Multimedia Tools and Applications

, Volume 77, Issue 24, pp 31525–31543 | Cite as

High precision image segmentation algorithm using SLIC and neighborhood rough set

  • Xinlin Xie
  • Gang XieEmail author
  • Xinying Xu


A high precision image segmentation algorithm using SLIC and neighborhood rough set is proposed. The algorithm mainly includes two stages: the stage of superpixel generation and the mergence stage based on neighborhood rough set. In superpixel generation stage, based on L-channel color histogram and its peak, the scheme of initial superpixel number generation is proposed according to the complexity of the image itself. For inaccuracy segmentation edge of SLIC caused by isolated pixels, the compactness factor is appropriately increased before they are generated. After that, the scheme of reclassifying each isolated pixel is proposed just relying on the color space. In superpixel mergence stage based on neighborhood rough set, the texture information using the gray level co-occurrence matrix is introduced into the feature representation of superpixel. It can reduce the dependence of color feature and improve the accuracy of the mergence. By constructing the information table, the neighborhood granule of each superpixel is acquired under the neighborhood threshold. Finally, the superpixels within the neighborhood granule are merged on the basis of the spatial adjacency between superpixels. In Berkeley segmentation data set, compared with the SLIC algorithm, the schemes of initial superpixel number generation and the isolated pixels processing are proved to be effective. Furthermore, the experiments demonstrate that the proposed algorithm can produce high-quality and high-precision image segmentation results in comparison with the SLIC-based image segmentation algorithms on three standard metrics.


Image segmentation SLIC Neighborhood rough set Superpixel Neighborhood granule 



This work was supported by the National Natural Science Foundation of China (61503271) and the Shanxi Scholarship Council of China (2016–044).


  1. 1.
    Achanta R, Süsstrunk S (2017) Superpixels and polygons using simple non-iterative clustering. Proc IEEE Conf Comput Vis Pattern Recognit: 4895–4904Google Scholar
  2. 2.
    Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Susstrunk S (2012) SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274–2282CrossRefGoogle Scholar
  3. 3.
    Arbelaez P, Maire M, Fowlkes C, Malik J (2011) Contour detection and hierarchical image segmentation. IEEE Trans Pattern Anal Mach Intell 33(5):898–916CrossRefGoogle Scholar
  4. 4.
    Ates H F, Sunetci S, Ak K E (2016) Kernel likelihood estimation for superpixel image parsing. Proc Int Conf Image Anal Recogn: 234–242Google Scholar
  5. 5.
    Bai XD, Cao ZG, Wang Y, Ye MN, Zhu L (2014) Image segmentation using modified SLIC and Nystrom based spectral clustering. Optik-Int J Light Elect Opt 125(16):4302–4307CrossRefGoogle Scholar
  6. 6.
    Bergh M V, Boix X, Roig G, Capitani B D (2012) Seeds: Superpixels extracted via energy-driven sampling. Proc IEEE Conf Eur Conf Comput Vision: 13–26Google Scholar
  7. 7.
    Chen Y, Zeng Z, Lu J (2016) Neighborhood rough set reduction with fish swarm algorithm. Soft Comput 21(23):6907–6918CrossRefGoogle Scholar
  8. 8.
    Chen H, Li T, Cai Y et al (2016) Parallel attribute reduction in dominance-based neighborhood rough set. Inf Sci 373:351–368CrossRefGoogle Scholar
  9. 9.
    Felzenszwalb PF, Huttenlocher DP (2004) Efficient graph-based image segmentation. Int J Comput Vis 59(2):167–181CrossRefGoogle Scholar
  10. 10.
    Hsu C Y, Ding J J (2013) Efficient image segmentation algorithm using SLIC superpixels and boundary-focused region merging. Proceedings of the IEEE 9th international conference on information, communications and Signal Process: 1–5Google Scholar
  11. 11.
    Hu Q, Yu D, Liu J, Wu C (2008) Neighborhood rough set based heterogeneous feature subset selection. Inf Sci 178(18):3577–3594MathSciNetCrossRefGoogle Scholar
  12. 12.
    Huang G, Pun CM (2015) Robust interactive segmentation using color histogram and contourlet transform. Int J Comput Theory Eng 7(6):489CrossRefGoogle Scholar
  13. 13.
    Li Z, Chen J (2015) Superpixel segmentation using linear spectral clustering. Proc IEEE Conf Comput Vis Pattern Recognit: 1356–1363Google Scholar
  14. 14.
    Li B, Xiao J, Wang X et al (2018) Feature reduction for power system transient stability assessment based on neighborhood rough set and discernibility matrix. Energies 11(1):185CrossRefGoogle Scholar
  15. 15.
    Liu M Y, Tuzel O, Ramalingam S, Chellappa R (2011) Entropy rate superpixel segmentation. Proc IEEE Conf Comput Vis Pattern Recognit: 2097–2104Google Scholar
  16. 16.
    Liu B, Hu H, Wang H et al (2013) Superpixel-based classification with an adaptive number of classes for polarimetric SAR images. IEEE Trans Geosci Remote Sens 51(2):907–924CrossRefGoogle Scholar
  17. 17.
    Liu F, Lin G, Shen C (2015) CRF learning with CNN features for image segmentation. Pattern Recogn 48(10):2983–2992CrossRefGoogle Scholar
  18. 18.
    Liu Y, Yang J, Chen Y et al (2017) Stability analysis of hyperspectral band selection algorithms based on neighborhood rough set theory for classification. ChemometIntell Lab Syst 169:35–44CrossRefGoogle Scholar
  19. 19.
    Lucchi A, Li Y, Smith K, Fua P (2012) Structured image segmentation using kernelized features. Proc IEEE Conf Eur Conf Comput Vision: 400–413Google Scholar
  20. 20.
    Peng B, Zhang L, Zhang D (2011) Automatic image segmentation by dynamic region merging. IEEE Trans Image Process 20(12):3592–3605MathSciNetCrossRefGoogle Scholar
  21. 21.
    Rantalankila P, Kannala J, Rahtu E (2014) Generating object segmentation proposals using global and local search. Proc IEEE Conf Comput Vis Pattern Recognit:2417–2424Google Scholar
  22. 22.
    Ren X, Malik J (2003) Learning a classification model for segmentation. Proc IEEE Int Conf Comput Vision: 10–17Google Scholar
  23. 23.
    Shen J, Hao X, Liang Z et al (2016) Real-time superpixel segmentation by DBSCAN clustering algorithm. IEEE Trans Image Process 25(12):5933–5942MathSciNetCrossRefGoogle Scholar
  24. 24.
    Shi J, Malik J (2000) Normalized cuts and image segmentation. IEEE Trans Pattern Anal Mach Intell 22(8):888–905CrossRefGoogle Scholar
  25. 25.
    Singla A, Patra S (2017) A fast automatic optimal threshold selection technique for image segmentation. SIViP 11(2):243–250CrossRefGoogle Scholar
  26. 26.
    Tighe J, Lazebnik S (2010) Superparsing: scalable nonparametric image parsing with superpixels. Proc IEEE Conf Eur Conf Comput Vision: 352–365Google Scholar
  27. 27.
    Wang S, Lu H, Yang F, Yang M H (2011) Superpixel tracking. Proc IEEE Conf Int Conf Comput Vision: 1323–1330Google Scholar
  28. 28.
    Wang C, Shao M, He Q et al (2016) Feature subset selection based on fuzzy neighborhood rough sets. Knowl-Based Syst 111:173–179CrossRefGoogle Scholar
  29. 29.
    Wang M, Liu X, Gao Y et al (2017) Superpixel segmentation: a benchmark. Signal Process Image Commun 56:28–39CrossRefGoogle Scholar
  30. 30.
    Zhang L, Yang Y, Gao Y et al (2014) A probabilistic associative model for segmenting weakly supervised images. IEEE Trans Image Process 23(9):4150–4159MathSciNetCrossRefGoogle Scholar
  31. 31.
    Zhang K, Zhang L, Lam KM, Zhang D (2016) A level set approach to image segmentation with intensity inhomogeneity. IEEE Trans Cybernet 46(2):546–557CrossRefGoogle Scholar
  32. 32.
    Zhang Y, Li X, Gao X et al (2017) A simple algorithm of superpixel segmentation with boundary constraint. IEEE transactions on circuits and systems for video. Technology 27(7):1502–1514Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.College of Information EngineeringTaiyuan University of TechnologyTaiyuanPeople’s Republic of China
  2. 2.College of Electronic Information EngineeringTaiyuan University of Science and TechnologyTaiyuanPeople’s Republic of China

Personalised recommendations