Neel Joshi
office: 212 Allen Center

Ira Kemelmacher
office: 282 Allen Center

Ian Simon
office: 618 Allen Center






Jiun-Hung Chen

Rahul Garg


Office Hours

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 it's impossible for you to make it to scheduled office hours, you can usually arrange an appointment with the TA or instructor. Just send an email requesting a meeting.


  • Programming experience
  • Vector calculus
  • Linear algebra
  • Matlab (not required as help sessions will be provided)


CSE 455 Course Reader, available at the UW Bookstore in the CSE textbook area. 

Other references

Richard Szeliski's book Computer Vision: Algorithms and Applications. The book draft is currently available online.

R. Hartley, A.Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press, 2000.
Some parts of this book are available online.

R. Hartley, A.Zisserman., Multiple View Geometry - Tutorial. CVPR (1999).

D. A. Forsyth, J. Ponce. Computer Vision a Modern Approach. Prentice Hall, 2003.


  • Email List:  First subscribe the class mailing list (use your email address and the Subscribe button), then use the hypermail archive online.
  • Computer Accounts:  if you don't have a CSE account, click here.
  • Lab (Sieg 327) access: if you are registered for the course but can not have access to the lab, please email cardkey at cs.
  • Forum: You can use CSE 455 Forum to post your questions.
  • Gradebook: You can use CSE 455 Gradebook to check your grades.


  • Programming Projects (70%)
  • Midterm (15%)
  • Final (15%)
  • Late projects will be penalized by 33% for each day it is late, and no extra credit will be awarded.  A project due on Friday at 1:30pm that is turned in by Monday at 1:30pm is one date late, while if it's turned in Monday night or Tuesday morning that will count as two days late (weekends do not count). Everyone gets 1 free late day for the quarter.

Syllabus (tentative)

Image Processing

  • filtering, convolution
  • image pyramids
  • edge detection
  • features
  • hough transform

Image Transformation

  • image warping (parametric transformations, resampling, texture mapping)
  • image compositing (alpha blending, color mosaics)
  • segmentation and matting (snakes, scissors)

Motion Estimation

  • optical flow
  • image alignment
  • image mosaics
  • feature tracking


  • physics of light
  • color
  • reflection
  • shading
  • shape from shading
  • photometric stereo

3D Modeling

  • projective geometry
  • camera modeling
  • single view metrology
  • camera calibration
  • stereo

Object Recognition and Applications

  • eigenfaces
  • applications (graphics, robotics)


Last modified 1/14/2010