Curved Reflection Symmetry Detection with Self-validation

  • Jingchen Liu
  • Yanxi Liu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6495)


We propose a novel, self-validating approach for detecting curved reflection symmetry patterns from real, unsegmented images. Our method benefits from the observation that any curved symmetry pattern can be approximated by a sequence of piecewise rigid reflection patterns. Pairs of symmetric feature points are first detected (including both inliers and outliers) and treated as ‘particles’. Multiple-hypothesis sampling and pruning are used to sample a smooth path going through inlier particles to recover the curved reflection axis. Our approach generates an explicit supporting region of the curved reflection symmetry, which is further used for intermediate self-validation, making the detection process more robust than prior state-of-the-art algorithms. Experimental results on 200+ images demonstrate the effectiveness and superiority of the proposed approach.


Feature Point Supporting Region Normalize Cross Correlation Smooth Path Symmetry Detection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Liu, Y., Hel-Or, H., Kaplan, C.S., Gool, L.V.: Computational symmetry in computer vision and computer graphics. Foundations and Trends in Computer Graphics and Vision 5, 1–195 (2010)CrossRefMATHGoogle Scholar
  2. 2.
    Weyl, H.: Symmetry. Princeton University Press, Princeton (1952)CrossRefMATHGoogle Scholar
  3. 3.
    Mitra, S., Liu, Y.: Local facial asymmetry for expression classification. In: Proceedings of the 2004 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2004), vol. 2, pp. 889–894 (2004)Google Scholar
  4. 4.
    Liu, J., Liu, Y.: Multi-target tracking of time-varying spatial patterns. In: Computer Vision and Pattern Recognition Conference, CVPR 2010 (2010)Google Scholar
  5. 5.
    Kuehnle, A.: Symmetry-based recognition of vehicle rears. Pattern Recogn. Lett. 12, 249–258 (1991)CrossRefGoogle Scholar
  6. 6.
    Mancas, M., Gosselin, B., Macq, B.: Fast and automatic tumoral area localisation using symmetry. In:Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, (ICASSP 2005), vol. 2, pp. 725–728 (2005)Google Scholar
  7. 7.
    Park, M., Lee, S., Chen, P.C., Kashyap, S., Butt, A.A., Liu, Y.: Performance evaluation of state-of-the-art discrete symmetry detection algorithms. In: Computer Vision and Pattern Recognition Conference (CVPR), pp. 1–8 (2008)Google Scholar
  8. 8.
    Sun, C., Si, D.: Fast reflectional symmetry detection using orientation histograms. Real-Time Imaging 5, 63–74 (1999)CrossRefGoogle Scholar
  9. 9.
    Masuda, T., Yamamoto, K., Yamada, H.: Detection of partial symmetry using correlation with rotated-reflected images. Pattern Recognition 26 (1993)Google Scholar
  10. 10.
    Loy, G., Eklundh, J.: Detecting symmetry and symmetric constellations of features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 508–521. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  11. 11.
    Mitra, N., Guibas, L., Pauly, M.: Partial and approximate symmetry detection for 3d geometry. ACM Transactions on Graphics 25, 560–568 (2006)CrossRefGoogle Scholar
  12. 12.
    Kanade, T., Kender, J.R.: Mapping image properties into shape constraints: skewed symmetry, affine-transformable patterns, and the shape-from-texture paradigm. In: Human and Machine Vision, pp. 237–257 (1983)Google Scholar
  13. 13.
    Shen, D., Ip, H., Teoh, E.: Robust detection of skewed symmetries. In: International Conference on Pattern Recognition, vol. 3, pp. 1010–1013 (2000)Google Scholar
  14. 14.
    Van Gool, L., Proesmans, M., Moons, T.: Mirror and point symmetry under perspective skewing. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 285–292 (1996)Google Scholar
  15. 15.
    Carlsson, S.: Symmetry in perspective. In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, p. 249. Springer, Heidelberg (1998)Google Scholar
  16. 16.
    Lei, Y., Wong, K.: Detection and localisation of reflectional and rotational symmetry under weak perspective projection. Pattern Recognition 32, 167–180 (1999)CrossRefGoogle Scholar
  17. 17.
    Cornelius, H., Loy, G.: Detecting bilateral symmetry in perspective. In: CVPRW, p. 191 (2006)Google Scholar
  18. 18.
    Lee, S., Liu, Y.: Curved glide-reflection symmetry detection. In: Computer Vision and Pattern Recognition Conference (CVPR 2009), pp. 1046–1053 (2009)Google Scholar
  19. 19.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60, 91–110 (2004)CrossRefGoogle Scholar
  20. 20.
    Zabrodsky, H., Peleg, S., Avnir, D.: Symmetry as a continuous feature. IEEE Transactions on Pattern Analysis and Machine Intelligence 17, 1154–1166 (1995)CrossRefGoogle Scholar
  21. 21.
    Söderkvist, O.J.O.: Computer vision classification of leaves from swedish trees. Master’s thesis, Linköping University (2001)Google Scholar
  22. 22.
    Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. International Journal of Computer Vision (IJCV) 1, 63–86 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Jingchen Liu
    • 1
  • Yanxi Liu
    • 1
    • 2
  1. 1.Department of Computer Science and EngineeringThe Pennsylvania State UniversityUniversity ParkUSA
  2. 2.Department of Electrical EngineeringThe Pennsylvania State UniversityUniversity ParkUSA

Personalised recommendations