CS370: Introduction to Computer Vision

• Fall 2009; Tuesday and Thursday, 2:30-3:45pm • Computer Science Building Room 140 (See map)


Erik Learned-Miller
elm at cs.umass.edu
(413) 545-2993

Teaching Assistant: None


Reading Materials

Temporary on-line version of Required Text: Temporary on-line copy
Make sure to get the 2nd edition!!!

Required Text: Digital Image Processing Using MATLAB, 2nd edition, (Hardcover)
Make sure to get the 2nd edition!!!


MATLAB Tutorial

Interesting Links

Movie shown in class on optical illusions

Checker shadow illusion

Early color photographs by S. M. Prokudin-Gorsky

Flower Garden movie.

Non-lambertian reflectance functions

Explanation of hexagonal sampling efficiency

Problem Sets

Homework 3 Sample Solution


Date Lecture topic New assignments Assignments due Reading
Sept. 8 Introduction. What is Computer Vision? Assignment 1: Read Lightness Perception and Lightness Illusions
Come up with five questions relevant to the paper. These can be things you didn't understand after a careful reading of the paper, or questions which the paper raises. Turn in the answer written up as a .pdf file. You will be graded on the depth of your questions and how much thought you were judged to have put into them.

As. 1 due Sept. 15

Sept. 10 Introduction to using MATLAB for Computer Vision. Matlab Session Transcript from Lecture

Assignment 2: Colorizing the Prokudin-Gorsky photo collection

As. 2 due Sept. 17

Chap. 2 in Textbook (skim)
Sept. 15 Formalizing the decision making process. Minimizing error. Maximizing utility. Review of basic probability theory. You will be responsible for all of the basic probability theory in this handout.

Probability handout (see lecture description).
Sept. 17 Introduction to supervised learning. Supervised learning for vision. Estimating distributions from data. Features of images.

Sept. 22 Estimating distributions from data. Estimating joint distributions of multiple variables. Leveraging independence for better estimation. More applications of Bayes' rule.

Sept. 24 Alignment by maximization of mutual information. Back to supervised learning using probability estimates.

Assignment 3. Aligning the Prokudin-Gorsky images automatically.
As. 3 due Oct. 6

Mutual Information handout.
Sept. 29 Naive Bayes. Assuming independence of features. Comparing the dependence of features using mutual information. Evaluating the value of features using mutual inforamtion.

Oct. 1 Nearest neighbor classification

Oct. 6
Nearest neighbor classification continued.

Oct. 8 Alignment and classification.

Assignment 4. Classification of handwritten digits. Training and test data file (digits.mat)
Due Oct. 22nd, before class (10\% penalty for lateness this time.)
Handout: Supervised learning and estimation
Oct. 13 Solving difficult alignment problems through joint alignment: congealing.

Oct. 15 Congealing continued.

Oct. 20 Image formation, lecture 1. Pinhole cameras, basic optics.

Oct. 22 Image formation, lecture 2. Radiometry. Solid Angle, watts per unit area, etc.

Assignment 5: Translation invariant classification
As. 4 due today. As. 5 extended to TUesday, Nov. 3, before class.

Oct. 27 Illuminance, luminance, brightness, radiance, irradiance, cosine to the fourth law.

Oct. 29

Nov. 3 **************************************** In Class Mid-term ***************************************

As. 5 due today! (before class)

Nov. 17 Background subtraction

Nov. 19 Background subtraction, continued.

Nov. 24 Optical flow.

Assignment 6: Background subtraction.
Assignment 6 is due on Dec. 10, the last day of class


Dec. 1 Comparing Lukas-Kanade optical flow and Horn-Schunk Optical flow.

Assignment 7

Dec. 3 Mobil-eye and examples of real-world vision apps. Edges and lines as primitive vision features.

Dec. 8 More on edges. Higher level features. SIFT features.

Dec. 10 Last day of class.

Friday Dec. 18 ***FINAL EXAM ***: 10:30am, Computer Science 142

Review of Radiometry
Lecture slides 1-30
Lecture slides 31-60
Lecture slides 61-90
Lecture slides 91-137