Undergraduate Program

Machine Vision

Course: CSC 
Term: Spring 2013-2014

CSC 249/449 Machine Vision (Spring 2013)

Course description

Fundamentals of computer vision, including image formation, elements of human vision, low-level image processing, and pattern recognition techniques. Advanced topics include modern visual features, graphical models, model-based and data-driven approaches, and contextual inference, as well as illustrative examples of successes and challenges in applications. CSC 449, a graduate-level course, requires additional readings and assignments (including a course project).

Please check pre-requisites on the official course listing page. Some knowledge of linear algebra and basic statistics is helpful but we will review these subjects in the class (please discuss with me if you are not sure). For assignments and projects, the most common programming languages are MatlabC or C++. Note that  Matlab provides an image processing toolbox and is available on most CS department undergraduate and research networks.


Course schedule (tentative - to be updated)

week dates chapter key topics CSC 249 CSC 449 notes
1 1/17 1, 2 overview; image formation      
2 1/22, 1/24 3, 4 color vision; low-level image processing      
3 1/29, 1/31 4, notes (Forsyth) texture; Intro to (review of) probability      
4 2/5, 2/7 Duda & Hart pattern recognition concepts (incl. classifiers)      
5 2/12, 2/14 5, 6 modern visual features      
6 2/19, 2/21 9, 10 mid-level vision (incl. segmentation, Hough Transform)      
7 2/26,
2/28
notes & special lecture recognizing faces and people      
8 3/5, 3/7 review/midterm exam        
9 3/12, 3/14 Spring Break        
10 3/19, 3/21 midterm solutions, 12 image registration selecting course  survey topics selecting course project topics 1-page proposal
11 3/26, 3/28 guest lecture by Prof. Jinwei Gu computational photography, computer graphics      
12 4/2, 4/4 11, 7, 8 tracking, stereo & 3D      
13 4/9, 4/11 18, notes recognizing objects, scenes, actions and events      
14 4/16, 4/18 notes data-driven computer vision      
15 4/23, 4/25 21, notes & special lecture  content-based image annotation & retrieval (or alternatively medical image analysis) or attribute learning in vision    
16 4/30, 5/2 notes & special lecture contextual inference in computer vision      
17 5/7, 5/9 final presentations  & reports impress us! 5/7 5/9  
18 5/14, 5/16* final presentations  & reports impress us!   5/14, 5/16*  

 


Instructor and grading

Instructor: Prof. Jiebo Luo, CSB Rm 611, x65784
TA: Lam Tran
Lectures: Tuesdays and Thursdays, 12:30-13:45, CSB 601
Office hours: after classes (15:00-16:00) or by appointment (use email).

Grading (total 100%)

  1. midterm 30%
  2. homework assignments 35% (including a small project 10%)
  3. final project & presentation (for CSC 449) 30% (presentation counts 10%)
  4. final survey & presentation (for CSC 249) 30% (presentation counts 10%)
  5. class participation and effort 5%
Expectation for the final project -  something "new", e.g., 
  1. an existing algorithm applied to new data or new problems
  2. a new algorithm (or a modified version of an existing algorithm) applied to the same data
  3. new findings from a comparative study of using different algorithms for the same problem

 Textbooks and other resources

Required textbook:

Computer Vision: A Modern Approach, 2/E
David A. Forsyth and Jean Ponce

ISBN-10: 013608592X
Publisher:  Prentice Hall, 2012

Recommended textbook:
Pattern Classification, 2/E
Richard O. Duda, Peter E. Hart and David G. Stork
ISBN-10: 0471056693
Publisher: John Wiley & Sons, 2001

Recommended papers (use IEEE Xplore on the university network for free access to these and other papers):
Longuet-Higgins Prize recipients
(CVPR annual award 
for 'fundamental contributions in Computer Vision that Have Withstood the Test of Time')