A Study of Observation Scales Based on Felzenswalb-Huttenlocher Dissimilarity Measure for Hierarchical Segmentation

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11414)


Hierarchical image segmentation provides a region-oriented scale-space, i.e., a set of image segmentations at different detail levels in which the segmentations at finer levels are nested with respect to those at coarser levels. Guimarães et al. proposed a hierarchical graph based image segmentation (HGB) method based on the Felzenszwalb-Huttenlocher dissimilarity. This HGB method computes, for each edge of a graph, the minimum scale in a hierarchy at which two regions linked by this edge should merge according to the dissimilarity. In order to generalize this method, we first propose an algorithm to compute the intervals which contain all the observation scales at which the associated regions should merge. Then, following the current trend in mathematical morphology to study criteria which are not increasing on a hierarchy, we present various strategies to select a significant observation scale in these intervals. We use the BSDS dataset to assess our observation scale selection methods. The experiments show that some of these strategies lead to better segmentation results than the ones obtained with the original HGB method.



The research leading to these results has received funding from the French Agence Nationale de la Recherche, grant ANR-15-CE40-0006 (CoMeDiC), the Brazilian Federal Agency of Support and Evaluation of Postgraduate Education (program CAPES/PVE: grant 064965/2014-01), Brazilian Federal Agency of Research (CNPq/Universal 421521/2016-3 and CNPq/PQ 307062/2016-3), Fundo de Amparo Pesquisa do Estado de Minas Gerais (FAPEMIG/PPM 00006-16), the Peruvian agency Consejo Nacional de Ciencia, Tecnológica CONCYTEC (contract N 101-2016-. FONDECYT-DE). The first author would like to thank Brazilian agencies CNPq and CAPES and Peruvian agency CONCYTEC for the financial support during his thesis.


  1. 1.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. TPAMI 33(5), 898–916 (2011)CrossRefGoogle Scholar
  2. 2.
    Cahuina, E.J.Y.C., Cousty, J., Kenmochi, Y., Araújo, D.A., Cámara-Chávez, G.: Algorithms for hierarchical segmentation based on the Felzenszwalb-Huttenlocher dissimilarity. In: ICPRAI. pp. 1–6 (2018)Google Scholar
  3. 3.
    Cousty, J., Najman, L.: Incremental algorithm for hierarchical minimum spanning forests and saliency of watershed cuts. In: Soille, P., Pesaresi, M., Ouzounis, G.K. (eds.) ISMM 2011. LNCS, vol. 6671, pp. 272–283. Springer, Heidelberg (2011). Scholar
  4. 4.
    Cousty, J., Najman, L., Kenmochi, Y., Guimarães, S.: Hierarchical segmentations with graphs: quasi-flat zones, minimum spanning trees, and saliency maps. JMIV 60(4), 479–502 (2018)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Dollár, P.: Zitnick: fast edge detection using structured forests. TPAMI 37(8), 1558–1570 (2015)CrossRefGoogle Scholar
  6. 6.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. IJCV 59(2), 167–181 (2004)CrossRefGoogle Scholar
  7. 7.
    Guigues, L., Cocquerez, J.P., Le Men, H.: Scale-sets image analysis. IJCV 68(3), 289–317 (2006)CrossRefGoogle Scholar
  8. 8.
    Guimarães, S., Kenmochi, Y., Cousty, J., Patrocinio Jr., Z., Najman, L.: Hierarchizing graph-based image segmentation algorithms relying on region dissimilarity - the case of the Felzenszwalb-Huttenlocher method. MMTA 2(1), 55–75 (2017)Google Scholar
  9. 9.
    Haxhimusa, Y., Ion, A., Kropatsch, W.G.: Irregular pyramid segmentations with stochastic graph decimation strategies. In: Martínez-Trinidad, J.F., Carrasco Ochoa, J.A., Kittler, J. (eds.) CIARP 2006. LNCS, vol. 4225, pp. 277–286. Springer, Heidelberg (2006). Scholar
  10. 10.
    Meyer, F., Maragos, P.: Morphological scale-space representation with levelings. In: Nielsen, M., Johansen, P., Olsen, O.F., Weickert, J. (eds.) Scale-Space 1999. LNCS, vol. 1682, pp. 187–198. Springer, Heidelberg (1999). Scholar
  11. 11.
    Pavlidis, T.: Structural Pattern Recognition. Springer Series in Electronics and Photonics, vol. 1. Springer, Heidelberg (1977)zbMATHGoogle Scholar
  12. 12.
    Perret, B., Cousty, J., Guimarães, S.J., Maia, D.S.: Evaluation of hierarchical watersheds. IEEE Trans. Image Process. 27(4), 1676–1688 (2018)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Pont-Tuset, J., Arbeláez, P., Barron, J.T., Marques, F., Malik, J.: Multiscale combinatorial grouping for image segmentation and object proposal generation. IEEE TPAMI 39(1), 128–140 (2017)CrossRefGoogle Scholar
  14. 14.
    Salembier, P., Garrido, L.: Binary partition tree as an efficient representation for image processing, segmentation, and information retrieval. TIP 9(4), 561–576 (2000)Google Scholar
  15. 15.
    Salembier, P., Oliveras, A., Garrido, L.: Antiextensive connected operators for image and sequence processing. TIP 7(4), 555–570 (1998)Google Scholar
  16. 16.
    Syu, J.H., Wang, S.J., Wang, L.: Hierarchical image segmentation based on iterative contraction and merging. TIP 26(5), 2246–2260 (2017)MathSciNetGoogle Scholar
  17. 17.
    Xu, Y., Géraud, T., Najman, L.: Connected filtering on tree-based shape-spaces. TPAMI 38(6), 1126–1140 (2016)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Université Paris-Est, LIGM, CNRS - ENPC - ESIEE Paris - UPEMNoisy-le-GrandFrance
  2. 2.Computer Science DepartmentUniversidade Federal de Minas GeraisBelo HorizonteBrazil
  3. 3.PUC Minas - ICEI - DCC - VIPLABBelo HorizonteBrazil
  4. 4.Computer Science DepartmentUniversidade Federal de Ouro PretoOuro PretoBrazil

Personalised recommendations