This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Shape Representation and Classification Using the Poisson Equation
December 2006 (vol. 28 no. 12)
pp. 1991-2005
Eitan Sharon, IEEE Computer Society
Ronen Basri, IEEE Computer Society
We present a novel approach that allows us to reliably compute many useful properties of a silhouette. Our approach assigns, for every internal point of the silhouette, a value reflecting the mean time required for a random walk beginning at the point to hit the boundaries. This function can be computed by solving Poisson's equation, with the silhouette contours providing boundary conditions. We show how this function can be used to reliably extract various shape properties including part structure and rough skeleton, local orientation and aspect ratio of different parts, and convex and concave sections of the boundaries. In addition to this, we discuss properties of the solution and show how to efficiently compute this solution using multigrid algorithms. We demonstrate the utility of the extracted properties by using them for shape classification and retrieval.

[1] S. Agarwal and D. Roth, “Learning a Sparse Representation for Object Detection,” Proc. European Conf. Computer Vision, vol. 2, pp.113-130, 2002.
[2] Y. Amit and D. Geman, “Shape Quantization and Recognition with Randomized Trees,” Neural Computation, vol. 9, no. 7, pp.1545-1588, 1997.
[3] J. August and S.W. Zucker, “Sketches with Curvature: The Curve Indicator Random Field and Markov Processes,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 4, pp. 387-400, Apr. 2003.
[4] R. Basri, L. Costa, D. Geiger, and D. Jacobs, “Determining the Similarity of Deformable Shapes,” Vision Research, vol. 38, pp.2365-2385, 1998.
[5] S. Belongie, J. Malik, and J. Puzicha, “Shape Matching and Object Recognition Using Shape Contexts,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 4, pp. 509-522, Apr. 2002.
[6] I. Biederman, “Human Image Understanding: Recent Research and a Theory,” Computer Graphics, Vision, Image Processing, vol. 32, pp. 29-73, 1985.
[7] M. Blank, L. Gorelick, E. Shechtman, M. Irani, and R. Basri, “Actions as Space-Time Shapes,” Proc. IEEE Int'l Conf. Computer Vision, 2005.
[8] H. Blum, “A Transformation for Extracting New Descriptors of Shape,” Proc. Symp. Models for the Perception of Speech and Visual Form, pp. 362-380, 1967.
[9] M. Bober, “MPEG-7 Visual Shape Descriptors,” IEEE Trans. Circuits and Systems for Video Technology, vol. 1, no. 6, 2001.
[10] E. Borenstein, E. Sharon, and S. Ullman, “Combining Top-Down and Bottom-Up Segmentation,” Proc. IEEE Workshop Perceptual Organization in Computer Vision, 2004.
[11] A. Brandt, “Interior Estimates for Second Order Elliptic Differential (or Finite-Difference) Equations via the Maximum Principle,” Israel J. Math., vol. 7, pp. 95-121, 1969.
[12] A. Brandt, “Multi-Level Adaptive Solutions to Boundary Value Problems,” Math. Computation, vol. 31, pp. 333-390, 1977.
[13] W.L. Briggs, V.E. Henson, and S.F. McCormick, A Multigrid Tutorial, second ed. SIAM, 2000.
[14] S. Carlsson, “Order Structure, Correspondence and Shape Based Categories,” Proc. Int'l Workshop Shape, Contour and Grouping, p.1681, 1999.
[15] D. Decoste and B. Schölkopf, “Training Invariant Support Vector Machines,” Machine Learning, vol. 46, no. 1-3, pp. 161-190, 2002.
[16] A. Douglis and L. Nirenberg, “Interior Estimates for Elliptic System of P.D.E,” Comm. Pure Applied Math., vol. 8, pp. 503-538, 1955.
[17] A. Duci, A.J. Yezzi, S.K. Mitter, and S. Soatto, “Shape Representation via Harmonic Embedding,” Proc. IEEE Int'l Conf. Computer Vision, pp. 656-662, 2003.
[18] R.O. Duda and P.E. Hart, Pattern Classification and Scene Analysis, first ed. Wiley, 1973,
[19] Introduction to MPEG-7: Multimedia Content Description Interface, B.S. Manjunath, P. Salembier, and T. Sikora, eds. Wiley, 2002.
[20] M. Elad, A. Tal, and S. Ar, “Content Based Retrieval of VRML Objects—An Iterative and Interactive Approach,” Proc. Sixth Eurographics Workshop Multimedia, pp. 97-108, 2001.
[21] 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. 264-274, 2003.
[22] M. Frenkel and R. Basri, “Curve Matching Using the Fast Matching Method,” Energy Minimization Methods in Computer Vision and Pattern Recognition, pp. 35-51, 2003.
[23] Y. Gdalyahu and D. Weinshall, “Flexible Syntactic Matching of Curves and Its Application to Automatic Hierarchical Classification of Silhouettes,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 12, p. 1999, Dec. 1999.
[24] D. Geiger, K. Kumaran, and L. Parida, “A Computational View of Visual Organization for Figure/Ground Separation,” Proc. EEE Conf. Computer Vision and Pattern Recognition, pp. 155-160, 1996.
[25] M. Giudici, F. Queirolo, and M. Valle, “Evaluation of Gradient Descent Learning Algorithms with Adaptive and Local Rate for Hand-Written Numerals,” Proc. European Symp. Artificial Neural Networks, pp. 289-294, 2002.
[26] L. Gorelick, M. Galun, E. Sharon, A. Brandt, and R. Basri, “Shape Representation and Classification Using the Poisson Equation,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp.61-67, 2004.
[27] P. Grother, NIST Special Database 19, Handprinted Forms and Characters Database, http://www.nist.gov/srdnistsd19.htm, 1995.
[28] D. Keysers, The USPS Database of Handwritten Digits. http://www_i6.informatik.rwth_aachen.de/ keysersusps.html, 2004.
[29] D. Keysers, C. Gollan, and H. Ney, “Local Context in Non-Linear Deformation Models for Handwritten Character Recognition,” Proc. Int'l Conf. Pattern Recognition, vol. 4, pp. 511-514, 2004.
[30] W.-Y. Kim and Y.-S. Kim, “A New Region-Based Shape Descriptor,” ISO/IEC MPEG99/M5472, 1999.
[31] E. Klassen, A. Srivastava, W. Mio, and S. Joshi, “Analysis of Planar Shapes Using Geodesic Paths on Shape Spaces,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 3, Mar. 2004.
[32] S.H. Lai and B.C. Vemuri, “An O(N) Iterative Solution to the Poisson Equation in Low-Level Vision Problems,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 9-14, 1994.
[33] Y. LeCun, “The MNIST Database of Handwritten Digits,” http://yann.lecun.com/exdb/mnistindex.html , 1998.
[34] Y. LeCun, L. Botou, L. Jackel, H. Drucker, C. Cortes, J. Denker, I. Guyon, U. Muller, E. Sackinger, P. Simard, and V. Vapnik, “Learning Algorithms for Classification: A Comparison on Handwritten Digit Recognition,” Neural Networks, pp. 261-276, 1995.
[35] B. Leibe, A. Leonardis, and B. Schiele, “Combined Object Categorization and Segmentation with an Implicit Shape Model,” Proc. European Conf. Computer Vision '04 Workshop Statistical Learning in Computer Vision, pp.17-32, May 2004.
[36] J. Li and A. Hero, “A Spectral Method for Solving Elliptic Equations for Surface Reconstruction and 3D Active Contours,” Proc. IEEE Int'l Conf. Image Processing, vol. III, pp. 1067-1070, 2001.
[37] C. Lin and R. Chellappa, “Classification of Partial 2-D Shapes Using Fourier Descriptors,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 5, pp. 686-690, 1987.
[38] M. Maila and J. Shi, “A Random Walks View of Spectral Segmentation,” AI and STATISTICS, 2001.
[39] D. Marr and H. K. Nishihara, “Representation and Recognition of the Spatial Organization of Three-Dimensional Shapes,” Proc. Royal Soc., London, vol. B200, pp. 269-294, 1978.
[40] K. Mokhtarian and M. Bober, Curvature Scale Space Representation: Theory, Applications and MPEG-7 Standardisation. Kluwer Academic (now Springer), 2003.
[41] “The MPEG-7 XM software repository,” http://www.lis.ei. tum.de/research/bv/topics/ mmdbe_mpeg7.html, 2005.
[42] D. Mumford, Elastica and Computer Vision, Algebraic Geometry and Its Applications, Chandrajit Bajaj, ed., pp. 491-506. Springer Verlag, 1994.
[43] Geometric Level Set Methods in Imaging, Vision, and Graphics, S.Osher and N. Paragios, eds. Springer, 2003.
[44] A.P. Pentland, “Recognition by Parts,” Proc. IEEE Int'l Conf. Computer Vision, pp. 612-620, 1987.
[45] P. Perez, M. Gangnet, and A. Blake, “Poisson Image Editing,” ACM Trans. Graphics, vol. 22, no. 3, pp. 313-318, 2003.
[46] T.B. Sebastian, P.N. Klein, and B.B. Kimia, “Shock-Based Indexing into Large Shape Databases,” Proc. European Conf. Computer Vision, vol. 3, pp. 731-746, 2002.
[47] T.B. Sebastian, P. Klien, and B.B. Kimia, “On Aligning Curves,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 1, pp. 116-125, Jan. 2003.
[48] E. Sharon and D. Mumford, “2D-Shape Analysis Using Conformal Mapping,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 350-357, 2004.
[49] K. Siddiqi and B. Kimia, “Parts of Visual Form: Computational Aspects,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 3, pp. 239-251, Mar. 1995.
[50] K. Siddiqi, A. Shokoufandeh, S.J. Dickinson, and S.W. Zucker, “Shock Graphs and Shape Matching,” Proc. IEEE Int'l Conf. Computer Vision, p. 222, 1998.
[51] P.Y. Simard, D. Steinkraus, and J. Platt, “Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis,” Proc. Int'l Conf. Document Analysis and Recognition, pp.958-962, 2003.
[52] T. Simchony, R. Chellappa, and M. Shao, “Direct Analytical Methods for Solving Poisson Equations in Computer Vision Problems,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 5, pp. 435-446, May 1990.
[53] U. Trottenberg, C. Oosterlee, and A. Schuller, Multigrid. Academic Press, 2001.
[54] S. Ullman, E. Sali, and M. Vidal-Naquet, “A Fragment-Based Approach to Object Representation and Classification,” Proc. Fourth Int'l Workshop Visual Form (IWVF4), 2001.
[55] L.R. Williams and D.W. Jacobs, “Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience,” Neural Computation, vol. 9, no. 4, pp. 837-858, 1997.
[56] D. Zhang and G. Lu, “Evaluation of MPEG-7 Shape Descriptors against Other Shape Descriptors,” Multimedia Systems, vol. 9, no. 1, pp. 15-30, 2003.
[57] M. Zuliani, C.S. Kenney, S. Bhagavathy, and B.S. Manjunath, “Drums and Curve Descriptors, ” Proc. British Machine Vision Conf., Sept. 2004.

Index Terms:
Computer vision, shape, Poisson equation, silhouette classification.
Citation:
Lena Gorelick, Meirav Galun, Eitan Sharon, Ronen Basri, Achi Brandt, "Shape Representation and Classification Using the Poisson Equation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 12, pp. 1991-2005, Dec. 2006, doi:10.1109/TPAMI.2006.253
Usage of this product signifies your acceptance of the Terms of Use.