CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2009 vol.31 Issue No.05 - May

Subscribe

Issue No.05 - May (2009 vol.31)

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

ABSTRACT

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.

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 & Machine Intelligence*, vol.31, no. 5, pp. 944-952, May 2009, doi:10.1109/TPAMI.2008.267REFERENCES

- [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.- [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.- [8] P. Winston, “Learning Structural Descriptions from Examples,”
The Psychology of Computer Vision, chap. 5, pp.157-209, McGraw-Hill, 1975.- [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.- [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.- [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.- [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.- [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.- [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.- [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. |