Abstract
This paper describes a view-based method for recognizing 3D objects from 2D images. We employ an aspect-graph structure, where the aspects are not based on the singularities of visual mapping but are instead formed using a notion of shape similarity between views. Specifically, the viewing sphere is endowed with a metric of dis-similarity for each pair of views and the problem of aspect generation is viewed as a “segmentation” of the viewing sphere into homogeneous regions. The viewing sphere is sampled at regular (5 degree) intervals and the similarity metric is used in an iterative procedure to combine views into aspects with a prototype representing each aspect. This is done in a “region-growing” regime which stands in contrast to the usual “edge detection” styles to computing the aspect graph. The aspect growth is constrained such that two aspects of an object remain distinct under the given similarity metric. Once the database of 3D objects is organized as a set of aspects, and prototypes for these aspects for each object, unknown views of database objects are compared with the prototypes and the results are ordered by similarity. We use two similarity metrics for shape, one based on curve matching and the other based on matching shock graphs, which for a database of 64 objects and unknown views of objects from the database give a recall rate of (90.3%, 74.2%, 59.7%) and (95.2%, 69.0%, 57.5%), respectively, for the top three matches; cumulative recall rate based on the top three matches is 98% and 100%, respectively. The result of indexing unknown views of objects not in the database also produce intuitive matches. We also develop a hierarchical indexing scheme to prune unlikely objects at an early stage to improve the efficiency of indexing, resulting in savings of 35% at the top level and of 55% at the next level, cumulatively.
Similar content being viewed by others
References
Adams, R. and Bischoff, L. 1994. Seeded region growing. PAMI, 16(6):641–647.
Anonymous, 2001. Eighth International Conference on Computer Vision, July 9–12, 2001, IEEE Computer Society Press: Vancouver, Canada.
Arcelli, C., Cordella, L., and di Baja, G.S. (Eds.). 2001. In Proceedings of the International Workshop on Visual Form, Springer: Capri, Italy.
Bajcsy, R. and Solina, F. 1987. Three dimensional object representation revisited. In ICCV87, pp. 231–240.
Barr, A. 1981. Superquadrics and angle-preserving transformations. IEEE CGA, 1(1):11–23.
Basri, R. and Ullman, S. 1988. The alignment of objects with smooth surfaces. In ICCV88, pp. 482–488.
Bellaire, G. 1993. Feature-based computation of hierarchical aspectgraphs. Machine GRAPHICS and VISION, 2(2):105–122.
Besl, P. and Jain, R. 1985. Three-dimensional object recognition. ACM Computing Surveys, 17(1):75–145.
Biederman, I. 1987. Recognition by components. Psych. Review, 94:115–147.
Bowyer, K. and Dyer, C. 1990. Aspect graphs: An introduction and survey of recent results. IJIST, 2:315–328.
Burns, J. and Kitchen, L. 1987. Recognition in 2D images of 3D objects from large model bases using prediction hierarchies. In IJCAI87, pp. 763–766.
Carlsson, S. and Weinshall, D. 1998. Dual computation of projective shape and camera positions from multiple images. IJCV, 27(3):227–241.
Chien, C. and Aggarwal, J. 1989. Model construction and shape recognition from occluding contours. PAMI, 11(4):372–389.
Cyr, C.M. and Kimia, B.B. 2001. 3D object recognition using shape similarity-based aspect graph. In ICCV2001, Eighth International Conference on Computer Vision, July 9–12, 2001, IEEE Computer Society Press: Vancouver, Canada, pp. 254–261.
Dickinson, S., Pentland, A., and Rosenfeld, A. 1992. 3D shape recovery using distributed aspect matching. PAMI, 14(2):174–198.
Eggert, D. and Bowyer, K. 1993. Computing the perspective projection aspect graph of solids of revolution. PAMI, 15(2):109–128.
Eggert, D., Bowyer, K., Dyer, C., Christensen, H., and Goldgof, D. 1993. The scale space aspect graph. PAMI, 15(11):1114–1130.
Fan, T., Medioni, G., and Nevatia, R. 1989. Recognizing 3D objects using surface descriptions. PAMI, 11(11):1140–1157.
Flynn, P. and Jain, A. 1991. BONSAI: 3D object recognition using constrained search. PAMI, 13(10):1066–1075.
Gigus, Z., Canny, J., and Seidel, R. 1991. Efficiently computing and representing aspect graphs of polyhedral objects. PAMI, 13(6):542–551.
Halliman, P.L., Gordon, G.G., Yuille, A.L., Giblin, P., and Mumford, D. 1999. In Two-and Three-Dimensional Patterns of the Face, A.K. Peters (Ed.)
Huttenlocher, D. and Ullman, S. 1990. Recognizing solid objects by alignment with an image. IJCV, 5(2):195–212.
Ikeuchi, K. and Kanade, T. 1988. Automatic generation of object recognition programs. PIEEE, 76(8):1016–1035.
Keren, D., Cooper, D.B., and Subrahmonia, J. 1994. Describing complicated objects by implicit polynomials. PAMI, 16(1):38–53.
Kirby, M. and Sirovich, L. 1990. Application of the kahunen-loeve procedure for the characterization of human faces. PAMI, 1:103–108.
Klein, P., Sebastian, T., and Kimia, B. 2001. Shape matching using edit-distance: An implementation. In Twelfth Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), Washington, D.C., pp. 781–790.
Koenderink, J.J. and van Doorn, A.J. 1976. The singularilarities of the visual mapping. Biol. Cyber., 24:51–59.
Koenderink, J.J. and van Doorn, A.J. 1979. The internal representation of solid shape with respect to vision. Biol. Cyber., 32:211–216.
Kriegman, D. and Ponce, J. 1990. Computing exact aspect graphs of curved objects: Solids of revolution. IJCV, 5(2):119–135.
Leymarie, F. and Kimia, B.B. 2001. The shock scaffold for representing 3D shapes. In Proceedings of the International Workshop on Visual Form, Springer: Capri, Italy, pp. 216–228.
Nayar, S., Rene, S., and Murase, H. 1996. Realtime 100 object recognition system. In Proceedings 1996 IEEE International Conference on Robotics and Automation, pp. 2321–2325.
Petitjean, S., Ponce, J., and Kriegman, D. 1992. Computing exact aspect graphs of curved objects:algebraic surfaces. IJCV, 9(3):231–255.
Pope, A. and Lowe, D. 1993. Learning object recognition models from images. In ICCV93, pp. 296–301.
Rosch, E. 1978. Principles of Categorization. Cognition and Categorization. Erlbaum Hillsdale, NJ.
Seales, W. and Dyer, C. 1992. Viewpoint from occluding contour. CVGIP, 55(2 March):198–211.
Sebastian, T., Klein, P., and Kimia, B. 2003. On aligning curves. PAMI, 25(1):116–125.
Sebastian, T.B., Crisco, J.J., Klein, P.N., and Kimia, B.B. 2000. Constructing 2D curve atlases. In Proceedings of Mathematical Methods in Biomedical Image Analysis, pp. 70–77.
Sebastian, T.B. and Kimia, B.B. 2001. Curves vs. skeletons in object recognition. In Proceedings of the IEEE International Conference on Image Processing, IEEE Computer Society Press: Thessaloniki, Greece, pp. 22–25.
Sebastian, T.B., Klein, P.N., and Kimia, B.B. 2001a. Alignment-based recognition of shape outlines. In Proceedings of the InternationalWorkshop on Visual Form, Springer: Capri, Italy, pp. 606–618.
Sebastian, T.B., Klein, P.N., and Kimia, B.B. 2001b. Recognition of shapes by editing shock graphs. In ICCV2001 Eighth International Conference on Computer Vision, July 9–12, 2001, IEEE Computer Society Press: Vancouver, Canada. pp. 755–762.
Sebastian, T.B., Klein, P.N., and Kimia, B.B. 2002. Shock-based indexing into large shape databases. In Seventh European Conference on Computer Vision, Springer Verlag: Copenhagen, Denmark, p. Part III:731–746.
Sebastian, T.B., Klein, P.N., and Kimia, B.B. 2004. Recognition of shapes by editing their shock graphs. PAMI, in press.
Shimshoni, I. and Ponce, J. 1997. Finite-resolution aspect graphs of polyhedral objects. PAMI, 19(4):315–327.
Shokoufandeh, A., Marsic, I., and Dickinson, S. 1999. View-based object recognition using saliency maps. IVC, 17(5/6):445–460.
Sripradisvarakul, T. and Jain, R. 1989. Generating aspect graphs for curved objects. In 3DWS89, pp. 109–115.
Stewman, J. and Bowyer, K. 1988. Creating the perspective projection aspect graph of polyhedral objects. 9:494–500.
Stone, J. 1999. Object recognition: View-specificity and motion-specificity. Vision Research, 39:4032–4044.
Tarr, M. and Kriegman, D. 2001. What defines a view? Vision Research, 41:1981–2004.
Turk, M. and Pentland, A. 1990. Eigenfaces for recognition. Journal of Cognitive Neuroscience.
Weinshall, D. and Werman, M. 1997. On view likelihood and stability. PAMI, 19(2):97–108.
Weishall, D. 1993. Model-based invariants for 3-D vision. The International Journal of Computer Vision, 10(1):27–42.
Weiss, I. and Ray, M. 2001. Model-based recognition of 3D objects from single images. PAMI, 23(2):116–128.
Wilkes, D. and Tsotsos, J. 1993. Active object recognition. In CVPR92, pp. 136–141.
Wong, A., Lu, S., and Rioux, M. 1989. Recognition and shape synthesis of 3D objects image based on attributed hypergraphs. PAMI, 11(3):279–290.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Cyr, C.M., Kimia, B.B. A Similarity-Based Aspect-Graph Approach to 3D Object Recognition. International Journal of Computer Vision 57, 5–22 (2004). https://doi.org/10.1023/B:VISI.0000013088.59081.4c
Issue Date:
DOI: https://doi.org/10.1023/B:VISI.0000013088.59081.4c