Advertisement

How Do Superpixels Affect Image Segmentation?

  • Allan Hanbury
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5197)

Abstract

Computationally intensive segmentation algorithms often operate on an image pre-segmented into small regions referred to as “superpixels”. We investigate the effect of the choice of the pre-segmentation algorithm and its parameters on the outcome of the final segmentation. Three pre-segmentation algorithms are compared. To avoid the particularities of sophisticated segmentation algorithms, the final segmentations are built using agglomerative hierarchical clustering. These segmentations are evaluated using 300 images from the Berkeley Segmentation Dataset. This leads to useful insights about the variations in the final segmentation caused by the choice of the pre-segmentation algorithm.

Keywords

image segmentation clustering segmentation evaluation 

References

  1. 1.
    Keuchel, J., Heiler, M., Schnörr, C.: Hierarchical image segmentation based on semidefinite programming. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 120–128. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  2. 2.
    Mičušík, B., Pajdla, T.: Multi-label image segmentation via max-sum solver. In: Proc. of the Conf. on Computer Vision and Pattern Recognition (CVPR) (2007)Google Scholar
  3. 3.
    Ren, X., Malik, J.: Learning a classification model for segmentation. In: International Conference on Computer Vision, pp. 10–17 (2003)Google Scholar
  4. 4.
    Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. IEEE Trans. on PAMI 24, 603–619 (2002)CrossRefGoogle Scholar
  5. 5.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. on PAMI 22(8), 888–905 (2000)CrossRefGoogle Scholar
  6. 6.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. International Journal of Computer Vision 59(2), 167–181 (2004)CrossRefGoogle Scholar
  7. 7.
    Meyer, F.: An overview of morphological segmentation. International Journal of Pattern Recognition and Artificial Intelligence 15(7), 1089–1118 (2001)CrossRefGoogle Scholar
  8. 8.
    Stawiaski, J., Decenciére, E.: Region merging via graph-cuts. Image Analysis and Stereology 27(1), 39–45 (2008)CrossRefzbMATHGoogle Scholar
  9. 9.
    Jain, A.K., Dubes, R.C.: Algorithms for Clustering Data. Prentice-Hall, Englewood Cliffs (1988)zbMATHGoogle Scholar
  10. 10.
    Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proc. 8th Int’l Conf. Computer Vision, vol. II, pp. 416–423 (2001)Google Scholar
  11. 11.
    Soille, P.: Morphological Image Analysis, 2nd edn. Springer, Heidelberg (2002)zbMATHGoogle Scholar
  12. 12.
    Meyer, F.: Graph based morphological segmentation. In: Proceedings of the second IAPR-TC-15 Workshop on Graph-based Representations, pp. 51–60 (1999)Google Scholar
  13. 13.
    Angulo, J., Serra, J.: Color segmentation by ordered mergings. In: Proc. of the Int. Conf. on Image Processing, vol. II, pp. 125–128 (2003)Google Scholar
  14. 14.
    Meyer, F.: Levelings, image simplification filters for segmentation. Journal of Mathematical Imaging and Vision 20, 59–72 (2004)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Poynton, C.: A Technical Introduction to Digital Video. Wiley, New York (1996)Google Scholar
  16. 16.
    Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(5), 530–549 (2004)CrossRefGoogle Scholar
  17. 17.
    Mahy, M., van Eyckden, L., Oosterlinck, A.: Evaluation of uniform color spaces developed after the adoption of CIELAB and CIELUV. Color Res. Appl. 19(2), 105–121 (1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Allan Hanbury
    • 1
  1. 1.Pattern Recognition and Image Processing Group, Institute of Computer-Aided AutomationVienna University of TechnologyViennaAustria

Personalised recommendations