A Faster Graph-Based Segmentation Algorithm with Statistical Region Merge

  • Ahmed Fahad
  • Tim Morris
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4292)


The paper presents a modification of a bottom up graph theoretic image segmentation algorithm to improve its performance. This algorithm uses Kruskal’s algorithm to build minimum spanning trees for segmentation that reflect global properties of the image: a predicate is defined for measuring the evidence of a boundary between two regions and the algorithm makes greedy decisions to produce the final segmentation. We modify the algorithm by reducing the number of edges required for sorting based on two criteria. We also show that the algorithm produces an over segmented result and suggest a statistical region merge process that will reduce the over segmentation. We have evaluated the algorithm by segmenting various video clips Our experimental results indicate the improved performance and quality of segmentation.


Image Segmentation Segmentation Algorithm Minimum Span Tree Edge Weight Colour Channel 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. on Pattern Analysis and Machine Intelligence 22, 888–905 (2000)CrossRefGoogle Scholar
  2. 2.
    Sharon, E., Brandt, A., Basri, R.: Fast multiscale image segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 70–77 (2000)Google Scholar
  3. 3.
    Cour, T., Benezit, F., Shi, J.: Spectral segmentation with multiscale graph decomposition. In: IEEE Conf. on Computer Vision and Pattern Recognition, vol. 2, pp. 1124–1131 (2005)Google Scholar
  4. 4.
    Macaire, L., Vandenbroucke, N., Postaire, J.-G.: Color image segmentation by analysis of subset connectedness and color homogeneity properties. Computer Vision and Image Understanding 102, 105–116 (2006)CrossRefGoogle Scholar
  5. 5.
    Deng, Y., Manjunath, B.S., Shin, H.: Color Image Segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 446–451 (1999)Google Scholar
  6. 6.
    Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence 24, 603–619 (2002)CrossRefGoogle Scholar
  7. 7.
    Sun, H., Yang, J., Ren, M.: A fast watershed algorithm based on chain code and its application in image segmentation. Pattern Recognition Letters 26, 1266–1274 (2005)CrossRefGoogle Scholar
  8. 8.
    Adams, R., Bischof, L.: Seeded region growing. IEEE Transactions on Pattern Analysis and Machine Intelligence 16, 641–647 (1994)CrossRefGoogle Scholar
  9. 9.
    Shih, F.Y., Cheng, S.: Automatic seeded region growing for color image segmentation. Image and Vision Computing 23, 877–886 (2005)CrossRefGoogle Scholar
  10. 10.
    Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. Int. J. of Computer Vision 59, 167–181 (2004)CrossRefGoogle Scholar
  11. 11.
    Haxhimusa, Y., Kropatsch, W.: Segmentation graph hierarchies. In: Joint IAPR Int. Workshops SSPR and SPR, pp. 343–351. Springer, Heidelberg (2004)Google Scholar
  12. 12.
    Forsyth, D.A., Ponce, J.: Computer vision a modern approach. Prentice Hall, Englewood Cliffs (2003)Google Scholar
  13. 13.
    Nock, R., Nielsen, F.: Statistical region merge. IEEE Trans. on Pattern Analysis and Machine Intelligence 26, 1452–1458 (2004)CrossRefGoogle Scholar
  14. 14.
    Zhang, Y.J.: A survey on evaluation methods for image segmentation. Pattern Recognition 29, 1335–1346 (1996)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ahmed Fahad
    • 1
  • Tim Morris
    • 1
  1. 1.School of InformaticsUniversity of ManchesterManchesterUK

Personalised recommendations