Programming and Computer Software

, Volume 34, Issue 3, pp 173–182 | Cite as

Segmentation of small objects in color images



A method for effective segmentation of small objects in color images is presented. It can be used jointly with region growing algorithms. Segmentation of small objects in color images is a difficult problem because their boundaries are close to each other. The proposed algorithm accurately determines the location of the boundary points of closely located small objects and finds the skeletons (seed regions) of those objects. The method makes use of conditions obtained by analyzing the change of color characteristics of the edge pixels along the direction that is orthogonal to the boundaries of adjacent objects. These conditions are generalized for the case of the well-known class of color images having misregistration artifacts. If high-quality seed regions are available, the final segmentation can be performed using one of the region growing methods. The segmentation algorithm based on the proposed method was tested using a large number of color images, and it proved to be very efficient.


Color Image Small Object Seed Region Optical Character Recognition Gradient Image 
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.
    Sezgin, M. and Sankur, B., Survey over Image Thresholding Techniques, J. Electron. Imaging, 2004, vol. 13 no. 1, pp. 146–165.CrossRefGoogle Scholar
  2. 2.
    Cheng, H.D., Jiang, X.H., Sun, Y., and Wang, J., Color Image Segmentation: Advances and Prospects, Pattern Recognit., 2001, vol. 34, no. 12, pp. 2259–2281.MATHCrossRefGoogle Scholar
  3. 3.
    Lucchese, L. and Mitra, S.K., Color Image Segmentation: A State-of-the-Art Survey, Proc. of the Indian National Sci. Academy (INSA_A), Image Process. Vision, Pattern Recognit., 2001, vol. 67A, no. 2, pp. 207–221.Google Scholar
  4. 4.
    Skarbek, W. and Koschan, A., Colour Image Segmentation—A Survey, Technical Report of the Berlin Technical University, Berlin, 2004.Google Scholar
  5. 5.
    Plataniotis, K.N. and Venetsanopoulos, D.T., Color Image Processing and Applications (Digital Signal Processing), Springer, Berlin, 2000.Google Scholar
  6. 6.
    R. C. Gonzalez and R. E. Woods, Digital Image Processing (Prentice-Hall, Upper Saddle River, N.J., 2002).Google Scholar
  7. 7.
    Chung, R.H.Y, Yung, N.H.C, and Cheung, P.Y.S., An Efficient Parameterless Quadrilateral-Based Image Segmentation Method, IEEE Trans. Pattern Anal. Mach. Intell., 2005, vol. 27, no. 9, pp. 1446–1458.CrossRefGoogle Scholar
  8. 8.
    O’Callaghan, R.J. and Bull, D.R., Combined Morphological-Spectral Unsupervised Image Segmentation, IEEE Trans. Image Process., 2005, vol. 14, no. 1, pp. 49–62.CrossRefGoogle Scholar
  9. 9.
    Hubel, D.H., Exploration of the Primary Visual Cortex, 1955–1978, Nature, 1982, vol. 299, pp. 515–524.CrossRefGoogle Scholar
  10. 10.
    White, J.M. and Rohrer, G.D., Image Thresholding for Optical Character Recognition and Other Applications Requiring Character Image Extraction, IBM J. Res. Dev., 1983, vol. 27, no. 4, pp. 400–411.CrossRefGoogle Scholar
  11. 11.
  12. 12.
    Beucher, S., The Watershed Transformation Applied to Image Segmentation, in Proc. 10th Pfefferkorn Conf. on Signal and Image Processing in Microscopy and Microanalysis, Cambridge, UK, 1991, Scanning Microscopy Int., 1996, Suppl. 6, pp. 299–314.Google Scholar
  13. 13.
    Hojjatoleslami, S.A. and Kittler, J., Region Growing: A New Approach, IEEE Trans. Image Process., 1998, vol. 7, no. 7, pp. 1079–1084.CrossRefGoogle Scholar
  14. 14.
    Adams, R. and Bischof, L., Seeded Region Growing, IEEE Trans. Pattern Anal. Mach. Intell., 1994, vol. 16, no. 6, pp. 641–647.CrossRefGoogle Scholar
  15. 15.
    Mehnert, A.J.H. and Jackway, P.T., An Improved Seeded Region Growing Algorithm, Pattern Recognit. Lett., 1997, vol. 18, no. 10, pp. 1065–1071.CrossRefGoogle Scholar
  16. 16.
    Fan, J., Yau, D.K.Y., Elmagarmid, A.K., and Aref, W.G., Automatic Image Segmentation by Integrating Color-Edge Extraction and Seeded Region Growing, IEEE Trans. Image Process., 2001, vol. 10, no. 10, pp. 1454–1466.MATHCrossRefGoogle Scholar
  17. 17.
    Wan, S.Y. and Higgins, W.E., Symmetric Region Growing, IEEE Trans. Image Process., 2003, vol. 12, no. 9, pp. 1007–1015.CrossRefGoogle Scholar
  18. 18.
    Levner, I. and Zhang, H., Classification-Driven Watershed Segmentation, IEEE Trans. Image Process., 2007, vol. 16, no. 5, pp. 1437–144.CrossRefMathSciNetGoogle Scholar
  19. 19.
    Jung, C.R., Combining Wavelets and Watersheds for Robust Multiscale Image Segmentation, Image Vision Comput., 2007, vol. 25, no. 1, pp. 24–33.CrossRefGoogle Scholar
  20. 20.
    Shih, F.Y. and Cheng, S., Automatic Seeded Region Growing for Color Image Segmentation, Image Vision Comput., 2005, vol. 23, no. 10, pp. 877–886.CrossRefGoogle Scholar
  21. 21.
    Beucher, S. and Meyer, F. The Morphological Approach to Segmentation: The Watershed Transformation, Mathematical Morphology in Image Processing, Dougherty, E.R., Ed., New York: Marcel Dekker, 1992, pp. 433–481.Google Scholar
  22. 22.
    Zenzo, N.D., A Note on the Gradient of a Multi-Image, Comput. Vision, Graphics, Image Process., 1986, vol. 33, pp. 116–125.CrossRefGoogle Scholar
  23. 23.
    Comaniciu, D. and Meer, P., Mean Shift: A Robust Approach toward Feature Space Analysis, IEEE Trans. Pattern Anal. Mach. Intell., 2002, vol. 24, no. 5, pp. 603–619.CrossRefGoogle Scholar
  24. 24.
  25. 25.
    Digital Color Imaging Handbook, Sharma, G., Ed., Boca Raton, Fl.: CRC, 2003, ch. 7, pp. 491–558.Google Scholar

Copyright information

© MAIK Nauka 2008

Authors and Affiliations

  1. 1.Institute of System AnalysisRussian Academy of SciencesMoscowRussia
  2. 2.Kharkevich Institute of Problems of Data TransmissionRussian Academy of SciencesMoscowRussia

Personalised recommendations