AI Qualifying Exam Reading List Associated with CS 766 - COMPUTER VISION

For Fall 2009 and Later Exams

Basic Topics

  1. Edge and Feature Detection: First and second-order differential operators, Laplacian-of-Gaussian operator, Canny operator, Gaussian and Laplacian pyramids, SIFT feature detector and descriptor, interest point detection.
    [BURT83; FORS03 (Chap. 7, 8, 9.2); LOWE99; TRUC98 (Chap. 3, 4)]
  2. Segmentation: Thresholding, boundary and curve detection, chain code, Hough transform, graph-based segmentation, RANSAC algorithm.
    [FORS03 (Chap. 14, 15); SHI00; TRUC98 (Chap. 5)]
  3. Stereo: Correlation, correspondence problem, epipolar geometry, fundamental matrix.
    [FORS03 (Chap. 10.1, 11); TRUC98 (Chap. 7)]
  4. Object Recognition: 2D object representations, model-based matching, principal component analysis, appearance-based recognition.
    [BELO02; FORS03 (Chap. 18, 22.1 - 22.3); TRUC98 (Chap. 10); TURK91; NAYA96; VIOL01]

Advanced Topics

  1. Image Formation, Camera Calibration, and Image-based Modeling and Rendering: Imaging geometry, radiometry, projection, camera calibration, digitization, mosaics, view synthesis, texture synthesis.
    [EFRO01; CIPO99; FORS03 (Chaps. 1 - 4, 26); SEIT96; SZEL06; TRUC98 (Chap. 6)]
  2. Feature Detection and Segmentation: Edge detection, interest operators, SIFT, feature descriptors, scale-space, snakes, segmentation, mean-shift algorithm, texture, robust methods, RANSAC.
    [AMIN90; BAKE04; COMA99; FORS03 (Chap. 9.1 - 9.3, 14 - 16); LOWE99; MIKO04; SHI00; STEW99; TRUC98 (Chap. 5)]
  3. Inferring Three-Dimensional Shape: Epipolar geometry, multiple-view geometry, fundamental matrix, trilinear tensor, shape from shading, stereo, photometric stereo, shape from contour, shape from texture.
    [BOYK01; CRIM99; FORS03 (Chap. 5, 9.4, 10, 11); HART00; KUTU00; POLL04; SCHA02; TRUC98 (Chap. 7, 9)]
  4. Motion Analysis: Motion detection, optical flow, tracking, active contours (snakes), layers, structure from motion, spatiotemporal processing.
    [AMIN90; BAKE04; FORS03 (Chap. 12, 13, 26.1); ISAR98; TOMA92; TRUC98 (Chap. 8); WANG94]
  5. Object Recognition: 2D and 3D object model construction and representation, appearance-based methods, alignment method, geometric hashing, principal component analysis, model-based matching, invariants, learning object categories, viewpoint and pose determination, systems.
    [BELO02; COOT98; FELZ05; FORS03 (Chap. 18, 21.4, 22.1 - 22.3, 23.1 - 23.3); GRAU05; NAYA96; TRUC98 (Chap. 10); ULLM91; VIOL01; WISK97]

References

[AMIN90]
Amini, A. A., Weymouth, T. E., Jain, R. C., Using dynamic programming for solving variational problems in vision, IEEE Trans. Pattern Analysis and Machine Intelligence 12(9), 1990, 855-867.

[BAKE04]
Baker S. and Matthews I., Lucas-Kanade 20 years on: A unifying framework, Int. J. Computer Vision 56(3), 2004, 221-255.

[BELO02]
Belongie, S., Malik, J., and Puzicha, J., Shape matching and object recognition using shape contexts, IEEE Trans. Pattern Analysis and Machine Intelligence 24(4), 2002, 509-522.

[BOYK01]
Boykov, Y. and Jolly, M.-P., Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images, Proc. 8th Int. Conf. Computer Vision, Vol. 1, 2001, 105-112.

[BURT83]
Burt, P., and Adelson, E., The Laplacian pyramid as a compact image code, IEEE Trans. Communications 31(4), 1983, 532-540.

[CIPO99]
Cipolla, R., and Gee, A., Projection, University of Cambridge Handout #3, 1999.

[COMA99]
Comaniciu, D., and Meer, P., Mean shift analysis and applications, Proc. 7th Int. Conf. Computer Vision, 1999, 1197-1203. (A more detailed version appears in Comaniciu, D., and Meer, P., Mean shift: A robust approach toward feature space analysis, IEEE Trans. Pattern Analysis and Machine Intelligence 24(5), 2002, 603-619.)

[COOT98]
Cootes, T., Edwards, G., and Taylor, C., Active appearance models, Proc. 5th European Conf. Computer Vision, Vol. 2, 1998, 484-498. (An alternative version appears in Cootes, T., Edwards, G., and Taylor, C., Active appearance models, IEEE Trans. Pattern Analysis and Machine Intelligence 23(6), 2001, 681-685.)

[CRIM99]
Criminisi, A., Reid, I., and Zisserman, A., Single view metrology, Proc. 7th Int. Conf. Computer Vision, 1999, 434-442. (Longer versions appear in (1) Criminisi, A., Reid, I., and Zisserman, A., Single view metrology, Int. J. Computer Vision 40(2), 2000, 123-148, and (2) Criminisi, A., Single-view metrology: Algorithms and applications, Proc. DAGM Symposium, 2002, 224-239.)

[EFRO01]
Efros, A., and Freeman, W., Image quilting for texture synthesis and transfer, Proc. SIGGRAPH '01, 2001, 341-346.

[FELZ05]
Felzenszwalb, P., and Huttenlocher, D., Pictorial structures for object recognition, Int. J. Computer Vision 61(1), 2005, 55-79.

[FORS03]
Forsyth, D., and Ponce, J., Computer Vision: A Modern Approach, Prentice Hall, Upper Saddle River, N.J., 2003.

[GRAU05]
Grauman, K. and Darrell T., The pyramid match kernel: Discriminative classification with sets of image features, Proc. Int. Conf. Computer Vision, 2005.

[HART00]
R. Hartley, R., and Zisserman, A., Epipolar geometry and the fundamental matrix, in Multiple View Geometry in Computer Vision, Chapter 8, Cambridge University Press, 2000, 219-243.

[ISAR98]
Isard, M., and Blake, A., CONDENSATION: Conditional density propagation for visual tracking, Int. J. Computer Vision 29(1), 1998, 5-28.

[KUTU00]
Kutulakos, K., and Seitz, S., A theory of shape by space carving, Int. J. Computer Vision 38(3), 2000, 199-218.

[LOWE99]
Lowe, D., Object recognition from local scale-invariant features, Proc. 7th Int. Conf. Computer Vision, 1999, 1150-1157. (For a more complete description of the SIFT feature detector, see Lowe, D., Distinctive image features from scale-invariant keypoints, Int. J. Computer Vision 60(2), 2004, 91-110.)

[MIKO04]
Mikolajczyk, K., and Schmid, C., Scale and affine invariant interest point detectors, Int. J. Computer Vision 60(1), 2004, 63-86.

[NAYA96]
Nayar, S., Murase, H., and Nene, S., Parametric appearance representation, in Early Visual Learning, S. Nayar and T. Poggio, eds., Oxford University Press, Oxford, 1996, 131-160.

[POLL04]
Pollefeys, M., Van Gool, L., Vergauwen, M., Verbiest, F., Cornelis, K., Tops, J., and Koch, R., Visual modeling with a hand-held camera, Int. J. Computer Vision 59(3), 2004, 207-232.

[SCHA02]
Scharstein, D., and Szeliski, R., A taxonomy and evaluation of dense two-frame stereo correspondence algorithms, Int. J. Computer Vision 47(1/2/3), 2002, 7-42.

[SEIT96]
Seitz, S., and Dyer, C., View morphing, Proc. SIGGRAPH 96, 1996, 21-30.

[SHI00]
Shi, J., and Malik, J., Normalized cuts and image segmentation, IEEE Trans. Pattern Analysis and Machine Intelligence 22(8), 2000, 888-905.

[STEW99]
Stewart, C., Robust parameter estimation in computer vision, SIAM Review 41(3), 1999, 513-537

[SZEL06]
Szeliski, R., Image alignment and stitching: A tutorial, Microsoft Research Technical Report MSR-TR-2004-92, December 2006.

[TOMA92]
Tomasi, C., and Kanade, T., Shape and motion from image streams under orthography: A factorization method, figures, Int. Journal Computer Vision 9(2), 1992, 137-154.

[TRUC98]
Trucco, E., and Verri, A., Introductory Techniques for 3-D Computer Vision, Prentice Hall, Upper Saddle River, N.J., 1998.

[TURK91]
Turk, M., and Pentland, A., Face recognition using eigenfaces, Proc. Computer Vision and Pattern Recognition Conf., 1991, 586-591. (An alternative paper that is longer but may be easier to read is Turk, M., and Pentland, A., Eigenfaces for recognition, J. Cognitive Neuroscience 3(1), 1991, 71-86.)

[ULLM91]
Ullman, S., and Basri, R., Recognition by linear combination of models, IEEE Trans. Pattern Analysis and Machine Intelligence 13(10), 1991, 992-1006.

[VIOL01]
Viola, P., and Jones, M., Rapid object detection using a boosted cascade of simple features, Proc. Computer Vision and Pattern Recognition Conf., Vol.1, 2001, 511-518. (A longer version appears in Viola, P., and Jones, M., Robust real-time face detection, Int. J. Computer Vision 57(2), 2004, 137-154.)

[WANG94]
Wang, J. Y. A., and Adelson, E. H., Representing moving images with layers, IEEE Trans. Image Processing 3(5), 1994, 625-638.

[WISK97]
Wiskott, L., Fellous, J-M., Kruger, N., and von der Malsburg, C., Face recognition by elastic bunch graph matching, IEEE Trans. Pattern Analysis and Machine Intelligence 19(7), 1997, 775-779.