Advertisement

Batch Neural Gas with Deterministic Initialization for Color Quantization

  • M. Emre Celebi
  • Quan Wen
  • Gerald Schaefer
  • Huiyu Zhou
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7594)

Abstract

Color quantization is an important operation with many applications in graphics and image processing. Clustering methods based on the competitive learning paradigm, in particular self-organizing maps, have been extensively applied to this problem. In this paper, we investigate the performance of the batch neural gas algorithm as a color quantizer. In contrast to self-organizing maps, this competitive learning algorithm does not impose a fixed topology and is insensitive to initialization. Experiments on publicly available test images demonstrate that, when initialized by a deterministic preclustering method, the batch neural gas algorithm outperforms some of the most popular quantizers in the literature.

Keywords

Color quantization clustering competitive learning batch neural gas 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Brun, L., Trémeau, A.: Color Quantization. In: Digital Color Imaging Handbook, pp. 589–638. CRC Press (2002)Google Scholar
  2. 2.
    Heckbert, P.: Color Image Quantization for Frame Buffer Display. ACM SIGGRAPH Comp. Graph 16, 297–307 (1982)CrossRefGoogle Scholar
  3. 3.
    Gervautz, M., Purgathofer, W.: A Simple Method for Color Quantization: Octree Quantization. In: New Trends in Computer Graphics, pp. 219–231. Springer (1988)Google Scholar
  4. 4.
    Wan, S., et al.: Variance-Based Color Image Quantization for Frame Buffer Display. Color Res. Appl. 15, 52–58 (1990)CrossRefGoogle Scholar
  5. 5.
    Wu, X.: Efficient Statistical Computations for Optimal Color Quantization. In: Graphics Gems, vol. II, pp. 126–133. Academic Press (1991)Google Scholar
  6. 6.
    Joy, G., Xiang, Z.: Center-Cut for Color Image Quantization. Visual Comput. 10, 62–66 (1993)CrossRefGoogle Scholar
  7. 7.
    Yang, C.Y., Lin, J.C.: RWM-Cut for Color Image Quantization. Comput Graph 20, 577–588 (1996)CrossRefGoogle Scholar
  8. 8.
    Velho, L., et al.: Color Image Quantization by Pairwise Clustering. In: Proc SIBGRAPI, pp. 203–210 (1997)Google Scholar
  9. 9.
    Brun, L., Mokhtari, M.: Two High Speed Color Quantization Algorithms. In: Proc CGIP, pp. 116–121 (2000)Google Scholar
  10. 10.
    Xiang, Z.: Color Image Quantization by Minimizing the Maximum Intercluster Distance. ACM T. Graphic 16, 260–276 (1997)CrossRefGoogle Scholar
  11. 11.
    Celebi, M.E.: Improving the Performance of K-means for Color Quantization. Image Vision Comput 29, 260–271 (2011)CrossRefGoogle Scholar
  12. 12.
    Wen, Q., Celebi, M.E.: Hard vs. Fuzzy C-Means Clustering for Color Quantization. Eurasip. J. Adv. Sig. Pr. 2011(1), 118–129 (2011)CrossRefGoogle Scholar
  13. 13.
    Dekker, A.: Kohonen Neural Networks for Optimal Colour Quantization. Network- Comp. Neural 5, 351–367 (1994)CrossRefzbMATHGoogle Scholar
  14. 14.
    Cottrell, M., et al.: Batch and Median Neural Gas. Neural Networks 19, 762–771 (2006)CrossRefzbMATHGoogle Scholar
  15. 15.
    Martinetz, T., et al.: Neural-Gas Network for Vector Quantization and its Application to Time-Series Prediction. IEEE T. Neural Networ. 4, 558–569 (1993)CrossRefGoogle Scholar
  16. 16.
    Cheng, S., Yang, C.: Fast and Novel Technique for Color Quantization Using Reduction of Color Space Dimensionality. Pattern Recogn. Lett. 22, 845–856 (2001)CrossRefzbMATHGoogle Scholar
  17. 17.
    Franzen, R.W.: Kodak Lossless True Color Image Suite (1999), http://www.r0k.us/graphics/kodak/

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • M. Emre Celebi
    • 1
  • Quan Wen
    • 2
  • Gerald Schaefer
    • 3
  • Huiyu Zhou
    • 4
  1. 1.Department of Computer ScienceLouisiana State UniversityShreveportUSA
  2. 2.School of Computer Science and EngineeringUniversity of Electronic Science and Technology of ChinaChengduP.R. China
  3. 3.Department of Computer ScienceLoughborough UniversityLoughboroughUK
  4. 4.The Institute of Electronics, Communications and Information TechnologyQueen’s University BelfastBelfastUK

Personalised recommendations