First Sym Etition: Metry Detection Comp Summary and Results

Symmetry is a pervasive phenomenon presenting itself in all forms and scales in natural and manmade environments and its detection plays an essential role at all levels of human as well as machine perception. The recent resurging interest in computational symmetry for computer vision and computer graphics applications has motivated us to conduct an US NSF funded symmetry detection algorithm competition as a workshop during 2011 Computer Vision and Pattern Recognition Conference. This competition sets the first benchmark in computer vision history for symmetry detection algorithms. In this report we explain the evaluation metric and the automatic execution of such evaluation workflow; we present and analyze the algorithms submitted, and show their results on three sets of real world images depicting reflection, rotation and translation symmetries respectively. This competition establishes a performance baseline for future work on symmetry detection. .

[1]  Jan-Olof Eklundh,et al.  Detecting Symmetry and Symmetric Constellations of Features , 2006, ECCV.

[2]  Yanxi Liu,et al.  Deformed Lattice Detection in Real-World Images Using Mean-Shift Belief Propagation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Luc Van Gool,et al.  Computational Symmetry in Computer Vision and Computer Graphics , 2010, Found. Trends Comput. Graph. Vis..