From skeletons to bone graphs: Medial abstraction for object recognition

Medial descriptions, such as shock graphs, have gained significant momentum in the shape-based object recognition community due to their invariance to translation, rotation, scale and articulation and their ability to cope with moderate amounts of within-class deformation. While they attempt to decompose a shape into a set of parts, this decomposition can suffer from ligature-induced instability. In particular, the addition of even a small part can have a dramatic impact on the representation in the vicinity of its attachment. We present an algorithm for identifying and representing the ligature structure, and restoring the non-ligature structures that remain. This leads to a bone graph, a new medial shape abstraction that captures a more intuitive notion of an objectpsilas parts than a skeleton or a shock graph, and offers improved stability and within-class deformation invariance. We demonstrate these advantages by comparing the use of bone graphs to shock graphs in a set of view-based object recognition and pose estimation trials.

[1]  Benjamin B. Kimia,et al.  Boundary Smoothing via Symmetry Transforms , 2001, Journal of Mathematical Imaging and Vision.

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

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

[4]  Dmitry Chetverikov,et al.  A Simple and Efficient Algorithm for Detection of High Curvature Points in Planar Curves , 2003, CAIP.

[5]  Kaleem Siddiqi,et al.  Ligature instabilities in the perceptual organization of shape , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[6]  Manish Singh,et al.  Bayesian estimation of the shape skeleton , 2010 .

[7]  H. Blum.  Biological shape and visual science. I. , 1973, Journal of theoretical biology.

[8]  Wenyu Liu,et al.  Skeleton Pruning by Contour Partitioning with Discrete Curve Evolution , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  M. Grayson.  Shortening embedded curves , 1989 .

[10]  Gabriella Sanniti di Baja,et al.  Using distance transforms to decompose 3D discrete objects , 2002, Image Vis. Comput..

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

[12]  HARRY BLUM,et al.  Shape description using weighted symmetric axis features , 1978, Pattern Recognit..

[13]  H. Blum.  Biological shape and visual science (part I) , 1973 .

[14]  Philip N. Klein,et al.  Recognition of shapes by editing their shock graphs , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Alfred M. Bruckstein,et al.  Pruning Medial Axes , 1998, Comput. Vis. Image Underst..

[16]  Stephen M. Pizer,et al.  Untangling the Blum Medial Axis Transform , 2003, International Journal of Computer Vision.

[17]  Benjamin B. Kimia,et al.  On the Intrinsic Reconstruction of Shape from Its Symmetries , 2003, IEEE Trans. Pattern Anal. Mach. Intell..