Pixel Coverage Segmentation for Improved Feature Estimation

  • Nataša Sladoje
  • Joakim Lindblad
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5716)


By utilizing intensity information available in images, partial coverage of pixels at object borders can be estimated. Such information can, in turn, provide more precise feature estimates. We present a pixel coverage segmentation method which assigns pixel values corresponding to the area of a pixel that is covered by the imaged object(s). Starting from any suitable crisp segmentation, we extract a one-pixel thin 4-connected boundary between the observed image components where a local linear mixture model is used for estimating fractional pixel coverage values. We evaluate the presented segmentation method, as well as its usefulness for subsequent precise feature estimation, on synthetic test objects with increasing levels of noise added. We conclude that for reasonable noise levels the presented method outperforms the achievable results of a perfect crisp segmentation. Finally, we illustrate the application of the suggested method on a real histological colour image.


Segmentation Method Partial Coverage Feature Estimation Voronoi Region Mixed Pixel 
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.


  1. 1.
    Bousion, N., Hatt, M., Reilhac, A., Visvikis, D.: Fully automated partial volume correction in PET based on a wavelet approach without the use of anatomical information. In: Proc. of IEEE Nuclear Science Symposium, pp. 2812–2816. IEEE Society, Los Alamitos (2007)Google Scholar
  2. 2.
    Choi, H.S., Haynor, D.R., Kim, Y.: Partial volume tissue classification of multichannel magnetic resonance images - a mixed model. IEEE Trans. on Medical Imaging 10(3), 395–407 (1991)CrossRefGoogle Scholar
  3. 3.
    Foody, G.M., Lucas, R.M., Curran, P.H., Honzak, M.: Non-linear mixture modeling without end-members using an artificial neural network. Int. Journal of Remote Sensing 18(4), 937–953 (1997)CrossRefGoogle Scholar
  4. 4.
    Jua, J., Kolaczykb, E.D., Gopa, S.: Gaussian mixture discriminant analysis and sub-pixel land cover characterization in remote sensing. Remote Sensing and Environment 84(4), 550–560 (2003)CrossRefGoogle Scholar
  5. 5.
    Leemput, K.V., Maes, F., Vandermeulen, D., Suetens, P.: A unifying framework for partial volume segmentation of brain MR images. IEEE Trans. on Medical Imaging 22(1), 105–119 (2003)CrossRefzbMATHGoogle Scholar
  6. 6.
    Niessen, W.J., Vincken, K.L., Weickert, J., ter Haar Romeny, B.M., Viergever, M.A.: Multiscale segmentation of three-dimensional MR brain images. International Journal of Computer Vision 31(2/3), 185–202 (1999)CrossRefGoogle Scholar
  7. 7.
    Sarve, H., Johansson, C.B., Lindblad, J., Borgefors, G., Franke Stenport, V.: Quantification of bone remodeling in the proximity of implants. In: Kropatsch, W.G., Kampel, M., Hanbury, A. (eds.) CAIP 2007. LNCS, vol. 4673, pp. 253–260. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  8. 8.
    Sladoje, N., Lindblad, J.: Estimation of moments of digitized objects with fuzzy borders. In: Roli, F., Vitulano, S. (eds.) ICIAP 2005. LNCS, vol. 3617, pp. 188–195. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  9. 9.
    Sladoje, N., Lindblad, J.: High-precision boundary length estimation by utilizing gray-level information. IEEE Trans. on Pattern Analysis and Machine Intelligence 32(2), 357–363 (2009)CrossRefGoogle Scholar
  10. 10.
    Souza, A., Udupa, J.K., Saha, P.K.: Volume rendering in the presence of partial volume effects. IEEE Trans. on Medical Imaging 24(2), 223–235 (2005)CrossRefGoogle Scholar
  11. 11.
    Verbeiren, S., Eerens, H., Piccard, I., Bauwens, I., Van Orshoven, J.: Sub-pixel classification of SPOT-VEGETATION time series for the assessment of regional crop areas in Belgium. Int. Journal of Applied Earth Observation and Geoinformation 10(4), 486–497 (2008)CrossRefGoogle Scholar
  12. 12.
    Vincken, K.L., Koster, A.S., Viergever, M.A.: Probabilistic segmentation of partial volume voxels. Pattern Recognition Letters 15, 477–484 (1994)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Nataša Sladoje
    • 1
  • Joakim Lindblad
    • 2
  1. 1.Faculty of EngineeringUniversity of Novi SadSerbia
  2. 2.Centre for Image Analysis, SLUUppsalaSweden

Personalised recommendations