Blood Cell Segmentation Using Minimum Area Watershed and Circle Radon Transformations

  • F Boray Tek
  • Andrew G. Dempster
  • Izzet Kale
Part of the Computational Imaging and Vision book series (CIVI, volume 30)


In this study, a segmentation method is presented for the images of microscopic peripheral blood which mainly contain red blood cells, some of which contain parasites, and some white blood cells. The method uses several operators based on mathematical morphology. The cell area information which is estimated using the area granulometry (area pattern spectrum) is used for several steps in the method. A modified version of the original watershed algorithm [31] called minimum area watershed transform is developed and employed as an initial segmentation operator. The circle Radon transform is applied to the labelled regions to locate the cell centers (markers). The final result is produced by applying the original marker controlled watershed transform to the Radon transform output with its markers obtained from the regional maxima. The proposed method can be applied to similar blob object segmentation problems by adapting red blood cell characteristics for the new blob objects. The method has been tested on a benchmark set and scored a successful correct segmentation rate of 95.40%.


Blood cell watershed area granulometry minimum area watershed transform (MAWT) circle Radon Transform (CRT) 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    M.C. De Andrade, G. Bertrand, and A.A. Araujo. Segmentation of microscopic images by flooding simulation: A catchment basins merging algorithm. In Proc. of the Society for Imaging and PhotoOptical Engineering. SPIE, 1997.Google Scholar
  2. [2]
    J. Angulo and G. Flandrin. Automated detection of working area of peripheral blood smears using mathematical morphology. A. Cellular Pathology, 25(1):37–49, 2003.Google Scholar
  3. [3]
    E.J. Breen and R. Jones. Attribute openings, thinnings, and granulometries. CVIU, 64:377–389, 1996.Google Scholar
  4. [4]
    A. Cosio, F. M. Flores, J. A. P. Castaneda, M. A. Solano, and S. Tato. Automatic counting of immunocytochemically stained cells. In Proc. 25th Annual Int. Conf. IEEE, Engineering in Medicine and Biology Society, pages 790–793, 2003.Google Scholar
  5. [5]
    E.R. Davies. Finding ellipses using the generalised hough transform. PRL, 9:87–96, 1989.Google Scholar
  6. [6]
    C. di Ruberto, A. Dempster, S. Khan, and B. Jarra. Segmentation of blood images using morphological operators. In ICPROO, pages Vol III: 397–400, 2000.Google Scholar
  7. [7]
    C. di Ruberto, A. Dempster, S. Khan, and B. Jarra. Analysis of infected blood cell images using morphological operators. IVC, 20(2):133–146, February 2002.CrossRefGoogle Scholar
  8. [8]
    R. O. Duda and P. E. Hart. Use of the hough transformation to detect lines & curves in pictures. Comm. ACM, 15(1), 1972.Google Scholar
  9. [9]
    N. Guil and E. L. Zapata. Lower order circle and ellipse hough transform. Pattern Recognition, 30:1729–1744, 1997.CrossRefGoogle Scholar
  10. [10]
    K. V. Hansen and P. A. Toft. Fast curve estimation using preconditioned generalized radon transform. IEEE Trans. on Image Processing, 5(12):1651–1661, 1996.CrossRefGoogle Scholar
  11. [11]
    C. L. Hendriks, M. van Ginkel, P.W. Verbeek, and L.J. van Vliet. The generalised radon transform: Sampling and memory considerations. In Proc. of CAIP2003, Groningen, Netherlands. Springer Verlag, 2003.Google Scholar
  12. [12]
    J. Illingworth and J. Kittler. Survey, a survey of the hough transform. Computer Vis. Graph. and Img. Processing, 44:87–116, 1988.CrossRefGoogle Scholar
  13. [13]
    V. F. Leavers. Use of the two-dimensional radon transform to generate a taxonomy of shape for the characterization of abrasive powder particles. IEEE Trans. on PAMI, 22(12):1411–1423, 2000.Google Scholar
  14. [14]
    O. Lezoray and H. Cardot. Bayesian marker extraction for color watershed in segmenting microscopic images. In Proc. Pattern Recognition, volume 1, pages 739–742, 2002.Google Scholar
  15. [15]
    Q. Liao and Y. Deng. An accurate segmentation method for white blood cell images. In Proc. IEEE Int. Symp. on Biomedical Imaging, pages 245–248, 2002.Google Scholar
  16. [16]
    P. Maragos. Pattern spectrum and multiscale shape representation. IEEE Trans. PAMI., 2:701–716, 1989.Google Scholar
  17. [17]
    R.A. Mclaughlin. Randomized hough transform: Improved ellipse detection with comparison. Pattern Recognition Letters, 19(3–4):299–305, March 1998.CrossRefGoogle Scholar
  18. [18]
    A. Meijster and M.H.F. Wilkinson. Fast computation of morphological area pattern spectra. In ICIPO1, pages III: 668–671, 2001.Google Scholar
  19. [19]
    F. Meyer and S. Beucher. Morphological segmentation. J. Vis. Comms. Image Represent., 1:21–46, 1990.CrossRefGoogle Scholar
  20. [20]
    L. Najman and M. Schmitt. Geodesic saliency of watershed contours and hierarchical segmentation. IEEE Trans. PAMI, 18:1163–1173, 1996.Google Scholar
  21. [21]
    J. Park and J. M. Keller. Snakes on the watershed. IEEE Trans. PAMI., 23(10):1201–1205, 2001.Google Scholar
  22. [22]
    KNR M. Rao. Application of Mathematical Morphology to Biomedical Image Processing. PhD thesis, U. Westminster, 2004.Google Scholar
  23. [23]
    KNR M. Rao and A. Dempster. Area-granulometry: an improved estimator of size distribution of image objects. Electronics Letters, 37:50–951, 2001.CrossRefGoogle Scholar
  24. [24]
    KNR M. Rao and A. Dempster. Modification on distance transform to avoid over-segmentation and under-segmentation. In Proc. VIPromCom-2002, Croatia, pages 295–301, 2002.Google Scholar
  25. [25]
    J.E Rivest, P. Soille, and S. Beucher. Morphological gradients. Journal of Electronic Imaging, 2(4), 1993.Google Scholar
  26. [26]
    P. Soille. Morphological Image Analysis. Springer-Verlag, Heidelberg, 2003.Google Scholar
  27. [27]
    C. Vachier and F. Meyer. Extinction value: a new measurement of persistence. In IEEE Workshop on Nonlinear Signal and Image Processing, pages 254–257, 1995.Google Scholar
  28. [28]
    M. van Ginkel, C.L. Luengo Hendriks, and L.J. van Vliet. A short introduction to the radon and hough transforms and how they relate to each other. Technical report, Quantitative Imaging Group, Delft University of Technology, 1997.Google Scholar
  29. [29]
    L. Vincent. Morphological area openings and closings for greyscale images. In Proc. NATO Shape in Picture Workshop, pages 197–208. Springer Verlag, 1992.Google Scholar
  30. [30]
    L. Vincent. Granulometries and opening trees. Fundamenta Informaticae, 41:57–90, 2000.Google Scholar
  31. [31]
    L. Vincent and P. Soille. Watersheds in digital spaces: An efficient algorithm based on immersion simulations. IEEE Trans. PAMI., vol. 13, pp. 583–598, June 1991, 13:583–598, 1991.Google Scholar
  32. [32]
    S.E. Volkova, N.Yu Ilyasova, A.V Ustinov, and A.G Khramov. Methods for analysing the images of blood preparations. Optics & Laser Technology, 27(2):255–261, 1995.Google Scholar

Copyright information

© Springer 2005

Authors and Affiliations

  • F Boray Tek
    • 1
  • Andrew G. Dempster
    • 1
  • Izzet Kale
    • 1
  1. 1.Applied DSP and VLSI Research GroupUniversity of WestminsterWestminster

Personalised recommendations