Advertisement

Learning-Based Symmetry Detection in Natural Images

  • Stavros Tsogkas
  • Iasonas Kokkinos
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7578)

Abstract

In this work we propose a learning-based approach to symmetry detection in natural images. We focus on ribbon-like structures, i.e. contours marking local and approximate reflection symmetry and make three contributions to improve their detection. First, we create and make publicly available a ground-truth dataset for this task by building on the Berkeley Segmentation Dataset. Second, we extract features representing multiple complementary cues, such as grayscale structure, color, texture, and spectral clustering information. Third, we use supervised learning to learn how to combine these cues, and employ MIL to accommodate the unknown scale and orientation of the symmetric structures. We systematically evaluate the performance contribution of each individual component in our pipeline, and demonstrate that overall we consistently improve upon results obtained using existing alternatives.

Keywords

Natural Image Spectral Cluster Integral Image Multiple Instance Learn 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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Konishi, S., Yuille, A.L., Coughlan, J.M., Zhu, S.C.: Statistical Edge Detection: Learning and Evaluating Edge Cues. PAMI (2003)Google Scholar
  2. 2.
    Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using local brightness, color, and texture cues. PAMI (2004)Google Scholar
  3. 3.
    Kokkinos, I.: Boundary Detection Using F-Measure-, Filter- and Feature- (F3) Boost. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 650–663. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  4. 4.
    Rosten, E., Drummond, T.W.: Machine Learning for High-Speed Corner Detection. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 430–443. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  5. 5.
    Apostoloff, N., Fitzgibbon, A.W.: Learning spatiotemporal t-junctions for occlusion detection. In: CVPR (2005)Google Scholar
  6. 6.
    Maire, M., Arbelaez, P., Fowlkes, C., Malik, J.: Using contours to detect and localize junctions in natural images. In: CVPR (2008)Google Scholar
  7. 7.
    Kokkinos, I., Maragos, P., Yuille, A.: Bottom-up & top-down object detection using primal sketch features and graphical models. In: CVPR, vol. 2, pp. 1893–1900. IEEE (2006)Google Scholar
  8. 8.
    Stark, M., Goesele, M., Schiele, B.: A shape-based object class model for knowledge transfer. In: ICCV (2009)Google Scholar
  9. 9.
    Siddiqi, K., Pizer, S.: Medial Representations. Springer (2009)Google Scholar
  10. 10.
    Liu, Y.: Computational symmetry in computer vision and computer graphics. Now publishers Inc. (2009)Google Scholar
  11. 11.
    Lindeberg, T.: Edge detection and ridge detection with automatic scale selection. IJCV (1998)Google Scholar
  12. 12.
    Pizer, S., Burbeck, C., Coggins, J., Fritsch, D., Morse, B.: Object shape before boundary shape: Scale-space medial axes. JMIV (1994)Google Scholar
  13. 13.
    Lôpez, A., Lumbreras, F., Serrat, J., Villanueva, J.: Evaluation of methods for ridge and valley detection. PAMI (1999)Google Scholar
  14. 14.
    Levinshtein, A., Dickinson, S., Sminchisescu, C.: Multiscale symmetric part detection and grouping. In: ICCV (2009)Google Scholar
  15. 15.
    Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: ICCV (2001)Google Scholar
  16. 16.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. PAMI (2011)Google Scholar
  17. 17.
    Babenko, B., Dollár, P., Tu, Z., Belongie, S., et al.: Simultaneous learning and alignment: Multi-instance and multi-pose learning (2008)Google Scholar
  18. 18.
    Keeler, J., Rumelhart, D., Leow, W.: Integrated segmentation and recognition of hand-printed numerals. In: NIPS (1990)Google Scholar
  19. 19.
    Viola, P., Platt, J., Zhang, C.: Multiple instance boosting for object detection. In: NIPS (2006)Google Scholar
  20. 20.
    Blum, H., et al.: A transformation for extracting new descriptors of shape. In: Models for the Perception of Speech and Visual Form (1967)Google Scholar
  21. 21.
    Brady, M., Asada, H.: Smoothed local symmetries and their implementation. IJRR (1984)Google Scholar
  22. 22.
    van Eede, M., Macrini, D., Telea, A., Sminchisescu, C., Dickinson, S.: Canonical skeletons for shape matching. In: ICPR (2006)Google Scholar
  23. 23.
    Telea, A., Van Wijk, J.: An augmented fast marching method for computing skeletons and centerlines. In: Eurographics (2002)Google Scholar
  24. 24.
    Telea, A., Sminchisescu, C., Dickinson, S.: Optimal inference for hierarchical skeleton abstraction. In: Pattern Recognition (2004)Google Scholar
  25. 25.
    Demirci, M., Shokoufandeh, A., Dickinson, S.: Skeletal shape abstraction from examples. PAMI (2009)Google Scholar
  26. 26.
    Siddiqi, K., Bouix, S., Tannenbaum, A., Zucker, S.: Hamilton-jacobi skeletons. IJCV (2002)Google Scholar
  27. 27.
    Haralick, R.: Ridges and valleys on digital images. In: CVGIP (1983)Google Scholar
  28. 28.
    Eberly, D., Gardner, R., Morse, B., Pizer, S., Scharlach, C.: Ridges for image analysis. JMIV (1994)Google Scholar
  29. 29.
    Steger, C.: An unbiased detector of curvilinear structures. PAMI (1998)Google Scholar
  30. 30.
    Pizer, S., Eberly, D., Fritsch, D., Morse, B.: Zoom-invariant vision of figural shape: The mathematics of cores* 1. In: CVIU (1998)Google Scholar
  31. 31.
    Weyl, H.: Symmetry. Princeton University Press (1983)Google Scholar
  32. 32.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: CVPR (2001)Google Scholar
  33. 33.
    Catanzaro, B., Su, B., Sundaram, N., Lee, Y., Murphy, M., Keutzer, K.: Efficient, high-quality image contour detection. In: ICCV (2009)Google Scholar
  34. 34.
    Rubner, Y., Puzicha, J., Tomasi, C., Buhmann, J.: Empirical evaluation of dissimilarity measures for color and texture. In: CVIU (2001)Google Scholar
  35. 35.
    Ng, A., Jordan, M., Weiss, Y.: On spectral clustering: Analysis and an algorithm. In: NIPS (2002)Google Scholar
  36. 36.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. PAMI (2000)Google Scholar
  37. 37.
    Cour, T., Benezit, F., Shi, J.: Spectral segmentation with multiscale graph decomposition. In: CVPR (2005)Google Scholar
  38. 38.
    Maji, S., Vishnoi, N., Malik, J.: Biased normalized cuts. In: CVPR (2011)Google Scholar
  39. 39.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV (2004)Google Scholar
  40. 40.
    Kokkinos, I.: Highly accurate boundary detection and grouping. In: CVPR (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Stavros Tsogkas
    • 1
    • 2
    • 3
  • Iasonas Kokkinos
    • 1
    • 2
    • 3
  1. 1.Center for Visual ComputingÉcole Centrale de ParisFrance
  2. 2.Equipe Galen, INRIA Saclay, Ile-de-FranceFrance
  3. 3.Center for Visual Computing, Ecole des Ponts ParisTechUniversité Paris-Est, LIGM (UMR CNRS)France

Personalised recommendations