| Peer-Reviewed

Processing Overlapped Cells Using K-Means and Watershed

Received: 30 April 2014     Accepted: 17 May 2014     Published: 30 May 2014
Views:       Downloads:
Abstract

Processing overlapped cells are tricky process especially when an automatic computerized system deals with 2D images of cells needed to be processed in biomedical filed, if these cells are overlapped this might give the impression and wrong indication of abnormality presence. In this paper a methodology are suggested and implemented to separate the overlapped from non-overlapped cells giving as a result two groups (clusters) for each. And we try to give an estimation of numbers of cells that overlapped under the microscope, the success rates of separating the two clusters (overlapped and non overlapped cells) are 100% while the success rate of the estimating the number of correct cells that overlapped compared with medical personal point view are 79.3%.

Published in International Journal of Intelligent Information Systems (Volume 3, Issue 1)
DOI 10.11648/j.ijiis.20140301.12
Page(s) 8-12
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2014. Published by Science Publishing Group

Keywords

Image Processing, K-Means, Blood Cells, Clustering, Watershed

References
[1] J. H. Carr, Bernadette F. Rodak, Clinical hematology Atlas, Saunders Elsevier, 3rd Ed, 2009, pp.222-230.
[2] S. Theo-doridis and K. Koutroumbs, " Pattern Recognition," Elsevier Inc.Academic Press, 4th Ed, 2009.
[3] G. Karkavitsas and M. Rangoussi, "Object Localization in medical images using genetic algorithm, " World academy of Science, Engineering and Tech-nology, vol. 2, pp. 6-9, Feb. 2005.
[4] P.J.H. Bronkorsta a, M.J.T. Reinders b, E.A. Hendriks b, J. Grimbergen a, R.M. Heethaar c, G.J. Brakenho, "On-line detection of red blood cell shape using deformable Templates, " Elsevier Science, vol. 3, pp. 413-424, Jan. 2000.
[5] E. Ozcan and C. K. Mohan, " Partial shape matching using genetic algorithms, " Elsevier Science, vol.18, Oct. 1997.
[6] M. Rizon, H.Yazid, P. Saad, A. Yeon Md Shakaff, A. Saad , M. Sugisaka, S. Yaacob, M.Rozailan Mamat and M. Karthigayan. " Object Detection using Circular Hough Transform," American Journal of Applied Sciences, vol.12, pp 1606-1609, Jan. 2005.
[7] K. Fukui and O. Yamaguchi, "Facial feature points extraction method based on combination of shape extraction and pattern matching," Trans. IEICE, Vol.8, pp.2170-2177, 1997.
[8] J. MacQueen. "Some methods for classification and analysis of multivariate observations". Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, pages 281–297, 1967
[9] SPSS Clementine Data Mining System. User Guide Version 5, 1998 (Integral Solutions Limited, Basingstoke, Hampshire).
[10] DataEngine 3.0 – Intelligent Data Analysis – an Easy Job, Management Intelligenter Technologien GmbH, Germany, 1998; http://www.mitgmbh.de.
[11] Kerr, A., Hall, H. K., and Kozub, S. Doing Statistics with SPSS, 2002 (Sage, London).
[12] S-PLUS 6 for Windows Guide to Statistics, Vol. 2, Insightful Corporation, Seattle, Washington, 2001; http://www.insightful.com/DocumentsLive/23/44/statman2.pdf.
[13] W. Barbakh, Ying Wu, and Colin Fyfe. "Non-standard parameter adaptation for exploratory data analysis" (2009), Uni-versity of the west of Scotland, Scotland ISBN: 978-3-642-04004-7.
[14] Allaoui, A. E. (2012). Medical Image Segmentation by Marker-Controlled Watershed and Mathematical Morphology. International Journal of Multiledia and Its Applications (IJMA), 1-9
[15] Ng, H. P. (2006). Medical Image Segmentation using K-Means Clustering and Improved Watershed Algorithm. Image Analysis and Interpretation, 2006 IEEE (pp. 61-65). Symposium: IEEE.
[16] Zhang, X. (2010). An Image Segmentation Method Based on Improved Watershed Algorithm. International Conference on Computational and Information Sciences (pp. 258-261). Chengdu, China: IEEE
[17] R. Gonzalez and R. Woods Digital Image Processing, Addison-Wesley Publishing Company, 1992, pp 518 – 548.
[18] G. Borgefors. Hierarchical chamfer matching: A parametric edge matching algorithm. IEEE Transactions on Pattern Analysis and Machine Intelligence, 10(6):849–865, November 1988.
[19] D. Huttenlocher, G. Klanderman, and W. Rucklidge. Comparing images using the hausdorff distance. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(9):850–863, September 1993.
[20] H. Blum. Biological shape and visual science. Theorerical Biology, 38:205–287, 1973.
Cite This Article
  • APA Style

    Faten Faraj Abushmmala, Fadwa Faraj Abushmmala. (2014). Processing Overlapped Cells Using K-Means and Watershed. International Journal of Intelligent Information Systems, 3(1), 8-12. https://doi.org/10.11648/j.ijiis.20140301.12

    Copy | Download

    ACS Style

    Faten Faraj Abushmmala; Fadwa Faraj Abushmmala. Processing Overlapped Cells Using K-Means and Watershed. Int. J. Intell. Inf. Syst. 2014, 3(1), 8-12. doi: 10.11648/j.ijiis.20140301.12

    Copy | Download

    AMA Style

    Faten Faraj Abushmmala, Fadwa Faraj Abushmmala. Processing Overlapped Cells Using K-Means and Watershed. Int J Intell Inf Syst. 2014;3(1):8-12. doi: 10.11648/j.ijiis.20140301.12

    Copy | Download

  • @article{10.11648/j.ijiis.20140301.12,
      author = {Faten Faraj Abushmmala and Fadwa Faraj Abushmmala},
      title = {Processing Overlapped Cells Using K-Means and Watershed},
      journal = {International Journal of Intelligent Information Systems},
      volume = {3},
      number = {1},
      pages = {8-12},
      doi = {10.11648/j.ijiis.20140301.12},
      url = {https://doi.org/10.11648/j.ijiis.20140301.12},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijiis.20140301.12},
      abstract = {Processing overlapped cells are tricky process especially when an automatic computerized system deals with 2D images of cells needed to be processed in biomedical filed, if these cells are overlapped this might give the impression and wrong indication of abnormality presence. In this paper a methodology are suggested and  implemented to separate the overlapped from non-overlapped cells giving as a result two groups (clusters) for each. And we try to give an estimation of  numbers of cells that overlapped under the microscope, the success rates of separating the two clusters (overlapped and non overlapped cells) are 100% while the success rate of the estimating the number of correct cells that overlapped compared with medical personal point view are 79.3%.},
     year = {2014}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Processing Overlapped Cells Using K-Means and Watershed
    AU  - Faten Faraj Abushmmala
    AU  - Fadwa Faraj Abushmmala
    Y1  - 2014/05/30
    PY  - 2014
    N1  - https://doi.org/10.11648/j.ijiis.20140301.12
    DO  - 10.11648/j.ijiis.20140301.12
    T2  - International Journal of Intelligent Information Systems
    JF  - International Journal of Intelligent Information Systems
    JO  - International Journal of Intelligent Information Systems
    SP  - 8
    EP  - 12
    PB  - Science Publishing Group
    SN  - 2328-7683
    UR  - https://doi.org/10.11648/j.ijiis.20140301.12
    AB  - Processing overlapped cells are tricky process especially when an automatic computerized system deals with 2D images of cells needed to be processed in biomedical filed, if these cells are overlapped this might give the impression and wrong indication of abnormality presence. In this paper a methodology are suggested and  implemented to separate the overlapped from non-overlapped cells giving as a result two groups (clusters) for each. And we try to give an estimation of  numbers of cells that overlapped under the microscope, the success rates of separating the two clusters (overlapped and non overlapped cells) are 100% while the success rate of the estimating the number of correct cells that overlapped compared with medical personal point view are 79.3%.
    VL  - 3
    IS  - 1
    ER  - 

    Copy | Download

Author Information
  • Computer Science Engineering Department, Islamic University (IUG),Gaza, Palestine

  • Industrial Engineering Department, Islamic University (IUG),Gaza, Palestine

  • Sections