Abstract
Shape abstraction is an important problem facing researchers in many fields such as pattern recognition, computer vision, and industrial design. Given a set of shapes, a recently developed shape abstraction framework generates an abstracted shape through the correspondences between their features. The correspondences are obtained based on the optimal solution of a well known transportation problem. Considering the case where multiple optimal solutions exist for one problem, this paper ranks all optimal solutions based on how much they preserve the local neighborhood relations and creates the abstracted shape using the solution with the highest rank. Experimental evaluation of the framework demonstrates that the proposed approach compares favorably with the previous shape abstraction technique.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ahuja, R.K., Magnanti, T.L., Orlin, J.B.: Network Flows: Theory, Algorithms, and Applications, pp. 4–7. Prentice Hall, Englewood Cliffs (1993)
Bajalinov, E.B.: Linear-Fractional Programming: Theory, Methods, Applications and Software. Kluwer Academic Publishers, Dordrecht (2003)
Blum, H.: Biological shape and visual science (part i). Journal of Theoretical Biology 38(2), 205–287 (1973)
Chen, E., Parent, R.: Shape averaging and its applications to industrial design. IEEE Computer Graphics and Applications 9(1), 47–54 (1989)
Christofides, N., Valls, V.: Finding all optimal solutions to the network flow problem. Mathematical Programming Studies 26, 209–212 (1986)
Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models their training and application. Computer Vision and Image Understanding 61(1), 38–59 (1995)
Demirci, F., Shokoufandeh, A., Dickinson, S.: Skeletal shape abstraction from examples. IEEE Transactions on Pattern Analysis and Machine Intelligence 31(5), 944–952 (2009)
Demirci, F., Shokoufandeh, A., Keselman, Y., Bretzner, L., Dickinson, S.: Object recognition as many-to-many feature matching. International Journal of Computer Vision 69(2), 203–222 (2006)
Dickinson, S.: The Evolution of Object Categorization and the Challenge of Image Abstraction, pp. 1–37. Cambridge University Press, Cambridge (2009)
Gupta, A.: Embedding tree metrics into low-dimensional euclidean spaces. Discrete & Computational Geometry 24(1), 105–116 (2000)
Hillier, F., Lieberman, G.: Introduction to mathematical programming. McGraw-Hill, New York (1990)
Jiang, X., Munger, A., Bunke, H.: On median graphs: properties, algorithms, and applications. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(10) (2001)
Levinshtein, A., Sminchisescu, C., Dickinson, S.: Learning hierarchical shape models from examples. In: Proceedings, International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition, pp. 251–267 (2005)
Rubner, Y., Tomasi, C., Guibas, L.J.: The earth mover’s distance as a metric for image retrieval. International Journal of Computer Vision 40(2), 99–121 (2000)
Siddiqi, K., Shokoufandeh, A., Dickinson, S., Zucker, S.: Shock graphs and shape matching. International Journal of Computer Vision 35(1), 13–32 (1999)
Winston, P., Binford, T., Katz, B., Lowry, M.: Learning physical description from functional descriptions, examples, and precedents. In: Proceedings, AAAI, Palo Alto, CA, pp. 433–439 (August 1983)
Zhu, S.-C., Mumford, D.: A stochastic grammar of images. Foundations and Trends in Computer Graphics and Vision 2, 259–362 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Akimaliev, M., Demirci, M.F. (2011). Shape Abstraction through Multiple Optimal Solutions. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2011. Lecture Notes in Computer Science, vol 6939. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24031-7_59
Download citation
DOI: https://doi.org/10.1007/978-3-642-24031-7_59
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24030-0
Online ISBN: 978-3-642-24031-7
eBook Packages: Computer ScienceComputer Science (R0)