Improved Spectral Density Measurement from Estimated Reflectance Data with Kernel Ridge Regression

  • Timo Eckhard
  • Maximilian Klammer
  • Eva M. Valero
  • Javier Hernández-Andrés
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8509)


Density measurement of printed color samples takes an important role in print quality inspection and process control. When multi-spectral imaging systems are considered for surface reflectance measurement, the possibility of calculating spectral print density over the spatial image domain arises. A drawback in using multi-spectral imaging systems is that some spectral reconstruction algorithms can produce estimated reflectances which contain negative values that are physically not meaningful. When spectral density calculations are considered, the results are erroneous and calculations might even fail in the worst case. We demonstrate how this problem can be avoided by using kernel ridge regression with additional link functions to constrain the estimates to positive values.


multi-spectral imaging spectral density kernel regression 


  1. 1.
    Kipphan, H.: Handbook of print media: Technologies and production methods. Springer (2001)Google Scholar
  2. 2.
    Verikas, A., Bacauskiene, M.: Estimating ink density from colour camera RGB values by the local kernel ridge regression. Eng. Appl. of Artificial Intelligence 21(1), 35–42 (2008)CrossRefGoogle Scholar
  3. 3.
    ISO 5:2009 Photography and graphic technology – Density measurements, Part 3: Spectral conditionsGoogle Scholar
  4. 4.
    Ribés, A., Schmitt, F.: Linear inverse problems in imaging. IEEE Signal Processing Magazine 25(4), 84–99 (2008)CrossRefGoogle Scholar
  5. 5.
    Heikkinen, V., Lenz, R., Jetsu, T., Parkkinen, J., Hauta-Kasari, M., Jääskeläinen, T.: Evaluation and unification of some methods for estimating reflectance spectra from RGB images. J. Opt. Soc. Am. A 25(10), 2444–2458 (2008)CrossRefGoogle Scholar
  6. 6.
    Eckhard, T., Valero, E., Hernndez-Andrs, J., Heikkinen, V.: Evaluating logarithmic kernel for spectral reflectance estimation - effects on model parametrization, training set size and number of sensor spectral channels. J. Opt. Soc. Am. A 31(3), 541–549 (2014)CrossRefGoogle Scholar
  7. 7.
    Heikkinen, V., Mirhashemi, A., Alho, J.: Link functions and Matérn kernel in the estimation of reflectance spectra from RGB responses. J. Opt. Soc. Am. A 30(11), 2444–2454 (2013)CrossRefGoogle Scholar
  8. 8.
    Park, J.I., Lee, M.H., Grossberg, M.D., Nayar, S.K.: Multispectral imaging using multiplexed illumination. In: IEEE 11th International Conference on Computer Vision, pp. 1–8. IEEE (2007)Google Scholar
  9. 9.
    Godau, C., Klammer, M., Eckhard, T., Schnitzlein, M., Nowack, D., Frei, B., Urban, P.: Evaluation of a multi-spectral camera system for inline color measurement. In: Annual meeting of the German Colour Group (2013)Google Scholar
  10. 10.
    CIE: Improvement to industrial colour-difference evaluation. Tech. rep., CIE Pub. No. 142-2001 (2001)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Timo Eckhard
    • 1
  • Maximilian Klammer
    • 2
  • Eva M. Valero
    • 1
  • Javier Hernández-Andrés
    • 1
  1. 1.Optics DepartmentUniversity of GranadaSpain
  2. 2.Chromasens GmbHKonstanzGermany

Personalised recommendations