Advertisement

Revisiting Skeletons from Natural Images

Conference paper
  • 455 Downloads
Part of the Association for Women in Mathematics Series book series (AWMS, volume 1)

Abstract

In the last two decades there have been several works promoting shape fields that implicitly encode local convexity/concavity properties of the shape boundary. These shape fields are formulated either as solutions to Poisson type PDEs or via heuristic approximations to them. The v-field of Tari-Shah-Pien, can be computed directly from a real image; thus, suggests a mechanism to bridge low level visual processing and high level shape computations. We revisit Tari, Shah and Pien’s v-field approach and extend its application to complex images with texture. We relate v-field value at a skeleton point to the distance of the point from a putative shape boundary, and use this relation to extract semantic image patches. At the end of the chapter, we experimentally compare the medial locus computed from the new v-field to that of Kimia et al.

Keywords

Shape Boundary Skeleton Point Edge Diffusivity High Level Visual Processing Shape Interior 
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.

Notes

Acknowledgements

We thank O. Ozcanli for running Kimia method [6] on our data. The work reported here is initiated under the grant TUBITAK 105E154 and completed with financial support of grant TUBITAK 112E208.

References

  1. 1.
    Aslan, C., Tari, S.: An axis-based representation for recognition. In: ICCV, Beijing, pp. 1339–1346 (2005)Google Scholar
  2. 2.
    Bergbauer, J., Tari, S.: Wimmelbild analysis with approximate curvature coding distance images. In: SSVM, Graz, pp. 489–500 (2013)Google Scholar
  3. 3.
    Erdem, E., Tari, S.: Mumford-Shah regularizer with contextual feedback. J. Math. Imaging Vis. 33(1), 67–84 (2009)CrossRefMathSciNetGoogle Scholar
  4. 4.
    Gurumoorthy, K., Rangarajan, A.: A Schroedinger equation for the fast computation of approximate Euclidean distance functions. In: SSVM, Voss, pp. 100–111 (2009)Google Scholar
  5. 5.
    Mumford, D., Shah, J.: Optimal approximations by piecewise smooth functions and associated variational problems. Commun. Pure Appl. Math. 42(5), 577–685 (1989)CrossRefzbMATHMathSciNetGoogle Scholar
  6. 6.
    Ozcanli, O.C., Kimia, B.B.: Generic object recognition via shock patch fragments. In: BMVC, Warwick, pp. 1030–1039 (2007)Google Scholar
  7. 7.
    Shah, J.: A common framework for curve evolution, segmentation and anisotropic diffusion. In: CVPR, San Francisco, pp. 136–142 (1996)Google Scholar
  8. 8.
    Tari, S.: Fluctuating distance fields, parts, three-partite skeletons. In: Innovations for Shape Analysis, pp. 439–466Google Scholar
  9. 9.
    Tari, S., Shah, J., Pien, H.: A computationally efficient shape analysis via level sets. In: Mathematical Methos in Biomedical Image Analysis, pp. 234–243 (1996) IEEE Computer Society Press, Los Alamitos, California (2013)Google Scholar
  10. 10.
    Tari, S., Shah, J., Pien, H.: Extraction of shape skeletons from grayscale images. Comput. Vis. Image Underst. 66(2), 133–146 (1997)CrossRefGoogle Scholar
  11. 11.
    Tek, H., Kimia, B.B.: Symmetry maps of free-form curve segments via wave propagation. Int. J. Comput. Vis. 54(1–3), 35–81 (2003)CrossRefzbMATHGoogle Scholar
  12. 12.
    Zucker, S.: Distance images and the enclosure field. In: Innovations for Shape Analysis, pp. 301–323. Springer, Berlin/New York (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland & The Association for Women in Mathematics 2015

Authors and Affiliations

  1. 1.Department of Computer EngineeringMiddle East Technical UniversityAnkaraTurkey
  2. 2.Department of Computer EngineeringHacettepe UniversityAnkaraTurkey

Personalised recommendations