for the visually impaired are some of the applications of Computer Vision.
In this course we study all the areas that comprise Computer Vision and look deeper into some of the most relevant and successful methods that have been presented until the present time.
Image formation, iimage features, object recognition, stereopsis, motion, structure from motion, biological inspiration/plausibility.
Continuous assessment (based on regular written and/or oral contribution by participants).
Assignments, approximately 3 or 4 along the course. Two to three weeks are given to complete each one of them.
Computer Vision: A modern approach. David Forsyth and Jean Ponce. Prentice Hall, 2003. ISBN: 0-13-085198-1 Computer Vision: Algorithms and applications. Richard Szeliski. Springer, 2010. ISBN: 978-1-84882-934-3 Computer Vision. Linda Shapiro and George Stockman. Prentice Hall, 2001. ISBN:0-13-030796-3
see dates
- Faculty of Mathematics, Computer Science and Physics