CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2013 vol.35 Issue No.10 - Oct.

Subscribe

Issue No.10 - Oct. (2013 vol.35)

pp: 2546-2552

Zhou Ren , Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore, Singapore

Junsong Yuan , Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore, Singapore

Wenyu Liu , Huazhong Univ. of Sci. & Technol., Wuhan, China

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2013.67

ABSTRACT

Shape decomposition is a fundamental problem for part-based shape representation. We propose the minimum near-convex decomposition (MNCD) to decompose arbitrary shapes into minimum number of "near-convex" parts. The near-convex shape decomposition is formulated as a discrete optimization problem by minimizing the number of nonintersecting cuts. Two perception rules are imposed as constraints into our objective function to improve the visual naturalness of the decomposition. With the degree of near-convexity a user-specified parameter, our decomposition is robust to local distortions and shape deformation. The optimization can be efficiently solved via binary integer linear programming. Both theoretical analysis and experiment results show that our approach outperforms the state-of-the-art results without introducing redundant parts and thus leads to robust shape representation.

INDEX TERMS

Shape, Visualization, Robustness, Integer linear programming, Linear programming, Optimization, Time complexity,discrete optimization, Shape decomposition, shape representation

CITATION

Zhou Ren, Junsong Yuan, Wenyu Liu, "Minimum Near-Convex Shape Decomposition",

*IEEE Transactions on Pattern Analysis & Machine Intelligence*, vol.35, no. 10, pp. 2546-2552, Oct. 2013, doi:10.1109/TPAMI.2013.67REFERENCES

- [1] Z. Ren, J. Yuan, C. Li, and W. Liu, "Minimum Near-Convex Decomposition for Robust Shape Representation,"
Proc. IEEE Int'l Conf. Computer Vision, pp. 303-310, 2011.- [2] K. Siddiqi, K. Tresness, and B.B. Kimia, "Parts of Visual Form: Psychophysical Aspects,"
Perception, vol. 25, pp. 399-424, 1996.- [3] I. Biederman, "Recognition-by-Components: A Theory of Human Image Understanding,"
Psychological Rev., vol. 94, pp. 115-147, 1987.- [4] M. Singh and D.D. Hoffman, "Part-Based Representations of Visual Shape and Implications for Visual Cognition,"
Advances in Psychology, vol. 130, pp. 401-459, 2001.- [5] T.A. Cass, "Robust Affine Structure Matching for 3D Object Recognition,"
IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 11, pp. 1265-1274, Nov. 1998.- [6] G. Lu and A. Sajjanhar, "Region-Based Shape Representation and Similarity Measure Suitable for Content-Based Image Retrieval,"
Multimeida Systems, vol. 7, pp. 165-174, 1999.- [7] J.-M. Lien and N. Amato, "Approximate Convex Decomposition of Polygons,"
Computational Geometry, vol. 35, pp. 100-123, 2006.- [8] H. Liu, L.J. Latecki, and W. Liu, "Convex Shape Decomposition,"
Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 104-124, 2010.- [9] J.M. Keil and J. Snoeyink, "On the Time Bound for Convex Decomposition of Simple Polygons,"
Int'l J. Computational Geometry and Application, vol. 12, pp. 181-192, 2002.- [10] J.M. Keil and J. Snoeyink,
Minimum Convex Decomposition, www.cs.ubc.ca/~snoeyink/demosconvdecomp, 2007.- [11] J.-M. Lien and N. Amato, "Approximate Convex Decomposition of Polyhedra,"
Proc. ACM Symp. Solid and Physical Modeling, pp. 121-131, 2007.- [12] D.D. Hoffman and M. Singh, "Salience of Visual Parts,"
Cognition, vol. 14, pp. 29-78, 1997.- [13] M. Singh, G. Seyranian, and D.D. Hoffman, "Parsing Silhouettes: The Short-Cut Rule,"
Perception and Psychophysics, vol. 61, pp. 636-660, 1999.- [14] Z. Ren, J. Yuan, and Z. Zhang, "Robust Hand Gesture Recognition Based on Finger-Earth Mover's Distance with a Commodity Depth Camera,"
Proc. ACM Int'l Conf. MultiMedia, pp. 1093-1096, 2011.- [15] Z. Ren, J. Yuan, J. Meng, and Z. Zhang, "Robust Part-Based Hand Gesture Recognition Using Kinect Sensor,"
IEEE Trans. Multimedia, in press, 2013.- [16] D. Macrini, S. Dickinson, D. Fleet, and K. Siddiqi, "Bone Graphs: Medial Shape Parsing and Abstraction,"
Computer Vision and Image Understanding, vol. 35, pp. 1044-1061, 2011.- [17] D. Macrini, C. Whiten, R. Laganiere, and M. Greenspan, "Probabilistic Shape Parsing for View-Based Object Recognition,"
Proc. Int'l Conf. Pattern Recognition, pp. 2302-2305, 2012.- [18] E. Zuckerberger, A. Tal, and S. Shlafman, "Polyhydral Surface Decomposition with Applications,"
Computers and Graphics, vol. 26, pp. 733-743, 2002.- [19] M. Singh and D.D. Hoffman, "Completing Visual Contours: The Relationship between Relatability and Minimizing Inflections,"
Perception and Psychophysics, vol. 61, pp. 943-951, 1999.- [20] S. Katz and A. Tal, "Hierarchical Mesh Decomposition Using Fuzzing Clustering and Cuts,"
ACM Trans. Graphics, vol. 2, pp. 954-961, 2003.- [21] F. Aurenhammer, "Weighted Skeletons and Fixed-Share Decomposition,"
Computational Geometry, vol. 40, no. 2, pp. 93-101, 2008.- [22] M. Tanase and R.C. Veltkamp, "Polygon Decomposition Based on the Straight Line Skeleton,"
Proc. Symp. Computational Geometry, pp. 58-67, 2003.- [23] J.-M. Lien, "Hybrid Motion Planning Using Minkowski Sums,"
Proc. Robotics: Science and Systems Conf., 2008.- [24] J.-M. Lien and Y. Lu, "Planning Motion in Similar Environments,"
Proc. Robotics: Science and System Conf., 2009.- [25] L.J. Latecki, R. Lakamper, and U. Eckhardt, "Shape Descriptors for Non-Rigid Shapes with a Single Closed Contour,"
Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 424-429, 2000.- [26] X. Bai, W. Liu, and Z. Tu, "Integrating Contour and Skeleton for Shape Classification,"
Proc. IEEE Workshop NORDIA, 2009.- [27] X. Mi and D. Decarlo, "Separating Parts from 2D Shapes Using Relatability,"
Proc. IEEE Int'l Conf. Computer Vision, pp. 1-8, 2007.- [28] Z. Ren, J. Meng, J. Yuan, and Z. Zhang, "Robust Hand Gesture Recognition with Kinect Sensor,"
Proc. ACM Int'l Conf. Multimedia, pp. 759-760, 2011. |