Instructor:  Steve Seitz
office:  592 Allen Center
(206) 616-9431
Office Hours:  Thursdays 11-12

TA:  Jiun-Hung Chen

Office Hours:  Wednesday 4-5pm at CSE216

The goal of computer vision is to compute properties of the three-dimensional world from digital images.  Problems in this field include identifying the 3D shape of an environment, determining how things are moving, and recognizing familiar people and objects, all through analysis of images and video.  This course provides an introduction to computer vision, including such topics as feature detection, image segmentation, motion estimation, image mosaics, 3D shape reconstruction, and object recognition.

Notes about office hours:  If you can't make scheduled office hours, you can always arrange an appointment with the professors or TA. Just send an email requesting a meeting.


  • Data structures
  • A good working knowledge of C and C++ programming
  • Linear algebra
  • Vector calculus
  • No prior knowledge of vision is assumed.


Required:  Richard Szeliski, Computer Vision: Algorithms and Applications (please check Web site weekly for updated drafts)
Optional:  Forsyth & Ponce, Computer Vision:  A Modern Approach, Pearson, 2002, ISBN 0130851981

We may also use readings from a few textbooks.


  • Email List:  First get a password reminder (use the Edit Options button at the very bottom of the page), then use the hypermail archive online.
  • Computer Accounts:  if you don't have a CSE account and want one for this class, click here
  • Lab:  if you need computer access, we can arrange cardkey access to the Instructional Graphics Lab in Sieg 327.  If this is the case, email us asap.


  • The grade is based on four programming projects

Last modified 04/01/2009