Efficient Symmetry Detection Using Local Affine Frames

  • Hugo Cornelius
  • Michal Perďoch
  • Jiří Matas
  • Gareth Loy
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4522)


We present an efficient method for detecting planar bilateral symmetries under perspective projection. The method uses local affine frames (LAFs) constructed on maximally stable extremal regions or any other affine covariant regions detected in the image to dramatically improve the process of detecting symmetric objects under perspective distortion. In contrast to the previous work no Hough transform, is used. Instead, each symmetric pair of LAFs votes just once for a single axis of symmetry. The time complexity of the method is n log(n), where n is the number of LAFs, allowing a near real-time performance. The proposed method is robust to background clutter and partial occlusion and is capable of detecting an arbitrary number of symmetries in the image.


Bilateral Symmetry Region Detector Symmetric Pair Perspective Projection Symmetric Pattern 
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.


  1. 1.
    Dakin, S.C., Herbert, A.M.: The spatial region of integration for visual symmetry detection. Proc. of the Royal Society London B. Bio. Sci. 265, 659–664 (1998)CrossRefGoogle Scholar
  2. 2.
    Horridge, G.A.: The honeybee (apis mellifera) detect bilateral symmetry and discriminates its axis. J. Insect Physiol. 42, 755–764 (1996)CrossRefGoogle Scholar
  3. 3.
    Loy, G., Eklundh, J.-O.: 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
  4. 4.
    Cornelius, H., Loy, G.: Detecting bilateral symmetry in perspective. In: Proc of 5th Workshop on Perceptual Organisation in Computer Vision (POCV) (2006)Google Scholar
  5. 5.
    Obdrzalek, S., Matas, J.: Object recognition using local affine frames on distinguished regions. In: BMVC (2002)Google Scholar
  6. 6.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: BMVC, 3D and Video (2002)Google Scholar
  7. 7.
    Mikolajczyk, K., Schmid, C.: An Affine Invariant Interest Point Detector. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 128–142. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  8. 8.
    Mitra, S., Liu, Y.: Local facial asymmetry for expression classification. In: CVPR (2004)Google Scholar
  9. 9.
    Zielke, T., Brauckmann, M., von Seelen, W.: Intensity and edge-based symmetry detection with an application to car-following. CVGIP 58(2), 177–190 (1993)CrossRefGoogle Scholar
  10. 10.
    Hong, W., Yang, A.Y., Huang, K., Ma, Y.: On symmetry and multiple-view geometry: Structure, pose, and calibration from a single image. IJCV 60(3), 241–265 (2004)CrossRefGoogle Scholar
  11. 11.
    Loy, G., Zelinsky, A.: Fast radial symmetry for detecting points of interest. PAMI 25(8), 959–973 (2003)Google Scholar
  12. 12.
    Sela, G., Levine, M.D.: Real-time attention for robotic vision. Real-Time Imaging 3, 173–194 (1997)CrossRefGoogle Scholar
  13. 13.
    Mukherjee, D.P., Zisserman, A., Brady, J.M.: Shape from symmetry—detecting and exploiting symmetry in affine images. Philosophical Transactions of the Royal Society of London, Series A 351, 77–106 (1995)zbMATHCrossRefGoogle Scholar
  14. 14.
    Tuytelaars, T., Turina, A., Gool, L.J.V.: Noncombinatorial detection of regular repetitions under perspective skew. PAMI 25(4), 418–432 (2003)Google Scholar
  15. 15.
    Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Gool, L.V.: A comparison of affine region detectors. IJCV 65(1-2), 43–72 (2005)CrossRefGoogle Scholar
  16. 16.
    Lindeberg, T., Gårding, J.: Shape-adapted smoothing in estimation of 3-d cues from affine deformations of local 2-d brightness structure. ICV (1997)Google Scholar
  17. 17.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)CrossRefGoogle Scholar
  18. 18.
    Obdrzalek, S., Matas, J.: Sub-linear indexing for large scale object recognition. In: BMVC (2005)Google Scholar
  19. 19.
    Fischler, M., Bolles, R.: Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM 24(6), 381–395 (1981)CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Hugo Cornelius
    • 1
  • Michal Perďoch
    • 2
  • Jiří Matas
    • 2
  • Gareth Loy
    • 1
  1. 1.CVAP, Royal Institute of Technology, StockholmSweden
  2. 2.Center for Machine Perception, CTU in PragueCzech Republic

Personalised recommendations