IT 803/ CS 803
Doctoral Tutorial in IT 

Special Topics in Computer Vision and Machine Learning

Time/Location: Tuesday 7:20-10:00,  Robinson B204
Instructor: Dr. Jana Kosecka
ST2, 417, kosecka@cs.gmu.edu
http://cs.gmu.edu/~kosecka/cs803.html

This course will cover topics in computer vision, robotics and machine learning, with the emphasis on mathematical tools, computational principles and more recent trends in these disciplines. First few weeks will cover the preliminaries of image formation and basic extraction of features from images. For the remainder of the semester we read and review selected papers. Each weak one student will present summary of the assigned paper, followed by a discussion of the strenghts and weaknesses of the paper. The homeworks will be comprised of implementing the basic technique covered in the paper in Matlab.

Grading: Homeworks (about every 2 weeks) + Project (optional) 70%  Presentations 30%
Prerequisites: linear algebra, calculus
Lecture Materials:  Lecture notes 

Recommended Textbooks:

Invitation to 3D Vision:  From Images to Geometric Models: Y. Ma, S. Soatto, J. Kosecka and S. Sastry (for part I of the course)
Introductory Techniques for 3D computer Vision. E. Trucco and A. Verri, Prentice-Hall, 1998
Computer Vision: A Modern Approach: D. Forsythe and J. Ponce, Prentice-Hall, 2003

Required Software:
Matlab

Quiz
A short quiz on the prerequisites will be given in the first class.

Preliminary list of papers:

  • M. Turk and A. Pentland. Eigenfaces for Recognition. Journal of Cognitive Neuroscience, 3(1), 1991
  • P. N. Belhumeur, J.P. Hespanha, D.J. Kriegman. Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(7): 711-720, 1997
  • R. Vidal, Y. Ma and S. Sastry. Generalized Principal Component Analysis. IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2003
  • S. Soatto, G. Doretto, Y.-N.Wu. Dynamic Textures, IJCV 2003
  • D. Lowe. Distintive Image Features from scale-invariant keypoints, IJCV 2004
  • J. Kosecka, F. Li, X. Yang. Global Localization and Relative positioning based on scale invariant keypoints, GMU-TR 2005
  • C. Tomasi and T. Kanade. Factoring Image Sequences into Shape and Motion 1991. Proceedings of IEEE Workshop on Visual Motion, 1991.
  • S. Baker et. al. Lucas-Kanade 20 year on. CMU-tech-report, 2003.
  • J. Shi and J. Malik. Normalized Cuts and Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8), 888-905, 2000.
  • H. Farid and E.H. Adelson. Separating Reflections from Images by use of Independent Components Analysis. JOSA, 16(9):2136-2145, 1999
  • Y. Weiss. Deriving Intrinsic Images from Image equences. International Conference on Computer Vision, 2001.

    • Addional list of topics:

  • Probabilistic Object Recognition - Constellation of Features Models.
  • Object detection and Modelling context
  • Low-Level feature invariants
  • Modelling reflectance properties of scenes