Hierarchical Graph-Based Segmentation in Detection of Object-Related Regions

  • Rafael Machado Ribeiro
  • Silvio Jamil Ferzoli Guimarães
  • Zenilton Kleber G. PatrocínioJr.Email author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11401)


Object detection is an important task in computer vision. Recently, several unsupervised approaches have been proposed to cope with this problem in a category-independent manner. This work evaluates the adoption of a hierarchical graph-based segmentation along with an state-of-the-art method to detect object-related regions. A hierarchical segmentation approach produces a set of partitions at different detail levels, in a way that a coarser level can be obtained by a simple merge of finer ones. Experimental results show that our proposal obtains an increase of 11% in object detection rate.


Object detection Hierarchical image segmentation Object segmentation Object localization 


  1. 1.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Susstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE TPAMI 34(11), 2274–2282 (2012)CrossRefGoogle Scholar
  2. 2.
    Alexe, B., Deselaers, T., Ferrari, V.: Measuring the objectness of image windows. IEEE TPAMI 34(11), 2189–2202 (2012)CrossRefGoogle Scholar
  3. 3.
    Carreira, J., Sminchisescu, C.: CPMC: automatic object segmentation using constrained parametric min-cuts. IEEE TPAMI 34(7), 1312–1328 (2012)CrossRefGoogle Scholar
  4. 4.
    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
  5. 5.
    Endries, I., Hoiem, D.: Category-independent object proposals with diverse ranking. IEEE TPAMI 36(2), 222–234 (2014)CrossRefGoogle Scholar
  6. 6.
    Everingham, M., Van Gool, C., Williams, C., Winn, J., Zisserman, A.: The pascal visual object classes challenge (2007).
  7. 7.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. IJCV 59(2), 167–181 (2004)CrossRefGoogle Scholar
  8. 8.
    Guiges, L., Cocquerez, J., Men, H.L.: Scale-sets image analysis. IJCV 68(3), 289–317 (2006)CrossRefGoogle Scholar
  9. 9.
    Guimarães, S.J.F., Kenmochi, Y., Cousty, J., Patrocínio Jr., Z.K.G., Najman, L.: Hierarchizing graph-based image segmentation algorithms relying on region dissimilarity: the case of the Felzenszwalb-Huttenlocher method. Math. Morphol. Theory Appl. 2, 55–75 (2017)Google Scholar
  10. 10.
    Guimarães, S.J.F., Cousty, J., Kenmochi, Y., Najman, L.: A hierarchical image segmentation algorithm based on an observation scale. In: Gimel’farb, G., et al. (eds.) SSPR/SPR 2012. LNCS, vol. 7626. Springer, Heidelberg (2012). Scholar
  11. 11.
    van de Sande, K.E.A., Uijlings, J.R.R., Gevers, T., Smeulders, A.W.M.: Segmentation as selective search for object recognition. In: ICCV 2011, pp. 1879–1886 (2011)Google Scholar
  12. 12.
    Zhang, H., Fritts, J.E., Goldman, S.A.: Image segmentation evaluation: a survey of unsupervised methods. CVIU 110(3), 260–280 (2008)Google Scholar
  13. 13.
    Zhang, X., Yang, Y.H., Han, Z., Wang, H., Gao, C.: Object class detection: a survey. ACM Comput. Surv. 46(1), 10:1–10:53 (2013)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Rafael Machado Ribeiro
    • 1
  • Silvio Jamil Ferzoli Guimarães
    • 1
  • Zenilton Kleber G. PatrocínioJr.
    • 1
    Email author
  1. 1.Computer Science DepartmentPontifical Catholic University of Minas GeraisBelo HorizonteBrazil

Personalised recommendations