Advertisement

Abstract

In this paper, we aim at learning the colour matching functions making use of hyperspectral and trichromatic imagery. The method presented here is quite general in nature, being data driven and devoid of constrained setups. Here, we adopt a probabilistic formulation so as to recover the colour matching functions directly from trichromatic and hyperspectral pixel pairs. To do this, we derive a log-likelihood function which is governed by both, the spectra-to-colour equivalence and a generative model for the colour matching functions. Cast into a probabilistic setting, we employ the EM algorithm for purposes of maximum a posteriori inference, where the M-step is effected making use of Levenberg-Marquardt optimisation. We present results on real-world data and provide a quantitative analysis based upon a colour calibration chart.

Keywords

Hyperspectral Image Colour Match Image Radiance Colour Match Function Liquid Crystal Tunable Filter 
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.
    Stiles, W.S., Burch, J.M.: Interim report to the Commission Internationale de l’Éclairage Zurich, 1955, on the National Physical Laboratory’s investigation of colour-matching. Optica Acta 2, 168–181 (1955)CrossRefGoogle Scholar
  2. 2.
    Wandell, B.A.: The synthesis and analysis of color images. IEEE Transactions on Pattern Analysis and Machine Intelligence 9(1), 2–13 (1987)CrossRefGoogle Scholar
  3. 3.
    Schechner, Y., Nayar, S.: Uncontrolled modulation imaging. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. II:97–II:204 (2004)Google Scholar
  4. 4.
    Schechner, Y., Nayar, S., Belhumeur, P.N.: A theory of multiplexed illumination. In: Int. Conference on Computer Vision, pp. II:808–II:816 (2003)Google Scholar
  5. 5.
    Chi, C., Yoo, H., Ben-Ezra, M.: Multi-spectral imaging by optimized wide band illumination. Int. Journal of Computer Vision 86, 140–151 (2010)CrossRefGoogle Scholar
  6. 6.
    Vora, P.L., Farrell, J.E., Tietz, J.D., Brainard, D.H.: Linear models for digital cameras. In: Proceedings of the IS&T’s 50th Annual Conference, pp. 377–382 (1997)Google Scholar
  7. 7.
    Finlayson, G., Hordley, S., Hubel, P.: Recovering device sensitivities with quadratic programming. In: Proceedings of the IS&T/SID Color Imaging Conference, pp. 90–95 (1998)Google Scholar
  8. 8.
    Urban, P., Desch, M., Happel, K., Spiehl, D.: Recovering camera sensitivities using target-based reflectances captured under multiple led-illuminations. In: Proceedings of the Workshop on Color Image Processing, pp. 9–16 (2010)Google Scholar
  9. 9.
    Martin, R., Arno, Z., Reinhard, K.: Practical spectral characterization of trichromatic cameras. In: SIGGRAPH Asia (2011)Google Scholar
  10. 10.
    Horn, B.K.P., Brooks, M.J.: The variational approach to shape from shading. CVGIP 33(2), 174–208 (1986)zbMATHGoogle Scholar
  11. 11.
    Kimmel, R., Elad, M., Shaked, D., Keshet, R., Sobel, I.: A variational framework for retinex. International Journal of Computer Vision 52(1), 7–23 (2003)zbMATHCrossRefGoogle Scholar
  12. 12.
    Finlayson, G.D., Schaefer, G.: Solving for colour constancy using a constrained dichromatic reflection model. International Journal of Computer Vision 42(3), 127–144 (2001)zbMATHCrossRefGoogle Scholar
  13. 13.
    Huynh, C.P., Robles-Kelly, A.: A solution of the dichromatic model for multispectral photometric invariance. International Journal of Computer Vision 90(1), 1–27 (2010)CrossRefGoogle Scholar
  14. 14.
    Gonzalez, R.C., Wintz, P.: Digital Image Processing. Addison-Wesley Publishing Company Limited (1986)Google Scholar
  15. 15.
    Vora, P., Farrell, J., Tietz, J., Brainard, D.: Image capture: Simulation of sensor responses from hyperspectral images. IEEE Transactions on Image Processing 10(2), 307–316 (2001)CrossRefGoogle Scholar
  16. 16.
    Dempster, A., Laird, N., Rubin, D.: Maximum-likehood from incomplete data via the EM algorithm. J. Royal Statistical Soc. Ser. B Methodological 39, 1–38 (1977)MathSciNetzbMATHGoogle Scholar
  17. 17.
    Nocedal, J., Wright, S.: Numerical Optimization. Springer (2000)Google Scholar
  18. 18.
    Bishop, C.M.: Pattern Recognition and Machine Learning. Springer (2006)Google Scholar
  19. 19.
    Barber, D.: Bayesian Reasoning and Machine Learning. Cambridge University Press (2012)Google Scholar
  20. 20.
    Dalai, N., Triggs, B.: Histogram of oriented gradients for human detection. In: Computer Vision and Pattern Recognition, pp. I:886–I:893 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Luis Romero-Ortega
    • 1
  • Antonio Robles-Kelly
    • 1
    • 2
    • 3
  1. 1.School of Eng. and Inf. Tech.UNSW@ADFACanberraAustralia
  2. 2.NICTACanberraAustralia
  3. 3.Research School of Eng.ANUCanberraAustralia

Personalised recommendations