Advertisement

KM and KHM Clustering Techniques for Colour Image Quantisation

  • Mariusz FrackiewiczEmail author
  • Henryk Palus
Chapter
Part of the Computational Methods in Applied Sciences book series (COMPUTMETHODS, volume 19)

Abstract

This paper deals with the comparison of two clustering techniques kmeans (KM) and k-harmonic means (KHM) in the case of their use in colour image quantisation. The classical KMtechnique establishes good background for this comparison. Authors proposed two original heuristic initialisation methods, one arbitrary(DC) and one adaptive (SD), that were used in both techniques. Apart from specific validity indices for clustering, the results were also evaluated by means of average colour differences in RGB (PSNR) and CIELAB colour space (ΔE) and additionally difference of colourfulness (ΔM). Experimental tests realised on benchmark colour images show the superiority of KHMover KM. Other problems with both clustering techniques e.g. empty clusters have also been highlighted.

Keywords

Colour image quantisation k-means k-harmonic means 

Notes

Acknowledgements

This work has been supported by the Polish Ministry of Science and Higher Education under RD grant no. N N516 374736 from the Science Budget 2009–2011.

References

  1. 1.
    Anderberg, M.: Cluster Analysis for Applications. Academic Press, New York, USA (1973)zbMATHGoogle Scholar
  2. 2.
    Boppana, D., Rao, S.: Clustering-based blind maximum likelihood sequence detection for GSM and TDMA systems. In: Proceedings of the 45th Midwest Symposium on Circuits and Systems, vol.1, pp. 427–430. Tulsa, OK, USA (2002)Google Scholar
  3. 3.
    Borsotti, M., Campadelli, P., Schettini, R.: Quantitative evaluation of color image segmentation results. Pattern Recogn. Lett. 19(8), 741–747 (1998)zbMATHCrossRefGoogle Scholar
  4. 4.
    Bradley, P.S., Bennett, K.P., Demiriz, A.: Constrained k-means clustering. Tech. Rep. MSR-TR-2000-65, Microsoft Research, Redmond, WA, USA (2000)Google Scholar
  5. 5.
    Brun, L., Tremeau, A.: Digital color imaging handbook, chapter Color quantization, pp. 589–637. CRC Press, Boca Raton, FA, USA (2003)Google Scholar
  6. 6.
    Celebi, M.: Effective initialization of k-means for color quantization. In: Proceedings of the IEEE International Conference on Image Processing (ICIP2009), Cairo, Egypt (2009)Google Scholar
  7. 7.
    Davies, D., Bouldin, D.: A cluster separation measure. IEEE Trans. Pattern Anal. Mach. Intell. 1(4), 224–227 (1979)CrossRefGoogle Scholar
  8. 8.
    Deng, Y., Manjunath, B.: Unsupervised segmentation of color-texture regions in images and video. IEEE Trans. Pattern Anal. Mach. Intell. 23(8), 800–810 (2001)CrossRefGoogle Scholar
  9. 9.
    Domański, M., Bartkowiak, M.: The colour image processing handbook, chapter Compression, pp. 242–304. Chapman and Hall, London, UK (1998)Google Scholar
  10. 10.
    Ekin, A., Jasinschi, R.: A robust thresholding method with applications to brain MR image segmentation. In: Proceedings of EUSIPCO, Florence, Italy (2006)Google Scholar
  11. 11.
    Giordani, P., Kohn, R.: Adaptive independent Metropolis-Hastings by fast estimation of mixture of normals. http://www.riksbank.com/upload/research/conferences/bayes2006/aimh_august1.pdf
  12. 12.
    Güngör, Z., Ünler, A.: K-harmonic means data clustering with simulated annealing heuristic. Appl. Math. Comput. 184(2), 199–209 (2007)zbMATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Güngör, Z., Ünler, A.: K-harmonic means data clustering with tabu-search method. Appl. Math. Model. 32(2), 1115–1125 (2008)zbMATHCrossRefGoogle Scholar
  14. 14.
    Güngör, Z., Ünler, A.: Applying k-harmonic means clustering to the part-machine classification problem. Expet. Syst. Appl. 36(2), 1179–1194 (2009)CrossRefGoogle Scholar
  15. 15.
    Hamerly, G., Elkan, C.: Alternatives to the k-means algorithm that find better clusterings. In: Proceedings of the 11th ACM Conference on Information and Knowledge Management (CIKM2002), McLean, VA, USA, pp. 600–607 (2002)Google Scholar
  16. 16.
    Hamerly, G.J.: Learning structure and concepts in data through data clustering. Ph.D. Thesis, University of California, San Diego (2003)Google Scholar
  17. 17.
    Hasler, D., Suesstrunk, S.: Measuring colourfulness for natural images. In: Electronic Imaging 2003: Human Vision and Electronic Imaging VIII, Proceedings of SPIE, vol. 5007, pp. 87–95 (2003)Google Scholar
  18. 18.
    Li, Q., Mitianoudis, N., Stathaki, T.: Spatial kernel k-harmonic means clustering for multi-spectral image thresholding. IET Image Process. 1(2), 156–167 (2007)CrossRefGoogle Scholar
  19. 19.
    MacQueen, J.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the 5th Berkeley Symposium on Mathematics, Statistics, and Probabilities, vol.I, pp. 281–297. Berkeley and Los Angeles, CA, USA (1967)Google Scholar
  20. 20.
    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: Proceedings of the 8th International Conference on Computer Vision, pp. 416–423. Vancouver, BC, Canada (2001)Google Scholar
  21. 21.
    McCamy, C., Marcus, H., Davidson, J.: A color rendition chart. J. Appl. Photogr. Eng. 2(3), 95–99 (1976)Google Scholar
  22. 22.
    Palus, H.: On color image quantization by the k-means algorithm. In: Droege, D., Paulus, D. (eds.) Proceedings of 10. Workshop Farbbildverarbeitung, pp. 58–65. Toenning, Germany (2004)Google Scholar
  23. 23.
    Palus, H.: Colourfulness of the image and its application in image filtering. In: Proceedings of 5th IEEE International Symposium on Signal Processing and Information Technology (ISSPIT 2005), pp. 884–889. Athens, Greece (2005)Google Scholar
  24. 24.
    Ray, S., Turi, R.: Determination of number of clusters in k-means clustering and application in colour image segmentation. In: Proceedings of the 4th International Conference on Advances in Pattern Recognition and Digital Techniques, pp. 137–143. Calcutta, India (1999)Google Scholar
  25. 25.
    Schaefer, R., Zhou, H.: Fuzzy clustering for colour reduction in images. Telecommun. Syst. 40, 17–25 (2009)CrossRefGoogle Scholar
  26. 26.
    Tsai, P., Hu, Y., Chang, C.: A color image watermarking scheme based on color quantization. Signal Process. 84(1), 95–106 (2004)zbMATHCrossRefGoogle Scholar
  27. 27.
    Ünler, A., Güngör, Z.: Particle swarm optimization based k-harmonic means data clustering. In: Proceedings of the 38th International Conference on Computers and Industrial Engineering, vol.1, pp. 379–387. Beijing, China (2008)Google Scholar
  28. 28.
    Wang, M., Yang, W., Acharya, R.: Color clustering techniques for color content-based image retrieval from image databases. In: Proceedings of IEEE International Conference on Multimedia Computing and Systems, pp. 442–449. Ottawa, Canada (1997)Google Scholar
  29. 29.
    Wyszecki, G., Stiles, W.: Color Science: Concepts and Methods, Quantitative Data and Formulae. Wiley, New York, USA (1982)Google Scholar
  30. 30.
    Zhang, B.: Generalized k-harmonic means – boosting in unsupervised learning. Tech. Rep. TR HPL-2000-137, Hewlett Packard Labs, Palo Alto, CA, USA (2000)Google Scholar
  31. 31.
    Zhang, B., Hsu, M., Dayal, U.: K-harmonic means – data clustering algorithm. Tech. Rep. TR HPL-1999-124, Hewlett Packard Labs, Palo Alto, CA, USA (1999)Google Scholar

Copyright information

© Springer Science+Business Media B.V. 2011

Authors and Affiliations

  1. 1.Silesian University of TechnologyGliwicePoland

Personalised recommendations