Skip to main content

Undergraduate Program

Machine Vision

Course: CSC  249
Term: Spring 2012-2013

CSC 249/449 Machine Vision (Spring 2012)


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 Matlab, C or C++. Note that  Matlab provides an image processing toolbox and is available on most CS department undergraduate and research networks.


Course schedule (tentative)

weekdateschapterkey topicsCSC 249CSC 449notes
11/191, 2overview; image formation   
21/24, 1/263, 4color vision; low-level image processing   
31/31, 2/24, notestexture; Intro to (review of) probability   
42/7, 2/9Duda & Hartpattern recognition concepts (incl. classifiers)   
52/14, 2/165, 6modern visual features   
62/21, 2/239, 10mid-level vision (incl. segmentation, Hough Transform)   
72/28, 3/1guest lectures by Dr. Andrew Gallagherrecognizing faces and people   
83/6, 3/8review/midterm exam    
93/13, 3/15spring break    
103/20, 3/22midterm solutions, 12image registrationselecting course  survey topicsselecting course project topics1-page proposal
113/27, 3/2911, 7, 8tracking, stereo & 3D   
124/3, 4/518, notesrecognizing objects, scenes, actions and events   
134/10, 4/12notesdata-driven computer vision   
144/17, 4/1921, notes, & guest lecture by Dr. Dhiraj Joshicontent-based image annotation & retrieval   
154/24, 4/26notescontextual inference in computer vision   
165/1, 5/3final presentations  & reportsimpress us!5/15/3 
175/5, 5/10final presentations  & reportsimpress us! 5/8, 5/10 

Instructor and grading

Instructor: Prof. Jiebo Luo, CSB Rm 611, x65784
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%)

  • homework assignments 35% (including a small project 10%)
  • midterm 30%
  • final project & presentation (for CSC 449) 30% (presentation counts 10%)
  • final survey & presentation (for CSC 249) 30% (presentation counts 10%)
  • class participation 5%

Expectation for the final project -  something "new"

  • an existing algorithm applied to new data or new problems
  • a new algorithm (or modified version of an existing algorithm) applied to the same data
  • 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')

  • 2005 –
    • David Mumford and Jayant Shah, "Boundary detection by minimizing functionals", CVPR 1985.
    • Ted Adelson and John Wang, "Layered representation for motion analysis", CVPR 1993.
  • 2006 –
    • H. Rowley, S. Baluja and Takeo Kanade, "Neural Network-Based Face Detection", CVPR 1996.
    • Cordelia Schmid and Roger Mohr, "Combining greyvalue invariants with local constraints for object recognition", CVPR 1996.
  • 2007 –
    • J. Shi and J. Malik, "Normalized Cuts and Image Segmentation", CVPR 1997.
    • E. Osuna, R. Freund, and F. Girosi, "Training Support Vector Machines: An Application to Face Detection", CVPR 1997.
  • 2008 –
    • H. Schneiderman and Takeo Kanade, "Probabilistic modeling of local appearance and spatial relationships for object recognition", CVPR 1998.
    • C. Bregler and J. Malik, "Tracking people with twists and exponential maps", CVPR 1998.
  • 2009 –
    • Jinggang Huang, David Mumford, "Statistics of Natural Images and Models", CVPR 1999.
    • Chris Stauffer, W.E.L. Grimson, "Adaptive Background Mixture Models for Real-Time Tracking", CVPR 1999.
  • 2010 –
    • Pedro F. Felzenszwalb and Daniel P. Huttenlocher, "Efficient Matching of Pictorial Structures", CVPR 2000.
    • Dorin Comaniciu, Visvanathan Ramesh, and Peter Meer, "Real-Time Tracking of Non-Rigid Objects Using Mean Shift", CVPR 2000.
  • 2011 –
    • Paul A. Viola and Michael J. Jones, "Rapid Object Detection using a Boosted Cascade of Simple Features", CVPR 2001.