Teaching     Home
News
   
Course

    CS 188/88 | Numerical Methods in Computer Vision | Fall 2004
Lecture

    TR 10:00 - 11:50 (X-hr: W 3:00-4:15) | Sudikoff 213
We will be making periodic use of X-hour so please keep this time available

Instructor
    Hany Farid | Sudikoff 159 | 646.2761
Syllabus

   

This class will cover topics in computer vision with an emphasis on the underlying mathematics and computational techniques. Each week we will discuss one paper -- I will lecture on the central mathematical concepts of the paper; a student will present a short (~15 minute) summary of the paper; we will critique the presentation and discuss the strengths and weaknesses of the paper; and you will then implement the basic technique(s) outlined in the paper for homework.

Grading

    Homework (75%) | Class Presentation/Participation (25%)
Computing

    All programming will be done in Matlab (tutorial)
Prerequisite
    calculus, linear algebra, Matlab

A short quiz (15 minutes) on prerequisite material will be given on the first day of class. Those without the proper background will not be able to take the course.
Papers

    Notes on convolution, differentiation, and Fourier transforms.

M. Turk and A. Pentland. Eigenfaces for Recognition. Journal of Cognitive Neuroscience, 3(1), 1991.
   [ pdf | Homework 1 ]

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.
   [ pdf | Homework 2 ]

S. Mika, B. Schlkopf, A. Smola, K.-R. Mller, M. Scholz, and G. Rtsch. Kernel PCA and de-noising in feature spaces. Advances in Neural Information Processing Systems (NIPS) 11:536-542, 1999.
   [ pdf | No Homework ]

H. Farid and E.H. Adelson. Separating Reflections from Images by use of Independent Components Analysis. Journal of the Optical Society of America, 16(9):2136-2145, 1999. (see also Separating reflections from a single image using local features by Levin, Zomet, and Weiss)
   [ pdf | Homework 3 ]

Y. Weiss. Deriving Intrinsic Images from Image Sequences. International Conference on Computer Vision, 2001.
   [ pdf | Homework 4]

S. Periaswamy and H. Farid. Elastic Registration in the Presence of Intensity Variations. IEEE Transactions on Medical Imaging, 22(7):865-874, 2003.
   [ pdf | Homework 5 ]

C. Tomasi and T. Kanade. Factoring Image Sequences into Shape and Motion 1991. Proceedings of IEEE Workshop on Visual Motion, 1991.
   [ pdf | Homework 6]

J. Shi and J. Malik. Normalized Cuts and Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8), 888-905, 2000.
   [ pdf | Homework 7]

J.M. Ogden, E.H. Adelson, J.R. Bergen, and P.J. Burt, Pyramid-Based Computer Graphics. RCA Engineer, 30(5):4-15, 1985.
   [ pdf ]
   and
P. Burt and E.H. Adelson. The Laplacian Pyramid as a Compact Image Code. Transactions on Communication, COM-31:532-540, 1983.
   [ pdf ]
Honor Code

   

The work that you submit must be your own, copying solutions or portions of solutions from a student or any other source is a violation of the honor code.

You may discuss general approaches with other students before you sit down at the computer to write code. Once you are writing code, however, your code must be written by you: any copying (electronic or otherwise) of another person's code or code fragments is a violation of the honor code - this includes code found on any web page (other than this page).

Violations of the honor code will be met with swift and severe punishment.

Teaching     Home