CSE586/EE554 Computer Vision II
Mathematical Tools for Computer Vision
CSE Department, Penn State University
Instructor: Robert Collins

Spring 2012 Schedule: Tues/Thurs 9:45-11:00AM, 371 Willard

Course Syllabus

Presentation Order

Course Introduction
Lecture Notes
Intro to Course (Jan 10)   [slides]
Review of prob and statistics (Jan 12)   [notes]
Reference Material
Paper Search/Reading/Writing/Vision Resources
Prob/Stats review chapters [on Angel course site]

Gaussian Mixture Models and Expectation Maximization
Lecture Notes
Motivation: Bag of Features Models (Jan 17)   [slides]
The Gaussian Distribution (Jan 17)   [scanned notes]
K-Means algorithm, including intro to MLE (Jan 19,24)   [notes]
Intro to Gaussian Mixture Models (Jan26)   [scanned notes]
GMM / EM derivation (Jan26,31)   [slides]   [6 per page]
EM clarification   [pdf notes]
Homework Assignments
Homework 1 due Sunday, Feb 5
submit critiques before class on Thursday, Feb 9 ( 2 out of 4 papers from the "Research Papers" list below)
Sample Critique and Oral Presentation
Here is a sample critique and sample oral presentation for the paper Statistical Color Models with Applications to Skin Detection, by Jones and Rehg. For reference, here were the critique instructions and presentation instructions from our introductory class lecture. Cavaet: the sample critique I've written would most likely receive a "check" in our check-minus, check, check-plus grading system. However, if you are trying for a check-plus, please don't go overboard... for example, \ keep the length to no more than 2 pages.
Reference Material
Intro to Gaussian Distribution , Bishop, PRML book
Old and New Matrix Algebra Useful for Statistics, Tom Minka.
Estimating Gaussian Mixture Densities with EM - A Tutorial, Carlo Tomasi.
Mixture Models and EM , Bishop, PRML book
Research Papers / Oral Presentations
Thursday, Feb 9
Gang Zheng Adaptive Background Mixture Models for Real-time Tracking, Stauffer and Grimson
related paper of interest: Understanding Background Mixture Models for Foreground Segmentation, Power and Shoonees
Yang Lin Blobworld: Image Segmentation using EM ..., Carson et.al.
J.George Local Color Transfer via Probabilistic Segmentation by Expectation-Maximization, Tai et.al.
J.Degol Simultaneous Estimation of Segmentation and Shape, Rittscher etal.