Learning Precise Local Boundaries in Images from Human Tracings

  • Martin Horn
  • Michael R. Berthold
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8156)

Abstract

Boundaries are the key cue to differentiate objects from each other and the background. However whether boundaries can be regarded as such cannot be determined generally as this highly depends on specific questions that need to be answered. As humans are best able to answer these questions and provide the required knowledge, it is often necessary to learn task-specific boundary properties from user-provided examples. However, current approaches to learning boundaries from examples completely ignore the inherent inaccuracy of human boundary tracings and, hence, derive an imprecise boundary description. We therefore provide an alternative view on supervised boundary learning and propose an efficient and robust algorithm to derive a precise boundary model for boundary detection.

Keywords

boundary detection supervised learning 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Martin, D.R., Fowlkes, C.C., Malik, J.: Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE PAMI 26(5), 530–549 (2004)CrossRefGoogle Scholar
  2. 2.
    Köthe, U.: Reliable Low-Level Image Analysis. Professorial dissertation, Department Informatik. University of Hamburg (2008)Google Scholar
  3. 3.
    Ren, X., Liefeng, B.: Discriminatively trained sparse code gradients for contour detection. In: Bartlett, P., Pereira, F., Burges, C., Bottou, L., Weinberger, K. (eds.) Advances in Neural Information Processing Systems 25, pp. 593–601 (2012)Google Scholar
  4. 4.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. Technical Report UCB/EECS-2010-17, EECS Department, University of California, Berkeley (February 2010)Google Scholar
  5. 5.
    Dollar, P., Tu, Z., Belongie, S.: Supervised learning of edges and object boundaries. In: CVPR, pp. 1964–1971 (2006)Google Scholar
  6. 6.
    Konishi, S., Yuille, A.L., Coughlan, J.M., Zhu, S.C.: Statistical edge detection: Learning and evaluating edge cues. IEEE PAMI 25, 57–74 (2003)CrossRefGoogle Scholar
  7. 7.
    Meila, M., Shi, J.: Learning segmentation by random walks. In: Advances in Neural Information Processing Systems, pp. 873–879. MIT Press (2001)Google Scholar
  8. 8.
    Will, S., Hermes, L., Buhmann, J.M., Puzicha, J.: On learning texture edge detectors. In: Proc. Int. Conf. Image Processing, pp. 877–880 (2000)Google Scholar
  9. 9.
    Martin, D.R., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. Technical Report UCB/CSD-01-1133, EECS Department, University of California, Berkeley (Jan 2001)Google Scholar
  10. 10.
    Adams, A., Baek, J., Davis, M.A.: Fast high-dimensional filtering using the permutohedral lattice. Computer Graphics Forum 29(2), 753–762 (2010)CrossRefGoogle Scholar
  11. 11.
    Horn, M., Berthold, M.: Towards active segmentation of cell images. In: Biomedical Imaging: From Nano to Macro, March 30 -April 2, pp. 177–181 (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Martin Horn
    • 1
  • Michael R. Berthold
    • 1
  1. 1.Nycomed Chair for Bioinformatics and Information Mining AND Konstanz Research School Chemical BiologyUniversity of KonstanzKonstanzGermany

Personalised recommendations