Correlation-Based Intrinsic Image Extraction from a Single Image

  • Xiaoyue Jiang
  • Andrew J. Schofield
  • Jeremy L. Wyatt
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6314)


Intrinsic images represent the underlying properties of a scene such as illumination (shading) and surface reflectance. Extracting intrinsic images is a challenging, ill-posed problem. Human performance on tasks such as shadow detection and shape-from-shading is improved by adding colour and texture to surfaces. In particular, when a surface is painted with a textured pattern, correlations between local mean luminance and local luminance amplitude promote the interpretation of luminance variations as illumination changes. Based on this finding, we propose a novel feature, local luminance amplitude, to separate illumination and reflectance, and a framework to integrate this cue with hue and texture to extract intrinsic images. The algorithm uses steerable filters to separate images into frequency and orientation components and constructs shading and reflectance images from weighted combinations of these components. Weights are determined by correlations between corresponding variations in local luminance, local amplitude, colour and texture. The intrinsic images are further refined by ensuring the consistency of local texture elements. We test this method on surfaces photographed under different lighting conditions. The effectiveness of the algorithm is demonstrated by the correlation between our intrinsic images and ground truth shading and reflectance data. Luminance amplitude was found to be a useful cue. Results are also presented for natural images.


Ground Truth Single Image Illumination Change Texture Modulation Ground Truth Image 
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.

Supplementary material

978-3-642-15561-1_5_MOESM1_ESM.pdf (1 mb)
Electronic Supplementary Material (1,0315 KB)


  1. 1.
    Barrow, H.G., Tanenbaum, J.M.: Recovering intrinsic scene characteristics from images. Computer Vision systems, 3–26 (1978)Google Scholar
  2. 2.
    Land, E.H., McCann, J.J.: Lightness and retinex theory. Journal of the Optical Society of America A 61, 1–11 (1971)CrossRefGoogle Scholar
  3. 3.
    Sinha, P., Adelson, E.: Recovering reflectance and illumination in a world of painted polyhedra. In: ICCV, pp. 156–163 (1993)Google Scholar
  4. 4.
    Bell, M., Freeman, W.T.: Learning local evidence for shading and reflectance. In: ICCV, vol. 1, pp. 670–677 (2001)Google Scholar
  5. 5.
    Funt, B.V., Drew, M.S., Brockington, M.: Recovering shading from color images. In: Sandini, G. (ed.) ECCV 1992. LNCS, vol. 588, pp. 124–132. Springer, Heidelberg (1992)Google Scholar
  6. 6.
    Olmos, A., Kingdom, F.A.A.: A biologically inspired algorithm for the reconvery of shading and reflectance images. Perception 33, 1463–1473 (2004)CrossRefGoogle Scholar
  7. 7.
    Tappen, M.F., Freeman, W.T., Adelson, E.H.: Recovering intrinsic images from a single image. IEEE Trans. Pattern Anal. Mach. Intell. 27, 1459–1472 (2005)CrossRefGoogle Scholar
  8. 8.
    Parraga, C.A., Troscianko, T., Tolhurst, D.J.: Spatiochromatic properties of natural images and human vision. Current Biology 12, 483–487 (2002)CrossRefGoogle Scholar
  9. 9.
    Finlayson, G.D., Hordley, S.D., Lu, C., Drew, M.: On the removal of shadows from images. IEEE Trans. Pattern Analysis and Machine Intelligence 28, 59–68 (2006)CrossRefGoogle Scholar
  10. 10.
    Kingdom, F.A.A.: Perceiving light versus material. Vis. Res. 48, 2090–2105 (2008)CrossRefGoogle Scholar
  11. 11.
    Shen, L., Tan, P., Lin, S.: Intrinsic image decomposition with non-local texture cues. In: IEEE Computer Vision and Pattern Recognition, pp. 1–7 (2008)Google Scholar
  12. 12.
    Weiss, Y.: Deriving intrinsic images from image sequences. In: ICCV, vol. 2, pp. 68–75 (2001)Google Scholar
  13. 13.
    Agrawal, A., Raskar, R., Chellappa, R.: Edge suppression by gradient field transformation using cross projection tensors. In: CVPR, vol. 2, pp. 2301–2308 (2006)Google Scholar
  14. 14.
    Matsushita, Y., Lin, S., Kang, S.B., Shum, H.Y.: Estimating intrinsic images from image sequences with biased illumination. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3022, pp. 274–286. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  15. 15.
    Schofield, A.J., Hesse, G., Rock, P.B., Georgeson, M.A.: Local luminance amplitude modulates the interpretation of shape-from-shading in textured surfaces. Vision Research 46, 3462–3482 (2006)CrossRefGoogle Scholar
  16. 16.
    Simoncelli, E.P., Freeman, W.T.: The steerable pyramid: A flexible architecture for multi-scale derivative computation. In: ICIP, pp. 444–447 (1995)Google Scholar
  17. 17.
    Comanicu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. 24, 603–619 (2004)CrossRefGoogle Scholar
  18. 18.
    Reinhard, E., Devlin, K.: Dynamic range reduction inspired by photoreceptor physiology. IEEE Trans. Visualization and Computer Graphics 11, 13–24 (2005)CrossRefGoogle Scholar
  19. 19.
    Waltz, R.A., Morales, J.L., Nocedal, J., Orban, D.: An interior algorithm for nonlinear optimization that combines line search and trust region steps. Mathematical Programming 107, 391–408 (2006)zbMATHCrossRefMathSciNetGoogle Scholar
  20. 20.
    Grosse, R., Johnson, M.K., Adelson, E.H., Freeman, W.T.: Ground-truth dataset and baseline evaluations for intrinsic image algorithms. In: ICCV (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Xiaoyue Jiang
    • 1
  • Andrew J. Schofield
    • 1
  • Jeremy L. Wyatt
    • 2
  1. 1.School of PsychologyUniversity of BirminghamBirminghamUK
  2. 2.School of Computer ScienceUniversity of BirminghamUK

Personalised recommendations