2523 Outline (Winter 2008) -------------------------- Each week, we will cover two papers in the 2x50 minutes (+ 10 minute break) class. The supplemental readings listed below are additional references meant to complement the two main papers, and are optional reading. When url's are listed for the papers below, students are expected to download their own copies. When e-versions are not available, copies will be provided in class (at the latest) at the lecture prior to the lecture in which they will be covered. Copies of the supplemental readings will not be provided. However, if you are trying to secure a supplemental reading, please contact me, as I may have a source you can copy. Coverage of the papers will be in the form of student presentations, consisting of (for each paper) a 30 minute presentation, followed by a 20 minute discussion. For your presentation, you may use overhead slides (which will be provided upon request), or a laptop-based powerpoint presentation (I can provide the laptop for the presentation, but you are expected to prepare it under vmware or staroffice). Students are expected to come to class having read at least the two covered papers. This is essential for a good discussion. The grade for the course will be based primarily on a project (~80%), along with your paper presentation(s) (~10%) and class participation (~10%). For your project, you can implement a recognition system, or you can survey a collection of related recognition papers. You must submit a one-page written project proposal to me by Jan 31 (latest). I encourage you to come and talk to me ASAP to discuss project ideas. I may be able to help you define a topic (project or papers) related to your own thesis research. Jan 8 Introduction 1. S. Dickinson, "Object Representation and Recognition", in: E. Lepore and Z. Pylyshyn (eds.), What is Cognitive Science?, Basil Blackwell publishers, 1999, pp 172--207. (http://www.cs.toronto.edu/~sven/2523/Papers/ruccs99.ps) Jan 15 Generalized Cylinder-Based Recognition 1. R. Nevatia and T.O. Binford. Description and Recognition of Curved Objects. Artificial Intelligence, (8):77--98, 1977. (www.cs.toronto.edu/~sven/2523/Papers/nevatia.pdf) 2. Brooks, R. A. "Model-Based Three Dimensional Interpretations of Two Dimensional Images", IEEE Pattern Analysis and Machine Intelligence, 140?150, March 1983; also in Proceedings of 7th Int. Joint Conf. on Artificial Intelligence, Vancouver, Canada, August 1981, pp. 619--624. (expanded version: Brooks, R. A. "Symbolic Reasoning Among 3-D Models and 2-D Images", Artificial Intelligence Journal, 17, (1-3), 1981, pp. 285--348.) (www.cs.toronto.edu/~sven/2523/Papers/acronym.pdf) Supplemental reading: 1. T. Binford. ``Visual Perception by Computer'', Proceedings, IEEE Conference on Systems and Control, Miami, FL, 1971. (www.cs.toronto.edu/~sven/2523/Papers/binford.pdf) 2. D. Marr and H. K. Nishihara. ``Representation and reconition of the spatial organization of three dimensional shapes'', Proceedings of Royal Society of London B, 200:269--294, 1978. 3. Gerald J. Agin, Thomas O. Binford, ``Computer Description of Curved Objects'', IEEE Trans. Computers 25(4): 439-449 (1976). Jan 22 Active Object Recognition (automatic programming) 1. R. C. Bolles and R. Horaud. ``3DPO: A three-dimensional part orientation system'', International Journal of Robotics Research, 5(3):3 26, Fall 1986. (www.cs.toronto.edu/~sven/2523/Papers/bolles.pdf) 2. K. Ikeuchi, ``Automatic Generation of Object Recognition Programs'' Proc of IEEE, 76(8), 1988 (www.cs.toronto.edu/~sven/2523/Papers/ikeuchi.pdf) Supplemental reading: Goad, Chris, ``Special purpose automatic programming for 3D model-based vision,'' Proceedings ARPA Image Understanding Workshop, Arlington, Virginia (1983). (also appears as ``Special purpose automatic programming for 3D model-based vision,'' in: From Pixels to Predicates, ed. Alex Pentland, (Ablex Publishing Co., 1986), 371-391.) Jan 29 Alignment 1. David G. Lowe, Three-dimensional object recognition from single two-dimensional images, Artificial Intelligence, 31, 3 (March 1987), pp. 355-395. (www.cs.toronto.edu/~sven/2523/Papers/lowe.pdf) 2. Huttenlocher, D.P., and Ullman, S., Recognizing Solid Objects by Alignment with an Image, IJCV(5), No. 2, November 1990, pp. 195-212. (also appears as shorter, preliminary version in: ``Recognizing Solid Objects by Alignment,'' Proceedings, DARPA Image Understanding Workshop, 1988, pp 1114--1124, and in ``Object Recognition Using Alignment,'' Proceedings, ICCV 1987, pp 102--111, and Proceedings, DARPA Image Understanding Workshop, 1987, pp 370--380. (www.cs.toronto.edu/~sven/2523/Papers/huttenlocher.pdf) Supplemental reading: 1. L.G. Roberts, ``Machine Perception of 3-D Solids,' Optical and Electro-Optical Information Processing, (J. T. Tippet etal., Eds.), 1965, pp.159-197. (the classic first paper in 3-D object recognition) (www.cs.toronto.edu/~sven/2523/Papers/roberts.html) 2. David G. Lowe, ``The viewpoint consistency constraint'', International Journal of Computer Vision, 1, 1 (1987), pp. 57-72. (a good companion paper to Lowe's AI Journal paper). 3. S. Ullman and R. Basri, ``Recognition by linear combinations of models'', IEEE Trans. Pattern Anal. Machine Intell., 13:992--1006, 1991. (The seminal linear combination (LC) of views paper.) Feb 5 Interpretation Tree Search 1. Grimson, W. E. L., and Lozano-P~rez, T. 1984. Modelbased recognition and localization-from sparse range or tactile data. Int. d. Robotics Res. 3(3):3-35. (www.cs.toronto.edu/~sven/2523/Papers/grimson.pdf) 2. T. J. Fan, G. Medioni, and R. Nevatia. Recognizing 3-D objects using surface descriptions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(11):1140--1157, 1989. (www.cs.toronto.edu/~sven/2523/Papers/fan.pdf) Supplemental reading: David T. Clemens. Region-Based Feature Interpretation for Recognizing 3D Models in 2D Images. Technical Report 1307, MIT AI Laboratory, 1991. (Good IT search application using regions in a 3D from 2D environment) Feb 12 Geometric Invariants 1. Flynn, P.J., and Jain, A.K., 3D Object Recognition Using Invariant Feature Indexing of Interpretation Tables, CVGIP(55), No. 2, March 1992, pp. 119-129. (www.cs.toronto.edu/~sven/2523/Papers/flynn.pdf) 2. Y. Lamdan, J. T. Schwartz and H. J. Wolfson, Affine invariant model-based object recognition, IEEE Trans. on Robotics and Automation 6(5):578-589 (1990). (also: `Object Recognition by Affine Invariant Matching'. Proc. CVPR, pp. 335--344, 1988.) (www.cs.toronto.edu/~sven/2523/Papers/lamdan.pdf) Supplemental reading: 1. Forsyth, D.A., Mundy, J.L., Zisserman, A., Coelho, C., Heller, A., Rothwell, C., "Invariant Descriptors for 3-D Object Recognition and Pose", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 13, pp. 971-992, October 1992. (use of projective invarants in object recognition, good scaling to large databases). 2. H. J. Wolfson and I. Rigoutsos, Geometric hashing: an overview, IEEE Comput. Sc. and Eng. 4(4), p. 10-21, 1997. (good applications to biomedical imaging) Feb 19 Reading Week Feb 26 Qualitative 3-D Shape-Based Recognition 1. I. Biederman, ``Recognition-by-Components: A Theory of Human Image Understanding'', Psychological Review, 94, 115-147. (shorter version in: I. Biederman, I ``Matching Image Edges to Object Memory'', In Proceedings of the First International Conference on Computer Vision, IEEE Computer Society, 1987, pp 384--392.) (www.cs.toronto.edu/~sven/2523/Papers/biederman.pdf) 1. A. Pentland, ``Perceptual Organization and the Representation of Natural Form'', Artificial Intelligence, Vol. 28, No. 2, pp 293-331, 1986. (www.cs.toronto.edu/~sven/2523/Papers/pentland.pdf) Supplemental reading: 1. A. Pentland, ``Recognition by Parts,'' Proc. Int'l Conf. on Computer Vision, pp 612--620, 1987. 2. Sven J. Dickinson, Alex P. Pentland, and Azriel Rosenfeld, ``3-D Shape Recovery Using Distributed Aspect Matching'', IEEE PAMI, Vol. 14, No. 2, pp 174 - 198. (proposes a general scheme for modeling and recovering qualitative part models) 2. S. J. Dickinson, A. P. Pentland, and A. Rosenfeld, ``From volumes to views: an approach to 3D object recognition'', CVGIP: Image Understanding, Vol.55, No.2, pp. 130-154, March 1992. (extends the previous recovery scheme to a recognition model) 4. S. Dickinson, R. Bergevin, I. Biederman, J.-O. Eklundh, A. Jain, R. Munck-Fairwod, and A. Pentland, ``Panel Report: The Potential of Geons for Generic 3-D Object Recognition'', Image and Vision Computing, Vol. 15, No. 4, April 1997, pp 277--292. (url on my website - a good overview of the issues and challenges facing geons - includes refs to all geon-related work). Mar 4 Deformable Models 1. S. Dickinson and D. Metaxas, ``Integrating Qualitative and Quantitative Shape Recovery'', International Journal of Computer Vision, Vol. 13, No. 3, 1994, pp 1--20. (first paper to recover deformable superquads from 2D images without manual initialization and with occlusion). (http://www.cs.toronto.edu/~sven/Papers/ijcv94.ps.gz) 2. Stan Sclaroff and Alex Pentland, ``Modal Matching for Correspondence and Recognition'', IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 17, No. 6, pp 545-561, 1995. (http://www.cs.toronto.edu/~sven/2523/Papers/sclaroff.pdf) Supplemental reading: 1. Demetri Terzopoulos and Dimitris N. Metaxas, ``Dynamic 3D Models with Local and Global Deformations: Deformable Superquadrics'', IEEE Transactions on Pattern Analysis and Machine Intelligence 13(7): 703-714 (1991). (nice framework for combining low-dimensional global part models with local deformations for increased coverage). 2. A.L. Yuille, D.S. Cohen, and P. Hallinan, "Feature extraction from faces using deformable templates," International Journal of Computer Vision, vol. 8, no. 2, pp. 99--112, 1992. (www.cs.toronto.edu/~sven/2523/Papers/yuille.pdf) 3. R. Basri, L. Costa, D. Geiger, and D. Jacobs, ``Determining the Similarity of Deformable Shapes," Vision Research, 38:2365-2385, 1998. (www.cs.toronto.edu/~sven/2523/Papers/basri.pdf) Mar 11 Function and Context 1. L. Stark and K. Bowyer, ``Function-Based Generic Recognition for Multiple Object Categories'', CVGIP(59), No. 1, January 1994, pp. 1-21. (www.cs.toronto.edu/~sven/2523/Papers/stark.pdf) 2. T. Strat and M. Fischler, ``Context-based vision: recognizing objects using information from both 2D and 3D imagery'', IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 13, Issue 10, Oct. 1991 Page(s):1050 - 1065 (www.cs.toronto.edu/~sven/2523/Papers/strat.pdf) Supplemental reading: 1. E. Rivlin, S. Dickinson, and A. Rosenfeld, ``Recognition by Functional Parts'', Computer Vision and Image Understanding, special issue on Function-based Object Recognition, Vol. 62, No. 2, September, 1995, pp 164--176. (takes a parts-based approach to functionality). 2. L. Vaina and M. Jaulent, ``Object Structure and Action Requirements: A Compatibility Model for Functional Recognition'', IJIS(6), 1991, pp. 313-336. 3. P. Cooper L. Birnbaum and M. Brand, ``Causal Scene Understanding'', CVIU(62), No. 2, September 1995, pp. 215-231. (www.cs.toronto.edu/~sven/2523/Papers/brand.pdf) 4. A. Torralba, K. Murphy, W. Freeman, and M. Rubin, ``Context-based vision system for place and object recognition'', Proceedings, ICCV, 2003. (www.cs.toronto.edu/~sven/2523/Papers/torralba.pdf) 5. S. Kumar and M. Hebert, ``A Hierarchical Field Framework for Unified Context-Based Classification'', Proceedings, IEEE International Conference on Computer Vision (ICCV), 2005. (www.cs.toronto.edu/~sven/Papers/humar.pdf) Mar 18 Appearance-Based Recognition 1. H. Murase and S. Nayar, ``Visual Learning And Recognition Of 3-D Objects From Appearance'', IJCV(14), 1995, pp. 5-24. (www.cs.toronto.edu/~sven/2523/Papers/murase.pdf) 2. A. Leonardis and H. Bischof, ``Robust Recognition Using Eigenimages'', Computer Vision and Image Understanding: CVIU, Vol. 78, No. 1, pp 99--118, 2000. (www.cs.toronto.edu/~sven/2523/Papers/leonardis.pdf) Supplemental reading: 1. M. Turk and A. Pentland, ``Face recognition using eigenfaces'', Proc. IEEE Conference on Computer Vision and Pattern Recognition, Maui, Hawaii, 1991. (the paper that started a revolution in the recognition community toward appearance-based recognition) (www.cs.toronto.edu/~sven/2523/Papers/turk.pdf) 2. C. Huang, O. Camps, and T. Kanungo. ``Object Recognition Using Appearance-Based Parts and Relations'', Proceedings of the IEEE Computer Vision and Pattern Recognition Conference, pp. 877-883, San Juan, Puerto Rico, June 1997. (nice extension to appearance-based parts) (www.cs.toronto.edu/~sven/2523/Papers/camps.ps) 3. J. Midgley, ``Probabilistic Eigenspace Object Recognition in the Presence of Occlusion'', M.S. thesis, Department of Computer Science, University of Toronto, 2001. (http://www.cs.toronto.edu/~jmidgley/ut-thesis.ps.gz) Mar 25 Local Feature-Based Recognition 1. D. Lowe, ``Object recognition from local scale invariant features'', ICCV, 1999. (www.cs.toronto.edu/~sven/2523/Papers/sift.pdf) 2. F. Rothganger, Svetlana Lazebnik, Cordelia Schmid, Jean Ponce, ``Object modeling and recognition using local affine-invariant image descriptors and multi-view spatial contraints'', International Journal of Computer Vision, to appear, 2005. (www.cs.toronto.edu/~sven/2523/rothganger.pdf) Supplemental reading: C. Schmid and R. Mohr, ``Local Grayvalue Invariants for Image Retrieval'', PAMI(19), No. 5, May 1997, pp. 530-535. (also: ``Combining Grey Value Invariants with Local Constraints for Object Recognition'', CVPR96(872-877). (www.cs.toronto.edu/~sven/2523/Papers/schmid.ps) 2. G. Carneiro and A. Jepson, ``Phase-Based Local Features'', ECCV, 2002. (www.cs.toronto.edu/~sven/2523/Papers/carneiro.pdf) Apr 1 Expanding Feature Scope 1. Randal C. Nelson and Andrea Selinger, ``A Cubist Approach to Object Recognition'', International Conference on Computer Vision (ICCV98), Bombay, India, January 1998, 614-621. (www.cs.toronto.edu/~sven/2523/Papers/nelson.ps) 2. Serge Belongie, Jitendra Malik and Jan Puzicha, ``Shape Matching and Object Recognition Using Shape Contexts, PAMI, 24(4):509-522, April 2002. (www.cs.toronto.edu/~sven/2523/Papers/belongie.pdf) Supplemental reading: D. Huttenlocher, G. Klanderman, and W. Rucklidge, ``Comparing Images Using the Hausdorff Distance'', IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 15, no. 9, pp. 850-863, 1993. (http://www.cs.cornell.edu/~dph/papers\HKR-TPAMI-93.pdf) J. Beis and D. Lowe, ``Shape indexing using approximate nearest-neighbor search in highdimensional spaces'', In Proc. IEEE Conf. Comp. Vision Patt. Recog., pages 1000--1006, 1997. (citeseer.nj.nec.com/beis97shape.html) Apr 8 Graph Algorithms and Object Recognition 1. K. Siddiqi, A. Shokoufandeh, S. Dickinson, and S. Zucker, ``Shock Graphs and Shape Matching''. International Journal of Computer Vision, Volume 30, 1999, pp 1--24. (http://www.cs.toronto.edu/~sven/Papers/ijcv99.ps.gz) 2. Thomas B. Sebastian, Philip Klien, and Benjamin B. Kimia, ``Recognition of shapes by editing their shock graphs, PAMI, Volume 26, Number 5, May 2004, pp 550--571. (www.cs.toronto.edu/~sven/2523/Papers/kimia.pdf) Supplemental reading: 1. M. Pelillo, K. Siddiqi, and S. W. Zucker, ``Matching hierarchical structures using association graphs'', IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(11):1105-1120, 1999. (very nice transformation of a discrete optimization problem (max clique) into a continuous optimization problem) (http://www.dsi.unive.it/~pelillo/papers/pami99.pdf) 2. D. Macrini, A. Shokoufandeh, S. Dickinson, K. Siddiqi, and S. Zucker, ``View-Based 3-D Object Recognition using Shock Graphs'', Proceedings, International Conference on Pattern Recognition, Quebec, August, 2002. (http://www.cs.toronto.edu/~sven/Papers/icpr2002.ps.gz) 3. F. Demirci, A. Shokoufandeh, Y. Keselman, L. Bretzner, and S. Dickinson, ``Object Recognition as Many-to-Many Feature Matching'', International Journal of Computer Vision, 2006, to appear. (http://www.cs.toronto.edu/~sven/Papers/ijcv06.pdf) 4. Y. Keselman and S. Dickinson, ``Generic Model Abstraction from Examples'', IEEE Transactions on Pattern Analysis and Machine Intelligence, special issue on Syntactic and Structural pattern Recognition, Volume 27, Number 7, July 2005. (http://www.cs.toronto.edu/~sven/Papers/pami-abstraction.pdf) 5. A. Shokoufandeh, D. Macrini, S. Dickinson, K. Siddiqi, and S. Zucker,, ``Indexing Hierarchical Structures using Graph Spectra'', IEEE Transactions on Pattern Analysis and Machine Intelligence, special issue on Syntactic and Structural pattern Recognition, Volume 27, Number 7, July 2005. (http://www.cs.toronto.edu/~sven/Papers/pami-index.pdf)