Connected Components Labeling on the GPU with Generalization to Voronoi Diagrams and Signed Distance Fields

  • A. Rasmusson
  • T. S. Sørensen
  • G. Ziegler
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8033)


Many image processing problems benefit from a complete solution to connected components labeling. This paper introduces a new data parallel labeling method based on calculation of label propagation sizes from the connectivity between pixels extracted in a pre-processing step and re-usal of established label propagation routes. The method achieves real-time performance for 2D images and it also generalizes to Voronoi diagrams and signed distance fields.


Computer vision connected components labeling GPU Voronoi diagrams 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hoshen, J., Kopelman, R.: Percolation and cluster distribution. I. Cluster multiple labeling technique and critical concentration algorithm. Phys. Rev. B 14, 3438–3445 (1976)CrossRefGoogle Scholar
  2. 2.
    Samet, H.: Connected component labeling using quadtrees. Journal of the ACM (JACM) 28, 487–501 (1981)MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Kiran, B., Ramakrishnan, K., Kumar, Y., Anoop, K.: An improved connected component labeling by recursive label propagation (2011)Google Scholar
  4. 4.
    Nvidia Corp.: CUDA C Programming Guide (2013),
  5. 5.
    Khronos Group: OpenCL (2013),
  6. 6.
    Owens, J., Luebke, D., Govindaraju, N., Harris, M., Krüger, J., Lefohn, A., Purcell, T.J.: A survey of general-purpose computation on graphics hardware. Computer Graphics Forum 26, 80–113 (2007)CrossRefGoogle Scholar
  7. 7.
    Hawick, K., Leist, A., Playne, D.: Parallel graph component labelling with GPUs and CUDA. Parallel Computing (2010)Google Scholar
  8. 8.
    Kalentev, O., Rai, A., Kemnitz, S., Schneider, R.: Connected component labeling on a 2D grid using CUDA. Journal of Parallel and Distributed Computing (2010)Google Scholar
  9. 9.
    Oliveira, V., Lotufo, R.: A Study on Connected Components Labeling algorithms using GPUs. Undergraduate Work (2010),
  10. 10.
    O’Connell, S.: A GPU Implementation of Connected Component Labeling. Masters Thesis, White Paper (2009),
  11. 11.
    Danielsson, P.: Euclidean distance mapping. Computer Graphics and Image Processing 14, 227–248 (1980)CrossRefGoogle Scholar
  12. 12.
    Rong, G., Tan, T.: Jump flooding in GPU with applications to Voronoi diagram and distance transform. In: Proceedings of the 2006 Symposium on Interactive 3D Graphics and Games, pp. 109–116. ACM (2006)Google Scholar
  13. 13.
    The GIMP Team: Gnu image manipulation program - maze plugin. Open Source (2013),
  14. 14.
    Top Coder: Top coder connected components challenge. Dataset, Online (2010),

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • A. Rasmusson
    • 1
    • 2
  • T. S. Sørensen
    • 1
  • G. Ziegler
    • 3
  1. 1.Computer ScienceAarhus UniversityDenmark
  2. 2.Stereology and EM LaboratoryAarhus UniversityDenmark
  3. 3.Nvidia Corp.USA

Personalised recommendations