Training-Based Spectral Reconstruction from a Single RGB Image

  • Rang M. H. Nguyen
  • Dilip K. Prasad
  • Michael S. Brown
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8695)


This paper focuses on a training-based method to reconstruct a scene’s spectral reflectance from a single RGB image captured by a camera with known spectral response. In particular, we explore a new strategy to use training images to model the mapping between camera-specific RGB values and scene reflectance spectra. Our method is based on a radial basis function network that leverages RGB white-balancing to normalize the scene illumination to recover the scene reflectance. We show that our method provides the best result against three state-of-art methods, especially when the tested illumination is not included in the training stage. In addition, we also show an effective approach to recover the spectral illumination from the reconstructed spectral reflectance and RGB image. As a part of this work, we present a newly captured, publicly available, data set of hyperspectral images that are useful for addressing problems pertaining to spectral imaging, analysis and processing.


Spectral Image Training Image Hyperspectral Image Radial Basis Function Network Color Constancy 
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.


  1. 1.
    Abed, F.M., Amirshahi, S.H., Abed, M.R.M.: Reconstruction of reflectance data using an interpolation technique. J. Opt. Soc. Am. A 26(3), 613–624 (2009)CrossRefGoogle Scholar
  2. 2.
    Agahian, F., Amirshahi, S.A., Amirshahi, S.H.: Reconstruction of reflectance spectra using weighted principal component analysis. Color Research & Application 33(5), 360–371 (2008)CrossRefGoogle Scholar
  3. 3.
    Ayala, F., Echávarri, J.F., Renet, P., Negueruela, A.I.: Use of three tristimulus values from surface reflectance spectra to calculate the principal components for reconstructing these spectra by using only three eigenvectors. J. Opt. Soc. Am. A 23(8), 2020–2026 (2006)CrossRefGoogle Scholar
  4. 4.
    Barakzehi, M., Amirshahi, S.H., Peyvandi, S., Afjeh, M.G.: Reconstruction of total radiance spectra of fluorescent samples by means of nonlinear principal component analysis. J. Opt. Soc. Am. A 30(9), 1862–1870 (2013)CrossRefGoogle Scholar
  5. 5.
    Brainard, D.H., Freeman, W.T.: Bayesian color constancy. J. Opt. Soc. Am. A 14(7), 1393–1411 (1997)CrossRefGoogle Scholar
  6. 6.
    Chen, S., Cowan, C.F., Grant, P.M.: Orthogonal least squares learning algorithm for radial basis function networks. IEEE Transactions on Neural Networks 2(2), 302–309 (1991)CrossRefGoogle Scholar
  7. 7.
    Cheng, D., Prasad, D.K., Brown, M.S.: Illuminant estimation for color constancy: why spatial-domain methods work and the role of the color distribution. J. Opt. Soc. Am. A 31(5), 1049–1058 (2014)CrossRefGoogle Scholar
  8. 8.
    Cohen, J.: Dependency of the spectral reflectance curves of the munsell color chips. Psychonomic Science (1964)Google Scholar
  9. 9.
    Connah, D., Westland, S., Thomson, M.G.: Recovering spectral information using digital camera systems. Coloration Technology 117(6), 309–312 (2001)CrossRefGoogle Scholar
  10. 10.
    Eslahi, N., Amirshahi, S.H., Agahian, F.: Recovery of spectral data using weighted canonical correlation regression. Optical Review 16(3), 296–303 (2009)CrossRefGoogle Scholar
  11. 11.
    Fairman, H.S., Brill, M.H.: The principal components of reflectances. Color Research & Application 29(2), 104–110 (2004)CrossRefGoogle Scholar
  12. 12.
    Finlayson, G.D., Trezzi, E.: Shades of gray and colour constancy. In: Color and Imaging Conference, vol. 2004, pp. 37–41 (2004)Google Scholar
  13. 13.
    Gijsenij, A., Gevers, T., van de Weijer, J.: Computational color constancy: Survey and experiments. IEEE Transactions on Image Processing 20(9), 2475–2489 (2011)CrossRefMathSciNetGoogle Scholar
  14. 14.
    Hall, R., Hall, R.: Illumination and color in computer generated imagery, vol. 7. Springer, New York (1989)CrossRefGoogle Scholar
  15. 15.
    Jaaskelainen, T., Parkkinen, J., Toyooka, S.: Vector-subspace model for color representation. J. Opt. Soc. Am. A 7(4), 725–730 (1990)CrossRefGoogle Scholar
  16. 16.
    Jiang, J., Liu, D., Gu, J., Susstrunk, S.: What is the space of spectral sensitivity functions for digital color cameras? In: IEEE Workshop on Applications of Computer Vision, pp. 168–179 (2013)Google Scholar
  17. 17.
    Laamanen, H., Jetsu, T., Jaaskelainen, T., Parkkinen, J.: Weighted compression of spectral color information. J. Opt. Soc. Am. A 25(6), 1383–1388 (2008)CrossRefGoogle Scholar
  18. 18.
    Lenz, R., Meer, P., Hauta-Kasari, M.: Spectral-based illumination estimation and color correction. Color Research & Application 24, 98–111 (1999)CrossRefGoogle Scholar
  19. 19.
    MacQueen, J.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley Symposium on Mathematical Statistics and Probability, California, USA, vol. 1, pp. 281–297 (1967)Google Scholar
  20. 20.
    Maloney, L.T.: Evaluation of linear models of surface spectral reflectance with small numbers of parameters. J. Opt. Soc. Am. A 3(10), 1673–1683 (1986)CrossRefGoogle Scholar
  21. 21.
    Maloney, L.T., Wandell, B.A.: Color constancy: a method for recovering surface spectral reflectance. J. Opt. Soc. Am. A 3(1), 29–33 (1986)CrossRefGoogle Scholar
  22. 22.
    Marimont, D.H., Wandell, B.A.: Linear models of surface and illuminant spectra. J. Opt. Soc. Am. A 9(11), 1905–1913 (1992)CrossRefGoogle Scholar
  23. 23.
    Park, J.I., Lee, M.H., Grossberg, M.D., Nayar, S.K.: Multispectral imaging using multiplexed illumination. In: International Conference on Computer Vision, pp. 1–8 (2007)Google Scholar
  24. 24.
    Parkkinen, J.P., Hallikainen, J., Jaaskelainen, T.: Characteristic spectra of munsell colors. J. Opt. Soc. Am. A 6(2), 318–322 (1989)CrossRefGoogle Scholar
  25. 25.
    Peyvandi, S., Amirshahi, S.H.: Generalized spectral decomposition: a theory and practice to spectral reconstruction. J. Opt. Soc. Am. A 28(8), 1545–1553 (2011)CrossRefGoogle Scholar
  26. 26.
    Peyvandi, S., Amirshahi, S.H., Hernández-Andrés, J., Nieves, J.L., Romero, J.: Spectral recovery of outdoor illumination by an extension of the bayesian inverse approach to the gaussian mixture model. J. Opt. Soc. Am. A 29(10), 2181–2189 (2012)CrossRefGoogle Scholar
  27. 27.
    Prasad, D.K., Nguyen, R., Brown, M.S.: Quick approximation of camera’s spectral response from casual lighting. In: IEEE International Conference on Computer Vision Workshops, pp. 844–851 (2013)Google Scholar
  28. 28.
    Romero, J., Garcia-Beltran, A., Hernández-Andrés, J.: Linear bases for representation of natural and artificial illuminants. J. Opt. Soc. Am. A 14(5), 1007–1014 (1997)CrossRefGoogle Scholar
  29. 29.
    Sharma, G., Wang, S.: Spectrum recovery from colorimetric data for color reproductions. In: Color Imaging: Device-Independent Color, Color Hardcopy, and Applications VII. Proc. SPIE, vol. 4663, pp. 8–14 (2002)Google Scholar
  30. 30.
    Zhang, X., Xu, H.: Reconstructing spectral reflectance by dividing spectral space and extending the principal components in principal component analysis. J. Opt. Soc. Am. A 25(2), 371–378 (2008)CrossRefGoogle Scholar
  31. 31.
    Zhao, H., Kawakami, R., Tan, R.T., Ikeuchi, K.: Estimating basis functions for spectral sensitivity of digital cameras. In: Meeting on Image Recognition and Understanding, vol. 1 (2009)Google Scholar
  32. 32.
    Zhao, Y., Berns, R.S.: Image-based spectral reflectance reconstruction using the matrix r method. Color Research & Application 32(5), 343–351 (2007)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Rang M. H. Nguyen
    • 1
  • Dilip K. Prasad
    • 1
  • Michael S. Brown
    • 1
  1. 1.School of ComputingNational University of SingaporeSingapore

Personalised recommendations