EE 589/689 Foundations of computer vision (Fall quarter 2006): project 3

Project 3 consists of reviewing a research paper. You can either choose one paper from the list below or suggest to me a paper yourselves. The only condition is that it should be on a different topic from your project 2. If possible, send me your review as a PDF file (using as email subject [EE539] Project 3); a handwritten review is also ok.

Your review should be 2-3 typed pages long and contain the following:

• A summary of the paper (1-2 pages long). You don't have to describe everything in the paper, use your judgement to select the important parts.
• Your evaluation of the paper. Here are some suggestions for questions to ask (not all may apply): What are the assumptions of the method? Are mathematical or algorithmical issues addressed rigorously (convergence, local optima, computational cost, etc.)? How is the optimisation carried out? Is the empirical evaluation fair and conclusive (competing methods are often presented at a disadvantage)? Is the method suitable for practical application (does it work with large images/large databases/real time/noisy images/clutter/occlusion/etc.), possibly with small modifications?

Deadline: Monday Dec. 11, 2006.

The list of papers, classified by type:

• Hough transforms and RANSAC:

  • Lei Xu and Erkki Oja: "Randomized Hough Transform (RHT): basic mechanisms, algorithms, and computational complexities". CVIU 57(2):131-154 (Mar. 1993).

• Motion segmentation:

  • John Y. A. Wang and Edward H. Adelson: "Representing moving images with layers". IEEE Trans. Image Proc. 3(5):525-638 (Sep. 1994). Other version.

• Graph-theoretical clustering:

  • Zhenyu Wu and Richard Leahy: "An optimal graph theoretic approach to data clustering: theory and its application to image segmentation". IEEE Trans. PAMI 15(11):1101-1113 (Nov. 1993).
  • Jianbo Shi and Jitendra Malik: "Normalized cuts and image segmentation". IEEE Trans. PAMI 22(8):888-905 (Aug. 2000).
  • Pedro F. Felzenszwalb and Daniel P. Huttenlocher: "Efficient graph-based image segmentation". IJCV 59(2):167-181 (Sep. 2004).

• Mean-shift clustering:

  • Dorin Comaniciu and Peter Meer: "Mean shift: a robust approach toward feature space analysis". IEEE Trans. PAMI 24(5):603-619 (May 2002).
  • Miguel Á. Carreira-Perpiñán: "Fast nonparametric clustering with gaussian blurring mean-shift". 23rd ICML, pp. 153-160 (2006).

• EM segmentation:

  • Chad Carson, Serge Belongie, Hayit Greenspan and Jitendra Malik: "Blobworld: image segmentation using expectation-maximization and its application to image querying". IEEE Trans. PAMI 24(8):1026-1038 (Aug. 2002).

• Detection (skin, faces, etc.):

  • Michael J. Jones and James M. Rehg: "Statistical color models with application to skin detection". IJCV 46(1):81-96 (Jan. 2002). Other version.
  • Henry Schneiderman and Takeo Kanade: "Object detection using the statistics of parts". IJCV 56(3):151-177 (Feb. 2004).
  • Matthew Alan Turk and Alex Pentland: "Eigenfaces for recognition". J. Cognitive Neurosci. 3(1):71-86 (1991).
  • Henry A. Rowley, Shumeet Baluja and Takeo Kanade: "Neural network-based face detection". IEEE Trans. PAMI 20(1):23-38 (Jan. 1998).
  • Kah-Kay Sung and Tomaso Poggio: "Example-based learning for view-based human face detection". IEEE Trans. PAMI 20(1):39-51 (Jan. 1998).

• Object recognition:

  • Daniel P. Huttenlocher and Shimon Ullman: "Recognizing solid objects by alignment with an image". IJCV 5(2):195-212 (Nov. 1990).

OHSU | OGI | Dept. of CSEE | Adaptive Systems Group | MACP's Home Page