Abstract
Object recognition systems have their roots in the AI community, and originally addressed the problem of object categorization. These early systems, however, were limited by their inability to bridge the representational gap between low-level image features and high-level object models, hindered by the assumption of one-to-one correspondence between image and model features. Over the next thirty years, the mainstream recognition community moved steadily in the direction of exemplar recognition while narrowing the representational gap. The community is now returning to the categorization problem, and faces the same representational gap as its predecessors did. We review the evolution of object recognition systems and argue that bridging this representational gap requires an ability to match image and model features many-to-many. We review three formulations of the many-to-many matching problem as applied to model acquisition and object recognition.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Cohen, S.D., Guibas, L.J.: The earth mover’s distance under transformation sets. In: Proceedings, 7th ICCV, Kerkyra, Greece (1999)
Demirci, M., Shokoufandeh, A., Dickinson, S., Keselman, Y., Bretzner, L.: Many-to-many feature matching using spherical coding of directed graphs. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 322–335. Springer, Heidelberg (2004)
Keselman, Y., Dickinson, S.: Generic model abstraction from examples. IEEE PAMI 27(7) (2005)
Keselman, Y., Shokoufandeh, A., Demirci, M., Dickinson, S.: Many-to-many graph matching via metric embedding. In: Proceedings, IEEE CVPR, Madison, WI (2003)
Macrini, D., Shokoufandeh, A., Dickinson, S., Siddiqi, K., Zucker, S.: View-based 3-D object recognition using shock graphs. In: Proceedings, Internal Conference on Pattern Recognition, Quebec City, August 2002, pp. 24–28 (2002)
Shokoufandeh, A., Dickinson, S., Jönsson, C., Bretzner, L., Lindeberg, T.: The representation and matching of qualitative shape at multiple scales. In: Proceedings, ECCV 2002, Copenhagen, pp. 759–772 (2002)
Shokoufandeh, A., Macrini, D., Dickinson, S., Siddiqi, K., Zucker, S.: Indexing hierarchical structures using graph spectra. IEEE PAMI 27(7) (2005)
Siddiqi, K., Shokoufandeh, A., Dickinson, S., Zucker, S.: Shock graphs and shape matching. International Journal of Computer Vision 30, 1–24 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dickinson, S., Shokoufandeh, A., Keselman, Y., Demirci, F., Macrini, D. (2005). Object Categorization and the Need for Many-to-Many Matching. In: Kropatsch, W.G., Sablatnig, R., Hanbury, A. (eds) Pattern Recognition. DAGM 2005. Lecture Notes in Computer Science, vol 3663. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550518_62
Download citation
DOI: https://doi.org/10.1007/11550518_62
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28703-2
Online ISBN: 978-3-540-31942-9
eBook Packages: Computer ScienceComputer Science (R0)