Instructor:	Dr. Ze-Nian Li, TASC-1 8223, Phone: 778-782-3761, li@sfu.ca Office Hours: Tuesdays and Thursdays 2:30-3:20
TA:	Sepideh Sarajian Office Hours: Mondays and Wednesdays 1:00-2:00 (starting Week 2)

Objectives:	This course covers various topics in computer vision with the emphasis on model-based approaches. Main subjects include image processing techniques, Hough transforms, 2-D and 3-D modeling and matching, neural networks for computer vision, and stereo vision. State-of-the-art model-based vision systems will be used as study cases. Students are expected to complete a term project.

Topics:	Low-level Image Processing Hough Transforms 2D and 3D Representations - Modeling Matching Using Invariant Local Features Neural Networks for Computer Vision Stereo Correspondence Algorithms Other Topics

Prerequisites:	MATH 152 and nine credits in CMPT upper division courses, or permission of the instructor.

Grading:	Assignments 20%, Midterm 20%, Term project 25%, Final exam 35%.

Late Penalties:	Assignments are due at the beginning of the specified class time.   For each day late, 10% of the total possible points will be deducted. No work will be accepted after two days late.

Recommended Textbooks:	R. Szeliski, "Computer Vision: Algorithms and Applications", Springer, 2010.   http://szeliski.org/Book/ includes a pre-publication version and many good CV course links. D.A. Forsyth and J. Ponce, "Computer Vision: A Modern Approach", 2nd ed., Prentice Hall, 2012.