This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Skeletal Shape Abstraction from Examples
May 2009 (vol. 31 no. 5)
pp. 944-952
M. Fatih Demirci, TOBB University of Economics and Technology, Ankara
Ali Shokoufandeh, Drexel University, Philadelphia
Sven J. Dickinson, University of Toronto, Toronto
Learning a class prototype from a set of exemplars is an important challenge facing researchers in object categorization. Although the problem is receiving growing interest, most approaches assume a one-to-one correspondence among local features, restricting their ability to learn true abstractions of a shape. In this paper, we present a new technique for learning an abstract shape prototype from a set of exemplars whose features are in many-to-many correspondence. Focusing on the domain of 2D shape, we represent a silhouette as a medial axis graph whose nodes correspond to "parts” defined by medial branches and whose edges connect adjacent parts. Given a pair of medial axis graphs, we establish a many-to-many correspondence between their nodes to find correspondences among articulating parts. Based on these correspondences, we recover the abstracted medial axis graph along with the positional and radial attributes associated with its nodes. We evaluate the abstracted prototypes in the context of a recognition task.

[1] R. Brooks, “Model-Based 3D Interpretations of 2D Images,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 5, no. 2, pp.140-150, 1983.
[2] R. Nevatia and T. Binford, “Description and Recognition of Curved Objects,” Artificial Intelligence, vol. 8, pp.77-98, 1977.
[3] R. Fergus, P. Perona, and A. Zisserman, “Object Class Recognition by Unsupervised Scale Invariant Learning,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp.264-271, June 2003.
[4] H. Blum, “A Transformation for Extracting New Descriptors of Shape,” Models for the Perception of Speech and Visual Form, W. Wathen-Dunn, ed., pp.362-380, MIT Press, 1967.
[5] N. Ueda and S. Suzuki, “Learning Visual Models from Shape Contours Using Multiscale Convex/Concave Structure Matching,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 4, pp.337-352, Apr. 1993.
[6] N. Duta, A. Jain, and M.P. Dubuisson-Jolly, “Learning 2D Shape Models,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp.8-14, June 1999.
[7] E. Chen and R. Parent, “Shape Averaging and Its Applications to Industrial Design,” IEEE Computer Graphics and Applications, vol. 9, no. 1, pp.47-54, Jan. 1989.
[8] P. Winston, “Learning Structural Descriptions from Examples,” The Psychology of Computer Vision, chap. 5, pp.157-209, McGraw-Hill, 1975.
[9] G. Ettinger, “Large Hierarchical Object Recognition Using Libraries of Parameterized Model Sub-Parts,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp.32-41, 1988.
[10] T.F. Cootes, C.J. Taylor, D.H. Cooper, and J. Graham, “Active Shape Models—Their Training and Application,” Computer Vision and Image Understanding, vol. 61, no. 1, pp.38-59, 1995.
[11] X. Jiang, A. Munger, and H. Bunke, “On Median Graphs: Properties, Algorithms, and Applications,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 10, pp.1144-1151, Oct. 2001.
[12] N. Burtnyk and M. Wein, “Interactive Skeleton Techniques for Enhancing Motion Dynamics in Key Frame Animation,” Comm. ACM, vol. 19, no. 10, pp.564-569, 1976.
[13] A. Mohan, C. Papageorgiou, and T. Poggio, “Example-Based Object Detection in Images by Components,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 4, pp.349-361, Apr. 2001.
[14] M. Weber, M. Welling, and P. Perona, “Unsupervised Learning of Models for Recognition,” Proc. Sixth European Conf. Computer Vision, vol. 1, pp.18-32, citeseer.nj.nec.comweber00unsupervised.html , 2000.
[15] L. Fei-Fei, R. Fergus, and P. Perona, “Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2004.
[16] B. Leibe and B. Schiele, “Analyzing Appearance and Contour Based Methods for Object Categorization,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2003.
[17] J. Winn and N. Jojic, “Locus: Learning Object Classes with Unsupervised Segmentation,” Proc. 10th IEEE Int'l Conf. Computer Vision, vol. 1, pp.756-763, 2005.
[18] B. Luo, R. Wilson, and E. Hancock, “Spectral Embedding of Graphs,” Pattern Recognition, vol. 36, no. 10, pp.2213-2230, 2003.
[19] Y. Keselman and S. Dickinson, “Generic Model Abstraction from Examples,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 7, pp.1141-1156, July 2005.
[20] A. Levinshtein, C. Sminchisescu, and S.J. Dickinson, “Learning Hierarchical Shape Models from Examples,” Proc. Int'l Workshop Energy Minimization Methods in Computer Vision and Pattern Recognition, pp.251-267, 2005.
[21] A. Torsello and E.R. Hancock, “Learning Shape-Classes Using a Mixture of Tree-Unions,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 6, pp.954-967, June 2006.
[22] S. Todorovic and N. Ahuja, “Unsupervised Category Modeling, Recognition, and Segmentation in Images,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 30, no. 12, pp. 2158-2174, Dec. 2008.
[23] M. Lozano and F. Escolano, “Protein Classification by Matching and Clustering Surface Graphs,” Pattern Recognition, vol. 39, no. 4, pp.539-551, 2006.
[24] B.B. Kimia, A.R. Tannenbaum, and S.W. Zucker, “Shapes, Shocks, and Deformations I: The Components of Two-Dimensional Shape and the Reaction-Diffusion Space,” Int'l J. Computer Vision, vol. 15, no. 3, pp.189-224, 1995.
[25] K. Siddiqi, S. Bouix, A. Tannenbaum, and S.W. Zucker, “Hamilton-Jacobi Skeletons,” Int'l J. Computer Vision, vol. 48, no. 3, pp.215-231, 2002.
[26] L.G. Shapiro and R.M. Haralick, “Structural Descriptions and Inexact Matching,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 3, pp.504-519, 1981.
[27] M. Pelillo, K. Siddiqi, and S. Zucker, “Matching Hierarchical Structures Using Association Graphs,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 11, pp.1105-1120, Nov. 1999.
[28] S. Gold and A. Rangarajan, “A Graduated Assignment Algorithm for Graph Matching,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 4, pp.377-388, Apr. 1996.
[29] K. Siddiqi, A. Shokoufandeh, S. Dickinson, and S. Zucker, “Shock Graphs and Shape Matching,” Int'l J. Computer Vision, vol. 30, pp.1-24, 1999.
[30] M.F. Demirci, A. Shokoufandeh, Y. Keselman, L. Bretzner, and S. Dickinson, “Object Recognition as Many-to-Many Feature Matching,” Int'l J. Computer Vision, vol. 69, no. 2, pp.203-222, 2006.
[31] R. Agarwala, V. Bafna, M. Farach, M. Paterson, and M. Thorup, “On the Approximability of Numerical Taxonomy (Fitting Distances by Tree Metrics),” SIAM J. Computing, vol. 28, no. 2, pp.1073-1085, 1999.
[32] J. Matoušek, “On Embedding Trees into Uniformly Convex Banach Spaces,” Israel J. Math., vol. 237, pp.221-237, 1999.
[33] Y. Rubner, C. Tomasi, and L.J. Guibas, “The Earth Mover's Distance as a Metric for Image Retrieval,” Int'l J. Computer Vision, vol. 40, no. 2, pp.99-121, 2000.
[34] J. August, K. Siddiqi, and S.W. Zucker, “Ligature Instabilities in the Perceptual Organization of Shape,” Computer Vision and Image Understanding, vol. 76, no. 3, pp.231-243, 1999.
[35] D. Macrini, K. Siddiqi, and S. Dickinson, “From Skeletons to Bone Graphs: Medial Abstraction for Object Recognition,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2008.
[36] E. Whittaker and G. Robinson, The Calculus of Observations: A Treatise on Numerical Mathematics, fourth ed. Dover, 1967.
[37] T. Sebastian, P.N. Klein, and B. Kimia, “Recognition of Shapes by Editing Their Shock Graphs,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 5, pp.550-571, May 2004.

Index Terms:
Shape abstraction, medial axis graphs, prototype learning, many-to-many graph matching.
Citation:
M. Fatih Demirci, Ali Shokoufandeh, Sven J. Dickinson, "Skeletal Shape Abstraction from Examples," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 5, pp. 944-952, May 2009, doi:10.1109/TPAMI.2008.267
Usage of this product signifies your acceptance of the Terms of Use.