Shape representation and classification using the Poisson equation

Silhouettes contain rich information about the shape of objects that can be used for recognition and classification. 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 multi-grid algorithms. We demonstrate the utility of the extracted properties by using them for shape classification.

[1]  Louis Nirenberg,et al.  Interior estimates for elliptic systems of partial differential equations , 1955 .

[2]  Achi Brandt,et al.  Interior estimates for second-order elliptic differential (or finite-difference) equations via the maximum principle , 1969 .

[3]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[4]  D. Brandt,et al.  Multi-level adaptive solutions to boundary-value problems math comptr , 1977 .

[5]  D. Marr,et al.  Representation and recognition of the spatial organization of three-dimensional shapes , 1978, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[6]  I. Biederman.  Human image understanding: Recent research and a theory , 1985, Computer Vision Graphics and Image Processing.

[7]  Rama Chellappa,et al.  Classification of Partial 2-D Shapes Using Fourier Descriptors , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  A. Pentland.  Recognition by Parts , 1987 .

[9]  William L. Briggs,et al.  A multigrid tutorial , 1987 .

[10]  Rama Chellappa,et al.  Direct Analytical Methods for Solving Poisson Equations in Computer Vision Problems , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Shang-Hong Lai,et al.  An O(N) iterative solution to the Poisson equation in low-level vision problems , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[12]  D. Mumford.  Elastica and Computer Vision , 1994 .

[13]  Patrick J. Grother,et al.  NIST Special Database 19 Handprinted Forms and Characters Database , 1995 .

[14]  Lance R. Williams,et al.  Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience , 1995, Neural Computation.

[15]  Kaleem Siddiqi,et al.  Parts of Visual Form: Computational Aspects , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Harris Drucker,et al.  Learning algorithms for classification: A comparison on handwritten digit recognition , 1995 .

[17]  Laxmi Parida,et al.  Visual organization for figure/ground separation , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  Yali Amit,et al.  Shape Quantization and Recognition with Randomized Trees , 1997, Neural Computation.

[19]  Ronen Basri,et al.  Determining the similarity of deformable shapes , 1998, Vision Research.

[20]  Daphna Weinshall,et al.  Flexible Syntactic Matching of Curves and Its Application to Automatic Hierarchical Classification of Silhouettes , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Stefan Carlsson,et al.  Order Structure, Correspondence, and Shape Based Categories , 1999, Shape, Contour and Grouping in Computer Vision.

[22]  Miroslaw Bober,et al.  MPEG-7 visual shape descriptors , 2001, IEEE Trans. Circuits Syst. Video Technol..

[23]  Michel Vidal-Naquet,et al.  A Fragment-Based Approach to Object Representation and Classification , 2001, IWVF.

[24]  Alfred O. Hero,et al.  A spectral method for solving elliptic equations for surface reconstruction and 3D active contours , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[25]  Jianbo Shi,et al.  A Random Walks View of Spectral Segmentation , 2001, AISTATS.

[26]  Michael Elad,et al.  Content Based Retrieval of VRML Objects - An Iterative and Interactive Approach , 2001, Eurographics Multimedia Workshop.

[27]  B. S. Manjunath,et al.  Introduction to MPEG-7: Multimedia Content Description Interface , 2002 .

[28]  Philip N. Klein,et al.  Shock-Based Indexing into Large Shape Databases , 2002, ECCV.

[29]  Dan Roth,et al.  Learning a Sparse Representation for Object Detection , 2002, ECCV.

[30]  Steven W. Zucker,et al.  Sketches with Curvature: The Curve Indicator Random Field and Markov Processes , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Patrice Y. Simard,et al.  Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[32]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[33]  Patrick Pérez,et al.  Poisson image editing , 2003, ACM Trans. Graph..

[34]  Miroslaw Bober,et al.  Curvature Scale Space Representation: Theory, Applications, and MPEG-7 Standardization , 2011, Computational Imaging and Vision.

[35]  Philip N. Klein,et al.  On Aligning Curves , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[36]  Guojun Lu,et al.  Evaluation of MPEG-7 shape descriptors against other shape descriptors , 2003, Multimedia Systems.

[37]  S. Osher,et al.  Geometric Level Set Methods in Imaging, Vision, and Graphics , 2011, Springer New York.

[38]  Ronen Basri,et al.  Curve Matching Using the Fast Marching Method , 2003, EMMCVPR.

[39]  Stefano Soatto,et al.  Shape representation via harmonic embedding , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[40]  Anuj Srivastava,et al.  Analysis of planar shapes using geodesic paths on shape spaces , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  Shimon Ullman,et al.  Combining Top-Down and Bottom-Up Segmentation , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[42]  David Mumford,et al.  2D-Shape Analysis Using Conformal Mapping , 2004, CVPR.

[43]  B. Schiele,et al.  Combined Object Categorization and Segmentation With an Implicit Shape Model , 2004 .

[44]  Ali Shokoufandeh,et al.  Shock Graphs and Shape Matching , 1998, International Journal of Computer Vision.

[45]  B. S. Manjunath,et al.  Drums and Curve Descriptors , 2004, BMVC.

[46]  Hermann Ney,et al.  Local context in non-linear deformation models for handwritten character recognition , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[47]  Bernhard Schölkopf,et al.  Training Invariant Support Vector Machines , 2002, Machine Learning.

[48]  Ronen Basri,et al.  Actions as space-time shapes , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[49]  Yann LeCun,et al.  The mnist database of handwritten digits , 2005 .

[50]  Ronen Basri,et al.  Shape Representation and Classification Using the Poisson Equation , 2006, IEEE Trans. Pattern Anal. Mach. Intell..