Skip to main content
Log in

A dynamic weights OWA fusion for ensemble clustering

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

In this work, a new image segmentation algorithm is introduced. The proposed algorithm combines the results of an hybrid clustering ensemble. The ensemble clustering is composed of fuzzy c-means (FCM) algorithm and fuzzy local information c-means (FCM_S1 and FCM_S2) algorithms with different values of the neighbors effect. The consensus technique is performed by the ordered weighted averaging (OWA) method. The weight attributed to each classifier can be modified during the process of classification and is determined by the classifier results of the pixel neighbors classification. Dynamic weights give the method the ability to select the temporal best performance during the classification process. Experiments performed on a synthetic image, and real images show that the proposed algorithm is effective and efficient and provides good noise elimination effect.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Abbreviations

\(X\) :

the data set

\(k\) :

number of clusters

\(C\) :

clusters centers vector

\(d(c_{i}\!,x_{j})\) :

distance measure between object \(x_{j}\) and \(c_{i}\) the center of cluster \(i\)

\(j_{m}\) :

objective function

\({u}_{\mathrm{i,j}}\) :

fuzzy membership of the \(i\)th pixel with respect to cluster \(j\)

\(N_{i}\) :

set of neighbors into a window around pixel \(x_{i}\).

\(N_{R}\) :

cardinality of the window

\(\overline{x}_{r}\) :

the average neighboring pixels lying within a window around \(x_{r}\)

\(a\) :

parameter used to control the effect of the neighbors term

\(N_{d}\) :

number of data in \(X\)

\(N_{c}\) :

number of clusterers.

\(\pi _{i}\) :

partition \(i\)

\(\lambda _{i}\) :

Label \(i\)

\(\pi ^{*}\) :

optimal partition

\(\varPhi ^{\mathrm{NMI}}\) :

normalized mutual information

\(\beta _m\) :

average mutual information

\(\beta _0\) :

parameter used to normalize the weights

\(W\) :

weight vector

\(a_{i}\) :

arguments to aggregate

\(b_{i}\) :

the \(i\)th largest element of the collection of aggregated objects

\(\alpha \) :

parameter used to control the effect of the past performance of the classifier

\(SA\) :

the rate of correct pixels classification

\(A_{i}\) :

the set of pixels attributed to the \(i\)th class

\(B_{i}\) :

the set of pixels belonging to the \(i\)th class

\(OA\) :

Overall Accuracy

References

  1. Wells, W.M., LGrimson, W.E., Kikinis, R., Arrdrige, S.R.: Adative segmentation of MRI data. IEEE Trans. Med. Imaging 15, 429–442 (1996)

    Article  Google Scholar 

  2. Fred, A.L., Jain, A.K.: Combining multiple clusterings using evidence accumulation. IEEE PAMI 27(6), 835–850 (2005)

    Article  Google Scholar 

  3. Yager, R.R.: On ordered weighted averaging aggregation operators in multicriteria decision making. IEEE Trans. Syst. Man Cybern. 18(1), 183–190 (1988)

    Article  MATH  MathSciNet  Google Scholar 

  4. Fullér, R., Majlender, P.: On obtaining minimal variability OWA operator weights. Fuzzy Sets Syst. 136(2), 203–215 (2003)

    Article  MATH  Google Scholar 

  5. Yager, R.R.: Quantifier guided aggregation using OWA operators. Int. J. Intell. Syst. 11(1), 49–73 (1996)

    Article  Google Scholar 

  6. Yager, R.R.: Decision making with fuzzy probability assessments. IEEE Trans. Fuzzy Syst. 7(4), 462–467 (1999)

    Article  MathSciNet  Google Scholar 

  7. Yager, R.R.: On the valuation of alternatives for decision-making under uncertainty. Int. J. Intell. Syst. 17(7), 687–707 (2002)

    Article  MATH  Google Scholar 

  8. Ahn, B.S.: On the properties of OWA operator weights functions with constant level of orness. IEEE Trans. Fuzzy Syst. 14(4), 511–515 (2006)

    Article  Google Scholar 

  9. Liu, X.: On the properties of equidifferent OWA operator. Int. J. Approx. Reason. 43(1), 90–107 (2006)

    Article  MATH  Google Scholar 

  10. Wang, Y., Parkan, C.: A minimax disparity approach for obtaining OWA operator weights. Inf. Sci. 175(1/2), 20–29 (2005)

    Article  MATH  MathSciNet  Google Scholar 

  11. Xu, Z.S.: An overview of methods for determining OWA weights. Int. J. Intell. Syst. 20(8), 843–865 (2005)

    Article  MATH  Google Scholar 

  12. Filev, D., Yager, R.R.: Analytic properties of maximum entropy OWA operators. Inf. Sci. 85, 11–27 (1995)

    Google Scholar 

  13. Wang, Y.M., Luo, Y., Liu, X.: Two new models for determining OWA operator weights. Comput. Ind. Eng. 52, 203–209 (2007)

    Google Scholar 

  14. Majlender, P.: OWA operators with maximal Renyi entropy. Fuzzy Sets Syst. 155, 340–360 (2005)

    Article  MATH  MathSciNet  Google Scholar 

  15. Dunn, J.: A fuzzy relative of the ISODATA process and its use in detecting compact well separated clusters. J. Cybern. 3, 32–57 (1974)

    Article  MathSciNet  Google Scholar 

  16. Bezdek, J.: Pattern Recognition With Fuzzy Objective Function Algorithms. Plenum, New York (1981)

    Book  MATH  Google Scholar 

  17. Groll, L., Jakel, J.: A new convergence proof of fuzzy c-means. IEEE Trans. Fuzzy Syst. 13(5), 717–720 (2005)

    Article  Google Scholar 

  18. Ahmed, M., Yamany, S., Mohamed, N., Farag, A., Moriarty, T.: A modified fuzzy C-means algorithm for bias field estimation and segmentation of MRI data. IEEE Trans. Med. Imaging 21, 193–199 (2002)

    Article  Google Scholar 

  19. Chen, S., Zhang, D.: Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure. IEEE Trans. Syst. Man Cybern. 34, 1907–1916 (2004)

    Article  Google Scholar 

  20. Krinidis, S., Chatzis, V.: A robust fuzzy local information c-means clustering algorithm. IEEE Trans. Image Process. 19(5), 1328–1337 (2010)

    Article  MathSciNet  Google Scholar 

  21. Riesen, K., Bunke, H.: Cluster ensembles based on vector space embeddings of graphs [J]. Lect. Notes Comput. Sci. 5519(1), 211–221 (2009)

    Article  Google Scholar 

  22. Zhang, L., Zhou, W., Wu, C., Huo, J., Zou, H.: Center matching scheme for K-means cluster ensembles[C]. MIPPR 2009 Pattern Recognit. Comput. Vis. 19(1):77–83 (2009)

  23. Strehl, A., Ghosh, J., Cardie, C.: Cluster ensembles: a knowledge reuse framework for combining multiple partitions[J]. J. Mach. Learn. Res. 3, 583–617 (2002)

    Google Scholar 

  24. Kang, K., Zhang, H.X., Fan, Y.: A novel clusterer ensemble algorithm based on dynamic cooperation [C]. In: Fifth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD’2008), pp. 32–35 (2008)

  25. Haixiong, F., Fuxian, L., Lu, X.: Cluster label aligning algorithm based on programming model. In: 24th Chinese Control and Decision Conference (CCDC), pp 1768–1772 (2012)

  26. Ayed, H.G., Kamel, M.S.: On voting based consensus of cluster ensembles. Pattern Recognit. 43, 1043–1953 (2010)

    Google Scholar 

  27. Ayed, H.G., Kamel, M.S.: Cumulative voting consensus method for partitions with a variable number of clusters. IEEE Trans. Pattern Anal. Mach. Intell. 30, 160–173 (2008)

    Article  Google Scholar 

  28. Kuhn, H.: The Hungarian method for the assignment problem. Nav. Res. Logist. Q. 2, 83–97 (1955)

    Article  Google Scholar 

  29. O’Hagan, M.: Aggregating template or rule antecedents in real-time expert systems with fuzzy set. In: Grove, P. (ed.) Proceedings of 22nd Annual IEEE Asilomar Conference Signals, Systems, and Computers, pp. 681–689. Pacific Grove, CA (1988)

  30. Zhou, Z., Tang, W.: Clusterer ensemble [J]. Knowl. Based Syst. 19(1), 77–83 (2006)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Nassim Ammour.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Ammour, N., Alajlan, N. A dynamic weights OWA fusion for ensemble clustering. SIViP 9, 727–734 (2015). https://doi.org/10.1007/s11760-013-0499-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-013-0499-1

Keywords

Navigation