Improving Image Segmentation for Boosting Image Annotation with Irregular Pyramids

  • Annette Morales-González
  • Edel García-Reyes
  • Luis Enrique Sucar
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8258)


Image Segmentation and Automatic Image Annotation are two research fields usually addressed independently. Treating these problems simultaneously and taking advantage of each other’s information may improve their individual results. In this work our ultimate goal is image annotation, which we perform using the hierarchical structure of irregular pyramids. We propose a new criterion to create new segmentation levels in the pyramid using low-level cues and semantic information coming from the annotation step. Later, we use the improved segmentation to obtain better annotation results in an iterative way across the hierarchy.We perform experiments in a subset of the Corel dataset, showing the relevance of combining both processes to improve the results of the final annotation.


image annotation image segmentation irregular pyramids 


  1. 1.
    Ullman, S.: Object recognition and segmentation by a fragment-based hierarchy. Trends in Cognitive Sciences 11(2), 58–64 (2007)CrossRefGoogle Scholar
  2. 2.
    van de Sande, K.E.A., Uijlings, J.R.R., Gevers, T., Smeulders, A.W.M.: Segmentation as selective search for object recognition. In: Proceedings of ICCV 2011, pp. 1879–1886. IEEE Computer Society (2011)Google Scholar
  3. 3.
    Akcay, H.G., Aksoy, S.: Automated detection of objects using multiple hierarchical segmentations. In: IGARSS, pp. 1468–1471. IEEE (2007)Google Scholar
  4. 4.
    Morales-González, A., García-Reyes, E., Sucar, L.E.: Hierarchical markov random fields with irregular pyramids for improving image annotation. In: Pavón, J., Duque-Méndez, N.D., Fuentes-Fernández, R. (eds.) IBERAMIA 2012. LNCS, vol. 7637, pp. 521–530. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  5. 5.
    Vieux, R., Benois-Pineau, J., Domenger, J.P., Braquelaire, A.: Segmentation-based multi-class semantic object detection. Multimedia Tools Appl. 60(2), 305–326 (2012)CrossRefGoogle Scholar
  6. 6.
    Torrent, A., Lladó, X., Freixenet, J., Torralba, A.: A boosting approach for the simultaneous detection and segmentation of generic objects. Pattern Recogn. Lett. 34(13), 1490–1498 (2013)CrossRefGoogle Scholar
  7. 7.
    Brun, L., Kropatsch, W.: Contains and inside relationships within combinatorial pyramids. Pattern Recogn. 39(4), 515–526 (2006)CrossRefzbMATHGoogle Scholar
  8. 8.
    Haxhimusa, Y., Kropatsch, W.G.: Hierarchy of partitions with dual graph contraction. In: Michaelis, B., Krell, G. (eds.) DAGM 2003. LNCS, vol. 2781, pp. 338–345. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  9. 9.
    Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8(6), 679–698 (1986)CrossRefGoogle Scholar
  10. 10.
    Carbonetto, P.: Unsupervised statistical models for general object recognition. Tech. Rep., The Faculty of Graduate Studies, Department of Computer Science, The University of British Columbia, West Mall Vancouver, BC Canada (2003)Google Scholar
  11. 11.
    Hernández-Gracidas, C., Sucar, L.E.: Markov random fields and spatial information to improve automatic image annotation. In: Mery, D., Rueda, L. (eds.) PSIVT 2007. LNCS, vol. 4872, pp. 879–892. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  12. 12.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)CrossRefzbMATHGoogle Scholar
  13. 13.
    Morales-González, A., García-Reyes, E.B.: Simple object recognition based on spatial relations and visual features represented using irregular pyramids. Multimedia Tools Appl. 63(3), 875–897 (2013)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Annette Morales-González
    • 1
  • Edel García-Reyes
    • 1
  • Luis Enrique Sucar
    • 2
  1. 1.Advanced Technologies Application CenterLa HabanaCuba
  2. 2.Instituto Nacional de Astrofísica, Óptica y ElectrónicaPueblaMexico

Personalised recommendations