Advertisement

Superpixel Segmentation by Object-Based Iterative Spanning Forest

  • Felipe BelémEmail author
  • Silvio Jamil F. Guimarães
  • Alexandre Xavier Falcão
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11401)

Abstract

Superpixel segmentation methods aim at representing image objects by the union of connected regions (superpixels). Such aim can be better approximated with a higher number of superpixels per object, which often leads to an unnecessary over-segmentation due to the absence of prior object information. In this work, we extend the Iterative Spanning Forest (ISF) framework to include object information and present a superpixel segmentation method based on object saliency detection. As ISF, the new framework, named Object-based ISF (OISF), relies on multiple executions of the Image Foresting Transform (IFT) algorithm for improved seed sets, such that each seed defines one connected superpixel as a spanning tree rooted at that seed. We describe an IFT-based method for object saliency detection and show that the corresponding saliency maps can improve seed estimation and connectivity function, increasing the superpixel resolution inside a given object. Experimental results on two medical image datasets demonstrate that the proposed OISF-based method outperforms the state-of-the-art in boundary adherence with higher number of superpixels inside the object.

Keywords

Superpixels Object saliency map Image Foresting Transform 

References

  1. 1.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34, 2274–2282 (2012).  https://doi.org/10.1109/TPAMI.2012.120CrossRefGoogle Scholar
  2. 2.
    Ciesielski, K.C., Falcão, A.X., Miranda, P.A.V.: Path-value functions for which Dijkstra’s algorithm returns optimal mapping. J. Math. Imaging Vis. 60, 1025–1036 (2018).  https://doi.org/10.1007/s10851-018-0793-1CrossRefMathSciNetzbMATHGoogle Scholar
  3. 3.
    Condori, M.A.T., Cappabianco, F.A.M., Falcão, A.X., De Miranda, P.A.V.: Extending the differential image foresting transform to root-based path-cost functions with application to superpixel segmentation. In: Proceedings of 30th Conference on Graphics Pattern Images (SIBGRAPI), pp. 7–14, October 2017.  https://doi.org/10.1109/SIBGRAPI.2017.8
  4. 4.
    Falcão, A.X., Stolfi, J., Lotufo, R.A.: The image foresting transform: theory, algorithms, and applications. IEEE Trans. Pattern Anal. Mach. Intell. 26, 19–29 (2004).  https://doi.org/10.1109/TPAMI.2004.1261076CrossRefGoogle Scholar
  5. 5.
    Li, Z., Chen, J.: Superpixel segmentation using linear spectral clustering. In: Proceedings of 28th Conference on Computer Vision and Pattern Recognition, pp. 1356–1363, June 2015.  https://doi.org/10.1109/CVPR.2015.7298741
  6. 6.
    Liu, Y.J., Yu, M., Li, B.J., He, Y.: Intrinsic manifold SLIC: a simple and efficient method for computing content-sensitive superpixels. IEEE Trans. Pattern Anal. Mach. Intell. 40(3), 653–666 (2018).  https://doi.org/10.1109/TPAMI.2017.2686857CrossRefGoogle Scholar
  7. 7.
    Neubert, P., Protzel, P.: Superpixel benchmark and comparison. In: Proceedings of Forum Bildverarbeitung, vol. 6, pp. 1–12 (2012)Google Scholar
  8. 8.
    Papa, J.P., Falcão, A.X., Suzuki, C.T.: Supervised pattern classification based on optimum-path forest. Int. J. Imaging Syst. Technol. 19(2), 120–131 (2009).  https://doi.org/10.1002/ima.20188CrossRefGoogle Scholar
  9. 9.
    Stutz, D., Hermans, A., Leibe, B.: Superpixels: an evaluation of the state-of-the-art. Computer Vis. Image Underst. 166, 1–27 (2018).  https://doi.org/10.1016/j.cviu.2017.03.007CrossRefGoogle Scholar
  10. 10.
    Tavares, A.C.M., Miranda, P.A.V., Spina, T.V., Falcão, A.X.: A supervoxel-based solution to resume segmentation for interactive correction by differential image-foresting transforms. In: Angulo, J., Velasco-Forero, S., Meyer, F. (eds.) ISMM 2017. LNCS, vol. 10225, pp. 107–118. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-57240-6_9CrossRefzbMATHGoogle Scholar
  11. 11.
    Vargas-Muñoz, J.E., Chowdhury, A.S., Alexandre, E.B., Galvão, F.L., Miranda, P.A.V., Falcão, A.X.: An iterative spanning forest framework for superpixel segmentation. IEEE Trans. Image Process (to appear 2019)Google Scholar
  12. 12.
    Wang, P., Zeng, G., Gan, R., Wang, J., Zha, H.: Structure-sensitive superpixels via geodesic distance. Int. J. Comput. Vis. 103, 1–21 (2013).  https://doi.org/10.1007/s11263-012-0588-6CrossRefMathSciNetzbMATHGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Felipe Belém
    • 1
    Email author
  • Silvio Jamil F. Guimarães
    • 2
  • Alexandre Xavier Falcão
    • 1
  1. 1.University of CampinasCampinasBrazil
  2. 2.Computer Science DepartmentPontifical Catholic University of Minas GeraisBelo HorizonteBrazil

Personalised recommendations