Advertisement

Supervised Assessment of Segmentation Hierarchies

  • Jordi Pont-Tuset
  • Ferran Marques
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7575)

Abstract

This paper addresses the problem of the supervised assessment of hierarchical region-based image representations. Given the large amount of partitions represented in such structures, the supervised assessment approaches in the literature are based on selecting a reduced set of representative partitions and evaluating their quality. Assessment results, therefore, depend on the partition selection strategy used. Instead, we propose to find the partition in the tree that best matches the ground-truth partition, that is, the upper-bound partition selection. We show that different partition selection algorithms can lead to different conclusions regarding the quality of the assessed trees and that the upper-bound partition selection provides the following advantages: 1) it does not limit the assessment to a reduced set of partitions, and 2) it better discriminates the random trees from actual ones, which reflects a better qualitative behavior. We model the problem as a Linear Fractional Combinatorial Optimization (LFCO) problem, which makes the upper-bound selection feasible and efficient.

Keywords

Ground Truth Random Tree Boundary Pixel Boundary Match Quad Tree 
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.
    Salembier, P., Garrido, L.: Binary partition tree as an efficient representation for image processing, segmentation, and information retrieval. IEEE Transactions on Image Processing 9(4), 561–576 (2000)CrossRefGoogle Scholar
  2. 2.
    Huihai, L., Woods, J.C., Ghanbari, M.: Binary partition tree analysis based on region evolution and its application to tree simplification. IEEE Transactions on Image Processing 16(4), 1131–1138 (2007)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Cardelino, J., Caselles, V., Bertalmio, M., Randall, G.: A contrario hierarchical image segmentation. In: IEEE International Conference on Image Processing, pp. 4041–4044 (2009)Google Scholar
  4. 4.
    McGuinness, K., O’connor: A comparative evaluation of interactive segmentation algorithms. Pattern Recognition 43, 434–444 (2010)zbMATHCrossRefGoogle Scholar
  5. 5.
    Arbeláez, P., Maire, M., Fowlkes, C.C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 33(5), 898–916 (2011)CrossRefGoogle Scholar
  6. 6.
    Pont-Tuset, J., Marques, F.: Contour detection using binary partition trees. In: IEEE International Conference on Image Processing, pp. 1609–1612 (2010)Google Scholar
  7. 7.
    Hunter, G.M., Steiglitz, K.: Operations on images using quad trees. IEEE Transactions on Pattern Analysis and Machine Intelligence 1(2), 145–153 (1979)CrossRefGoogle Scholar
  8. 8.
    Vilaplana, V., Marques, F., Salembier, P.: Binary partition trees for object detection. IEEE Transactions on Image Processing 17(11), 2201–2216 (2008)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Calderero, F., Marques, F.: Region merging techniques using information theory statistical measures. IEEE Transactions on Image Processing 19(6), 1567–1586 (2010)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Radzik, T.: Newton’s method for fractional combinatorial optimization. In: Symposium on Foundations of Computer Science, pp. 659–669 (1992)Google Scholar
  11. 11.
    Unnikrishnan, R., Pantofaru, C., Hebert, M.: Toward objective evaluation of image segmentation algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(6), 929–944 (2007)CrossRefGoogle Scholar
  12. 12.
    Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(5), 530–549 (2004)CrossRefGoogle Scholar
  13. 13.
    Nunes, P., Marques, F., Pereira, F., Gasull, A.: A contour-based approach to binary shape coding using a multiple grid chain code. Signal Processing: Image Communication 15(7-8), 585–599 (2000)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Jordi Pont-Tuset
    • 1
  • Ferran Marques
    • 1
  1. 1.Universitat Politècnica de Catalunya BarcelonaTechBarcelonaSpain

Personalised recommendations