Shape Learning with Function-Described Graphs

A new method for shape learning is presented in this paper. This method incorporates abilities from both statistical and structural pattern recognition approaches to shape analysis. It borrows from statistical pattern recognition the capability of modelling sets of point coordinates, and from structural pattern recognition the ability of dealing with highly irregular patterns, such as those generated by points missingness. To that end we use a novel adaptation of Procrustes analysis, designed by us to align sets of points with missing elements. We use this information to generate sets of attributed graphs (AGs). From each set of AGs we synthesize a function-described graph (FDG), which is a type of compact representation that has the capability of probabilistic modelling of both structural and attribute information. Multivariate normal probability density estimation is used in FDGs instead of the originally used histograms. Comparative results of classification performance are presented of structural vs. attributes + structural information.

[1]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[2]  Alberto Sanfeliu,et al.  Function-described graphs for modelling objects represented by sets of attributed graphs , 2003, Pattern Recognit..

[3]  C. Goodall.  Procrustes methods in the statistical analysis of shape , 1991 .

[4]  Steven Gold,et al.  A Graduated Assignment Algorithm for Graph Matching , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Jacques J. F. Commandeur,et al.  Orthogonal Procrustes rotation for matrices with missing values , 1993 .

[6]  Haifeng Zhao,et al.  Shape Representation Based on Polar-Graph Spectra , 2006 .

[7]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[8]  Edwin R. Hancock,et al.  Discovering Shape Categories by Clustering Shock Trees , 2001, CAIP.

[9]  Sang Uk Lee,et al.  A new shape decomposition scheme for graph-based representation , 2005, Pattern Recognit..

[10]  Anuj Srivastava,et al.  Statistical shape analysis: clustering, learning, and testing , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Christopher J. Taylor,et al.  A Framework for Automatic Landmark Identification Using a New Method of Nonrigid Correspondence , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Alberto Sanfeliu,et al.  Synthesis of Function-Described Graphs and Clustering of Attributed Graphs , 2002, Int. J. Pattern Recognit. Artif. Intell..

[13]  Nikos Paragios,et al.  Shape registration in implicit spaces using information theory and free form deformations , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[15]  Edwin R. Hancock,et al.  A unified framework for alignment and correspondence , 2003, Comput. Vis. Image Underst..

[16]  Timothy F. Cootes,et al.  Building optimal 2D statistical shape models , 2003, Image Vis. Comput..

[17]  Alberto Sanfeliu,et al.  Second-Order Random Graphs For Modeling Sets Of Attributed Graphs And Their Application To Object Learning And Recognition , 2004, Int. J. Pattern Recognit. Artif. Intell..