Resolution-Independent Superpixels Based on Convex Constrained Meshes Without Small Angles

  • Jeremy Forsythe
  • Vitaliy Kurlin
  • Andrew Fitzgibbon
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10072)


The over-segmentation problem for images is studied in the new resolution-independent formulation when a large image is approximated by a small number of convex polygons with straight edges at subpixel precision. These polygonal superpixels are obtained by refining and extending subpixel edge segments to a full mesh of convex polygons without small angles and with approximation guarantees. Another novelty is the objective error difference between an original pixel-based image and the reconstructed image with a best constant color over each superpixel, which does not need human segmentations. The experiments on images from the Berkeley Segmentation Database show that new meshes are smaller and provide better approximations than the state-of-the-art.


Reconstruction Error Convex Polygon Constant Color Straight Edge Simple Linear Iterative Cluster 


  1. 1.
    Viola, F., Fitzgibbon, A., Cipolla, R.: A unifying resolution-independent formulation for early vision. In: Proceedings of CVPR, pp. 494–501 (2012)Google Scholar
  2. 2.
    von Gioi, R.G., Jakubowicz, J., Morel, J.M., Randall, G.: LSD: a line segment detector. Image Process. Line 2, 35–55 (2012)CrossRefGoogle Scholar
  3. 3.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. Trans. PAMI 33, 898–916 (2011)CrossRefGoogle Scholar
  4. 4.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. Trans. PAMI 22, 888–905 (2000)CrossRefGoogle Scholar
  5. 5.
    Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59, 167–181 (2004)CrossRefGoogle Scholar
  6. 6.
    Levinshtein, A., Stere, A., Kutulakos, K., Fleet, D., Siddiqi, K.: Turbopixels: fast superpixels using geometric flows. Trans. PAMI 31, 2290–2297 (2009)CrossRefGoogle Scholar
  7. 7.
    Moore, A., Prince, S., Warrell, J.: Lattice cut - constructing superpixels using layer constraints. In: Proceedings of CVPR, pp. 2117–2124 (2010)Google Scholar
  8. 8.
    Liu, M.Y., Tuzel, O., Ramalingam, S., Chellappa, R.: Entropy rate superpixel segmentation. In: Proceedings of CVPR, pp. 2097–2104 (2011)Google Scholar
  9. 9.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. T-PAMI 34, 2274–2282 (2012)CrossRefGoogle Scholar
  10. 10.
    Van de Bergh, M., Boix, X., Roig, G., Van Gool, L.: Seeds: superpixels extracted via energy-driven sampling. Int. J. Comput. Vis. 111, 298–314 (2015)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Veksler, O., Boykov, Y., Mehrani, P.: Superpixels and supervoxels in an energy optimization framework. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6315, pp. 211–224. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-15555-0_16 CrossRefGoogle Scholar
  12. 12.
    Chen, C., Freedman, D., Lampert, C.: Enforcing topological constraints in random field image segmentation. In: Proceedings of CVPR, pp. 2089–2096 (2011)Google Scholar
  13. 13.
    Duan, L., Lafarge, F.: Image partitioning into convex polygons. In: Proceedings of CVPR (Computer Vision and Pattern Recognition), pp. 3119–3127 (2015)Google Scholar
  14. 14.
    Shewchuk, J.R.: Delaunay refinement algorithms for triangular mesh generation. Comput. Geom. Theor. Appl. 22, 21–74 (2002)MathSciNetCrossRefMATHGoogle Scholar
  15. 15.
    Forsythe, J., Kurlin, V., Fitzgibbon, A.: Resolution-independent superpixels based on convex constrained meshes (full version) (2016).

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Jeremy Forsythe
    • 1
    • 2
  • Vitaliy Kurlin
    • 3
  • Andrew Fitzgibbon
    • 4
  1. 1.Vienna University of TechnologyViennaAustria
  2. 2.Department of Mathematical SciencesDurham UniversityDurhamUK
  3. 3.Computer Science DepartmentUniversity of LiverpoolLiverpoolUK
  4. 4.Microsoft ResearchCambridgeUK

Personalised recommendations