CSC 420, Fall 2011
Introduction to Image Understanding

General Information

Instructor Prof. Allan Jepson.
Email jepson at cs dot toronto dot edu
Office Hour Fri. Noon-1pm, D.L. Pratt 283D, or by appointment.
Lectures FALL 2011 Times: Tues @ 3pm, Fri @ 11am (Note different times on Tues. and Friday),
Room: Lash Miller, 80 St. George St., Room 123
Starts: Tues. Sept. 13.
Tutorials FALL 2009 Time: Thurs @ 3pm,
Room: Lash Miller, Room 123.
Start: Thurs. Sept. 15.
Course Information Sheet Handout
Course Bulletin Board
Email-Newsgroup Policy There may be no response from 24 hours before an assignment is due, up to the actual time it is due.
Final Exam The Faculty of Arts and Science will schedule the exam sometime in October. Look up the time and place on the Examinations page, where it will be listed as CSC420.
Shortcuts To... Assignments, Lecture and Tutorial Notes

Course Materials


2 Assignments 40%  
1 Project 60%

Late Policy

Assignments are due at the beginning of the tutorial or lecture on the due date (e.g., Tues. at 3:10, or Fri. at 11:10).

The penalties for lateness are:

Assignments and the project will be submitted electronically through CDF.

Medical Issues

If you are unable to hand in an assignment or write an exam due to a serious medical condition, have your doctor complete a UofT Student Medical Certificate available from UofT Health Services Forms. Submit the completed certificate to your instructor.

CDF Information

By registering in this course you should have a CDF account. For information on CDF see Before going to a CDF lab, or to the course bulletin board, you need to look-up your CDF account.

Current Marks

Your marks are/will be posted on the CDF secure website

Matlab Vision Toolboxes

This course will use Matlab. If you are new to Matlab, first read the Matlab primer and try running the code described there.

Matlab tutorials are also provided to illustrate many of the concepts introduced in this course. The tutorials are installed on the CDF lab machines. After logging onto a CDF machine, cd ~jepson/pub/matlab and read the README file. This file tells you how to set up matlab so that it will run the tutorials. The tutorials are located in two directories:

We ISE and UTVIS to indicate these two toolboxes.

The Matlab toolboxes we use in this course are also available for download to your home computer (assuming you have Matlab at home) from the file (60MB). After unzipping this file, see the matlab/README file for instructions on how to set your matlab path. A second zip file containing two image sequences is needed for the motion tutorial, namely file (75MB). Unpack this zip file in the same directory as the previous one. It should form a new subdirectory matlab/images/seq/.


We take plagarism very seriously. Everything you hand in to be marked, namely assignments, tests and the final exam, must represent your own work. Read How not to plagarize.


Links to assignments and related information are/will be provided here.
Percent Posting Date Due Date Links
A1 20% Sept. 27 3pm, Thurs. Oct 13 Matlab starter code.
A2 20% Oct. 18 Extended to:
8am, Thurs. Nov. 3
Matlab starter code.
Project (Updated: 4:11pm 09/11/11) 60% Nov. 9 Proposal: Tues., Nov. 15, 3pm.
Milestone Presentation and Report: Fri., Dec. 2, 11am.
Final Report: Wed., Dec. 7, 3pm (extendable).
NEW (5pm Nov.18): Matlab starter code.
Image sequence on CDF: /u/jepson/pub/csc420/data/Flowers_03[p].avi
Here Flowers_03p.avi is just the first 50 or so frames.
See for info on the VLFeat software.

Lecture and Tutorial Materials

Links to some of the lecture/tutorial notes are provided below.
Date, Type Lecture/Tutorial Notes Additional/Optional Readings
Sept. 13-16
Lecture Notes
Image Projection Optional Reading: Section 2.1 of Szeliski's text.
Sept. 15
Tutorial Material
Intro to Matlab
Geometrical Review of Linear Algebra
Sept. 20-23
Lecture Notes
Linear Filtering Required Reading: Section 3.2 of Szeliski's text.
Optional Reading: Sections 3.4-5 of Szeliski's text.
Sept. 22
Tutorial Material
Intro to SVD with Applications in Vision.  
Sept. 27-30
Lecture Notes
Image Features: Part I
Image Features: Part II
Required Reading: Sections 4.1 and 4.2 of Szeliski's text.
Sept. 29
Tutorial Material
HoG example code.  
Sept. 30 - Oct. 4
Lecture Notes
Image Features: Part III
Normalized LoG of Sunflowers Image: nrmLoG_Sunflowers.avi (1.7Mb)
Required Reading: References Lowe (2004) and Bay et al, (2008), as cited on last page of "Image Features: Part III" lecture notes.
Oct. 7-14
Lecture Notes
Image Landmark Applications
Parameter Estimation
Required Reading: Sections 6.1 and 6.2 and Appendices B1 through B3 of Szeliski's text.
Oct. 13
Tutorial Notes
Derivations for Estimation Notes
Oct. 14-18
Lecture Notes
Parameter Estimation with Data Outliers Matlab Estimation Demos
Oct. 18
Lecture Notes
Edge Detection  
Oct. 21- Nov. 1
Lecture Notes
Epipolar Geometry Required Reading: Sections 7.1 and 7.2 of Szeliski's text.
Matlab Homography and F-matrix Estimation Demos
Nov. 3 - 10
Lecture Notes
Image Motion Reading: Fleet and Weiss Chapter
Reading: Sections 8.1 and 8.2 of Szeliski's text.
Nov. 15 - 22
Lecture Notes
Multi-Frame Reconstruction Reading: Section 7.3 of Szeliski's text.