Pattern Recognition and Image Analysis

, Volume 24, Issue 4, pp 502–505 | Cite as

Optimal feature space for semantic image segmentation

Representation, Processing, Analysis and Understanding of Images


A new method for semantic segmentation with object adaptation is proposed. Segmentation is performed on a feature map obtained as a weighted sum of HSV-space components: hue, saturation, and- value. Homogeneity criterion for grouping pixels into clusters and weighted sum coefficients is adjusted using the particle swarm optimization (PSO) algorithm. The method is tested using images wherein a face is a semantically meaningful object. The accuracy of the segmentation is shown to be higher when using a feature map obtained as a weighted sum of color components than in cases when a single color component is used. The accuracy of the proposed method is estimated as the correspondence of a fragmented segment to a face region, detected using the Viola-Jones method, within an image.


semantic segmentation feature spaces optimization 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    B. Basturk and D. Karaboga, “An Artificial Bee Colony (ABC) algorithm for numeric function optimization,” in Proc. IEEE Swarm Intelligence Symp. (Indianapolis, 2006).Google Scholar
  2. 2.
    D. Marr, Vision: A Computational Investigation into the Human Representation and Pro-cessing of Visual Information (Henry Holt and Co., New York, 1982).Google Scholar
  3. 3.
    E. Borenstein and S. Ullman, “Combined topdown/bottom-up segmentation,” IEEE Trans. Pattern Anal. Mach. Intellig. 30(12), 2109–2125 (2008).CrossRefGoogle Scholar
  4. 4.
    H. G. Barrow and R. J. Popplestone, “Relational descriptions in picture processing,” Mach. Intellig. 1, 377–396 (1971).Google Scholar
  5. 5.
    H. Derek, A. A. Efros, and M. Herbert, “Geometric context from a single image,” in Proc. 10th Int. IEEE Conf. on Computer Vision ICCV 2005 (Beijing, 2005), Vol. 1.Google Scholar
  6. 6.
    J. Carreira and C. Sminchisescu, “Constrained parametric min-cuts for automatic object segmentation,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (San Francisco, 2010).Google Scholar
  7. 7.
    Luccheseyz, L. and S. K. Mitray, “Color image segmentation: A state-of-the-art survey,” in Proc. Indian National Science Academy (INSA-A) (Natl. Sci. Acad., Delhi, 2001), pp. 207–221.Google Scholar
  8. 8.
    M. Piccardi, Background Substractio Techniques: A Review (Comput. Vision Research Group (CVRG), University of Technology, Sydney (UTS), 2004).Google Scholar
  9. 9.
    P. A. Viola and M. J. Jones, “Robust real-time face detection,” Int. J. Comput. Vision 57(2), 137–154 (2004).CrossRefGoogle Scholar
  10. 10.
    S. Anishenko, D. Shaposhnikov, R. Comley, and X. Gao, “A colour based approach for face segmentation from video images under low luminance levels,” in Proc. 11th IASTED Int. Conf. on Computer Graphics and Imaging (CGIM 2010) (Innsbruck, 2010), pp. 184–189.Google Scholar
  11. 11.
    V. Sara, C. Rother, and V. Kolmogorov, “Object cosegmentation,” in Proc. Comput. Vision Pattern Recogn. Conf. (CVPR) (Colorado Springs, 2011).Google Scholar

Copyright information

© Pleiades Publishing, Ltd. 2014

Authors and Affiliations

  1. 1.Kogan Research Institute for Neurocybernetics at the Southern Federal UniversityRostov-on-DonRussia

Personalised recommendations