Advertisement

An Improved Multi-Class Spectral Clustering Based on Normalized Cuts

  • Diego Hernán Peluffo-Ordóñez
  • Carlos Daniel Acosta-Medina
  • César Germáan Castellanos-Domínguez
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7441)

Abstract

In this work, we present an improved multi-class spectral clustering (MCSC) that represents an alternative to the standard k-way normalized clustering, avoiding the use of an iterative algorithm for tuning the orthogonal matrix rotation. The performance of proposed method is compared with the conventional MCSC and k-means in terms of different clustering quality indicators. Results are accomplished on commonly used toy data sets with hardly separable classes, as well as on an image segmentation database. In addition, as a clustering indicator, a novel unsupervised measure is introduced to quantify the performance of the proposed method. The proposed method spends lower processing time than conventional spectral clustering approaches.

Keywords

Cluster Performance Spectral Cluster Cluster Coherence Spectral Cluster Method Lower Processing Time 
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.

References

  1. 1.
    Yu, S.X., Jianbo, S.: Multiclass spectral clustering. In: ICCV 2003: Proceedings of the Ninth IEEE International Conference on Computer Vision, p. 313. IEEE Computer Society, Washington, DC (2003)CrossRefGoogle Scholar
  2. 2.
    Alzate, C., Suykens, J.A.K.: Multiway spectral clustering with out-of-sample extensions through weighted kernel pca. IEEE Transactions on Pattern Analysis and Machine Intelligence 32(2), 335–347 (2010)CrossRefGoogle Scholar
  3. 3.
    Suykens, J.A.K., Alzate, C., Pelckmans, K.: Primal and dual model representations in kernel-based learning. Statistics Surveys 4, 148–183 (2010)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Dhillon, I., Guan, Y., Kulis, B.: Kernel k-means: spectral clustering and normalized cuts. In: Proceedings of the tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 551–556. ACM (2004)Google Scholar
  5. 5.
    Zelnik-manor, L., Perona, P.: Self-tuning spectral clustering. In: Advances in Neural Information Processing Systems 17, pp. 1601–1608. MIT Press (2004)Google Scholar
  6. 6.
    O’Callaghan, R.J., Bull, D.R.: Combined morphological-spectral unsupervised image segmentation. IEEE Transactions on Image Processing 14(1), 49–62 (2005)CrossRefGoogle Scholar
  7. 7.
    Tung, F., Wong, A., Clausi, D.A.: Enabling scalable spectral clustering for image segmentation. Pattern Recognition 43(12), 4069–4076 (2010)zbMATHCrossRefGoogle Scholar
  8. 8.
    Lee, S., Hayes, M.: Properties of the singular value decomposition for efficient data clustering. IEEE Signal Processing Letters 11(11), 862–866 (2004), doi:10.1109/LSP.2004.833513CrossRefGoogle Scholar
  9. 9.
    Álvarez-Meza, A., Valencia-Aguirre, J., Daza-Santacoloma, G., Castellanos-Domínguez, G.: Global and local choice of the number of nearest neighbors in locally linear embedding. Pattern Recognition Letters 32(16), 2171–2177 (2011)CrossRefGoogle Scholar
  10. 10.
    Cvetkovic-Ilic, D.S.: Re-nnd solutions of the matrix equation AXB= C. Journal of the Australian Mathematical Society 84(1), 63–72 (2008)MathSciNetzbMATHCrossRefGoogle Scholar
  11. 11.
    Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proc. 8th Int’l Conf. Computer Vision, vol. 2, pp. 416–423 (July 2001)Google Scholar
  12. 12.
    Ben-Israel, A., Greville, T.N.E.: Generalized inverses: theory and applications, vol. 15. Springer (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Diego Hernán Peluffo-Ordóñez
    • 1
  • Carlos Daniel Acosta-Medina
    • 1
  • César Germáan Castellanos-Domínguez
    • 1
  1. 1.Signal Processing and Recognition GroupUniversidad Nacional de ColombiaManizalesColombia

Personalised recommendations