Automatic Palette Identification of Colored Graphics

  • Vinciane Lacroix
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6020)


The median-shift, a new clustering algorithm, is proposed to automatically identify the palette of colored graphics, a pre-requisite for graphics vectorization. The median-shift is an iterative process which shifts each data point to the “median” point of its neighborhood defined thanks to a distance measure and a maximum radius, the only parameter of the method. The process is viewed as a graph transformation which converges to a set of clusters made of one or several connected vertices. As the palette identification depends on color perception, the clustering is performed in the L*a*b* feature space. As pixels located on edges are made of mixed colors not expected to be part of the palette, they are removed from the initial data set by an automatic pre-processing. Results are shown on scanned maps and on the Macbeth color chart and compared to well established methods.


palette extraction clustering mean-shift 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Diebel, J.R.: Bayesian Image Vectorization: The Probabilistic Inversion of Vector Image Rasterization. Phd thesis, Standford University (2008)Google Scholar
  2. 2.
    Hilaire, X.: RANVEC and the Arc Segmentation Contest: Second Evaluation. In: Liu, W., Lladós, J. (eds.) GREC 2005. LNCS, vol. 3926, pp. 362–368. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  3. 3.
    Chen, Y., et al.: Extracting Contour Lines From Common-Conditioned Topograpic Maps. IEEE TGARS 44(4), 1048–1057 (2006)Google Scholar
  4. 4.
    Deseilligny, M.P.: Lecture automatique de cartes, Phd thesis, Université René Descartes, Paris, France (1994)Google Scholar
  5. 5.
    Robert, R.: Contribution à la lecture automatique de cartes, Phd thesis, Université de Rouen, Rouen, France (1997)Google Scholar
  6. 6.
    Braquelaire, J.-P., Brun, L.: Comparison and Optimization of Methods of Color Image Quantization. IEEE Trans. on Image Processing 6(7), 1048–1052 (1997)CrossRefGoogle Scholar
  7. 7.
    Jain, A.K., Duin, R.P.W., Mao, J.: Statistical Pattern Recognition: A Review. IEEE Trans. PAMI 22(1), 4–37 (2000)Google Scholar
  8. 8.
    Comaniciu, D., Meer, P.: Mean Shift: A Robust Approach Toward Feature Space Analysis. IEEE Trans. PAMI 24(5), 603–619 (2002)Google Scholar
  9. 9.
    Tran, T.N., Wehrens, H.R.M.J., Buydens, L.M.C.: Clustering multispectral images: a tutorial. Chemometrics and Int. Lab. Syst. 77, 3–17 (2005)Google Scholar
  10. 10.
    Price, K.: Computer Vision Biography, 8.8.3 MRF Models for Segmentation, (accessed 05-09)
  11. 11.
    Koschan, A., Abidi, M.: Detection and Classification of Edges in Color Images. Sig. Proc. Mag., Spec. Issue on Color Img. Proc. 22(1), 64–73 (2005)Google Scholar
  12. 12.
    Lacroix, V., Acheroy, M.: Feature-Extraction Using the Constrained Gradient. ISPRS J. of Photogram. and RS 53(2), 85–94 (1998)CrossRefGoogle Scholar
  13. 13.
    Palus, H.: On color image quantization by the k-means algorithm. 10. In: Droege, D., Paulus, D. (eds.) Workshop Farbbildverarbeitung, Universität Koblenz-Landau, Tönning, Der Andere Verlag (2004)Google Scholar
  14. 14.
    Bouman, C.A.: Cluster: An unsupervised algorithm for modeling Gaussian mixtures (1997),
  15. 15.
    Ohta, N., Robertson, A.R.: Colorimetry Fundamentals and Applications. John Wiley & Sons, Ltd., Chichester (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Vinciane Lacroix
    • 1
  1. 1.CISS DepartmentRoyal Military AcademyBrusselsBelgium

Personalised recommendations