Hierarchical Bag of Paths for Kernel Based Shape Classification

Graph kernels methods are based on an implicit embedding of graphs within a vector space of large dimension. This implicit embedding allows to apply to graphs methods which where until recently solely reserved to numerical data. Within the shape classification framework, graphs are often produced by a skeletonization step which is sensitive to noise. We propose in this paper to integrate the robustness to structural noise by using a kernel based on a bag of path where each path is associated to a hierarchy encoding successive simplifications of the path. Several experiments prove the robustness and the flexibility of our approach compared to alternative shape classification methods.

[1]  C. Berg,et al.  Harmonic Analysis on Semigroups , 1984 .

[2]  Horst Bunke,et al.  Edit distance-based kernel functions for structural pattern classification , 2006, Pattern Recognit..

[3]  Paul H. Rabinowitz,et al.  On subharmonic solutions of hamiltonian systems , 1980 .

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

[5]  Bernard Haasdonk,et al.  Feature space interpretation of SVMs with indefinite kernels , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Gabriella Tarantello,et al.  Subharmonic solutions with prescribed minimal period for nonautonomous Hamiltonian systems , 1988 .

[7]  Manuel Davy,et al.  An online kernel change detection algorithm , 2005, IEEE Transactions on Signal Processing.

[8]  Benjamin B. Kimia,et al.  On the Local Form and Transitions of Symmetry Sets, Medial Axes, and Shocks , 2004, International Journal of Computer Vision.

[9]  F. Clarke,et al.  Nonlinear oscillations and boundary value problems for Hamiltonian systems , 1982 .

[10]  E. Hancock,et al.  A Skeletal Measure of 2D Shape Similarity , 2001 .

[11]  Kaleem Siddiqi,et al.  Matching Hierarchical Structures Using Association Graphs , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  David Haussler,et al.  Convolution kernels on discrete structures , 1999 .

[13]  Kaspar Riesen,et al.  A Family of Novel Graph Kernels for Structural Pattern Recognition , 2007, CIARP.

[14]  Cecilia Di Ruberto,et al.  Recognition of shapes by attributed skeletal graphs , 2004, Pattern Recognit..

[15]  Hisashi Kashima,et al.  Marginalized Kernels Between Labeled Graphs , 2003, ICML.

[16]  Benjamin B. Kimia,et al.  Symmetry-Based Indexing of Image Databases , 1998, J. Vis. Commun. Image Represent..

[17]  Alain Rakotomamonjy,et al.  Kernel on Bag of Paths For Measuring Similarity of Shapes , 2007, ESANN.