Abstract

In this paper, a robust illuminant estimation algorithm for color constancy is proposed. Considering the drawback of the well-known max-RGB algorithm, which regards only pixels with the maximum image intensities, we explore the representative pixels from an image for illuminant estimation: The representative pixels are determined via the intensity bounds corresponding to a certain percentage value in the normalized accumulative histograms. To achieve the suitable percentage, an iterative algorithm is presented by simultaneously neutralizing the chromaticity distribution and preventing overcorrection. The experimental results on the benchmark databases provided by Simon Fraser University and Microsoft Research Cambridge, as well as several web images, demonstrate the effectiveness of our approach.

© 2012 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. A. Gijsenij, T. Gevers, and J. van de Weijer, “Computational color constancy: survey and experiments,” IEEE Trans. Image Process. 20, 2475–2489 (2011).
    [CrossRef]
  2. D. H. Foster, “Color constancy,” Vis. Res. 51, 674–700 (2011).
    [CrossRef]
  3. J. M. Geusebroek, R. V. D. Boomgaard, and A. W. M. Smeulders, “Color invariance,” IEEE Trans. PAMI 23, 1338–1350 (2001).
    [CrossRef]
  4. T. Gevers and A. W. M. Smeulders, “Color based object recognition,” Pattern Recogn. 32, 453–464 (1999).
    [CrossRef]
  5. E. H. Land and J. J. McCann, “Lightness and retinex theory,” J. Opt. Soc. Am. A 61, 1–11 (1971).
    [CrossRef]
  6. G. Buchsbaum, “A spatial processor model for object color perception,” J. Franklin Inst. 310, 1–26 (1980).
    [CrossRef]
  7. G. D. Finlayson and E. Trezzi, “Shades of gray and color constancy,” in Proceedings of the 12th Color Imaging Conference (IS&T/SID, 2004), pp. 37–41.
  8. J. van de Weijer, T. Gevers, and A. Gijsenij, “Edge-based color constancy,” IEEE Trans. Image Process. 16, 2207–2214 (2007).
    [CrossRef]
  9. D. Forsth, “A novel algorithm for color constancy,” Int. J. Comput. Vis. 5, 5–36 (1990).
    [CrossRef]
  10. A. Gijsenij, T. Gevers, and J. van de Weijer, “Generalized gamut mapping using image derivative structures for color constancy,” Int. J. Comput. Vis. 86, 127–139 (2010).
    [CrossRef]
  11. G. D. Finlayson, S. D. Hordley, and R. Xu, “Convex programming colour constancy with a diagonal-offset model,” in Proceedings of IEEE International Conference on Image Processing (IEEE, 2005), pp. 948–951.
  12. R. T. Tan, K. Nishino, and K. Ikeuchi, “Illumination chromaticity estimation using inverse-intensity chromaticity space,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2003), pp. 673–680.
  13. K. Barnard, L. Martin, A. Coath, and B. Funt, “A comparison of computational color constancy algorithms—Part II: experiments with image data,” IEEE Trans. Image Process. 11, 985–996 (2002).
    [CrossRef]
  14. B. Funt and L. Shi, “MaxRGB reconsidered,” J. Imaging Sci. Technol. 56, 20501 (2012).
    [CrossRef]
  15. F. Gasparini and R. Schettini, “Color balancing of digital photos using simple image statistics,” Pattern Recogn. 37, 1201–1217 (2004).
    [CrossRef]
  16. S. Tominaga, S. Ebisui, and B. A. Wandell, “Scene illuminant classification: brighter is better,” J. Opt. Soc. Am. A 18, 55–64 (2001).
    [CrossRef]
  17. K. Barnard, L. Martin, B. Funt, and A. Coath, “A data set for color research,” Color Res. Appl. 27, 147–151 (2002).
    [CrossRef]
  18. P. V. Gehler, C. Rother, A. Blake, T. Minka, and T. Sharp, “Bayesian color constancy revisited,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2008), pp. 1–8.
  19. A. Gijsenij, T. Gevers, and M. Lucassen, “A perceptual analysis of distance measures for color constancy algorithms,” J. Opt. Soc. Am. A 26, 2243–2256 (2009).
    [CrossRef]
  20. S. Hordley and G. Finlayson, “Reevaluation of color constancy algorithm performance,” J. Opt. Soc. Am. A 23, 1008–1020 (2006).
    [CrossRef]
  21. A. Gijsenij and T. Gevers, “Color constancy: research website on illuminant estimation,” http://colorconstancy.com .

2012 (1)

B. Funt and L. Shi, “MaxRGB reconsidered,” J. Imaging Sci. Technol. 56, 20501 (2012).
[CrossRef]

2011 (2)

A. Gijsenij, T. Gevers, and J. van de Weijer, “Computational color constancy: survey and experiments,” IEEE Trans. Image Process. 20, 2475–2489 (2011).
[CrossRef]

D. H. Foster, “Color constancy,” Vis. Res. 51, 674–700 (2011).
[CrossRef]

2010 (1)

A. Gijsenij, T. Gevers, and J. van de Weijer, “Generalized gamut mapping using image derivative structures for color constancy,” Int. J. Comput. Vis. 86, 127–139 (2010).
[CrossRef]

2009 (1)

2007 (1)

J. van de Weijer, T. Gevers, and A. Gijsenij, “Edge-based color constancy,” IEEE Trans. Image Process. 16, 2207–2214 (2007).
[CrossRef]

2006 (1)

2004 (1)

F. Gasparini and R. Schettini, “Color balancing of digital photos using simple image statistics,” Pattern Recogn. 37, 1201–1217 (2004).
[CrossRef]

2002 (2)

K. Barnard, L. Martin, B. Funt, and A. Coath, “A data set for color research,” Color Res. Appl. 27, 147–151 (2002).
[CrossRef]

K. Barnard, L. Martin, A. Coath, and B. Funt, “A comparison of computational color constancy algorithms—Part II: experiments with image data,” IEEE Trans. Image Process. 11, 985–996 (2002).
[CrossRef]

2001 (2)

J. M. Geusebroek, R. V. D. Boomgaard, and A. W. M. Smeulders, “Color invariance,” IEEE Trans. PAMI 23, 1338–1350 (2001).
[CrossRef]

S. Tominaga, S. Ebisui, and B. A. Wandell, “Scene illuminant classification: brighter is better,” J. Opt. Soc. Am. A 18, 55–64 (2001).
[CrossRef]

1999 (1)

T. Gevers and A. W. M. Smeulders, “Color based object recognition,” Pattern Recogn. 32, 453–464 (1999).
[CrossRef]

1990 (1)

D. Forsth, “A novel algorithm for color constancy,” Int. J. Comput. Vis. 5, 5–36 (1990).
[CrossRef]

1980 (1)

G. Buchsbaum, “A spatial processor model for object color perception,” J. Franklin Inst. 310, 1–26 (1980).
[CrossRef]

1971 (1)

E. H. Land and J. J. McCann, “Lightness and retinex theory,” J. Opt. Soc. Am. A 61, 1–11 (1971).
[CrossRef]

Barnard, K.

K. Barnard, L. Martin, A. Coath, and B. Funt, “A comparison of computational color constancy algorithms—Part II: experiments with image data,” IEEE Trans. Image Process. 11, 985–996 (2002).
[CrossRef]

K. Barnard, L. Martin, B. Funt, and A. Coath, “A data set for color research,” Color Res. Appl. 27, 147–151 (2002).
[CrossRef]

Blake, A.

P. V. Gehler, C. Rother, A. Blake, T. Minka, and T. Sharp, “Bayesian color constancy revisited,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2008), pp. 1–8.

Boomgaard, R. V. D.

J. M. Geusebroek, R. V. D. Boomgaard, and A. W. M. Smeulders, “Color invariance,” IEEE Trans. PAMI 23, 1338–1350 (2001).
[CrossRef]

Buchsbaum, G.

G. Buchsbaum, “A spatial processor model for object color perception,” J. Franklin Inst. 310, 1–26 (1980).
[CrossRef]

Coath, A.

K. Barnard, L. Martin, A. Coath, and B. Funt, “A comparison of computational color constancy algorithms—Part II: experiments with image data,” IEEE Trans. Image Process. 11, 985–996 (2002).
[CrossRef]

K. Barnard, L. Martin, B. Funt, and A. Coath, “A data set for color research,” Color Res. Appl. 27, 147–151 (2002).
[CrossRef]

Ebisui, S.

Finlayson, G.

Finlayson, G. D.

G. D. Finlayson, S. D. Hordley, and R. Xu, “Convex programming colour constancy with a diagonal-offset model,” in Proceedings of IEEE International Conference on Image Processing (IEEE, 2005), pp. 948–951.

G. D. Finlayson and E. Trezzi, “Shades of gray and color constancy,” in Proceedings of the 12th Color Imaging Conference (IS&T/SID, 2004), pp. 37–41.

Forsth, D.

D. Forsth, “A novel algorithm for color constancy,” Int. J. Comput. Vis. 5, 5–36 (1990).
[CrossRef]

Foster, D. H.

D. H. Foster, “Color constancy,” Vis. Res. 51, 674–700 (2011).
[CrossRef]

Funt, B.

B. Funt and L. Shi, “MaxRGB reconsidered,” J. Imaging Sci. Technol. 56, 20501 (2012).
[CrossRef]

K. Barnard, L. Martin, A. Coath, and B. Funt, “A comparison of computational color constancy algorithms—Part II: experiments with image data,” IEEE Trans. Image Process. 11, 985–996 (2002).
[CrossRef]

K. Barnard, L. Martin, B. Funt, and A. Coath, “A data set for color research,” Color Res. Appl. 27, 147–151 (2002).
[CrossRef]

Gasparini, F.

F. Gasparini and R. Schettini, “Color balancing of digital photos using simple image statistics,” Pattern Recogn. 37, 1201–1217 (2004).
[CrossRef]

Gehler, P. V.

P. V. Gehler, C. Rother, A. Blake, T. Minka, and T. Sharp, “Bayesian color constancy revisited,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2008), pp. 1–8.

Geusebroek, J. M.

J. M. Geusebroek, R. V. D. Boomgaard, and A. W. M. Smeulders, “Color invariance,” IEEE Trans. PAMI 23, 1338–1350 (2001).
[CrossRef]

Gevers, T.

A. Gijsenij, T. Gevers, and J. van de Weijer, “Computational color constancy: survey and experiments,” IEEE Trans. Image Process. 20, 2475–2489 (2011).
[CrossRef]

A. Gijsenij, T. Gevers, and J. van de Weijer, “Generalized gamut mapping using image derivative structures for color constancy,” Int. J. Comput. Vis. 86, 127–139 (2010).
[CrossRef]

A. Gijsenij, T. Gevers, and M. Lucassen, “A perceptual analysis of distance measures for color constancy algorithms,” J. Opt. Soc. Am. A 26, 2243–2256 (2009).
[CrossRef]

J. van de Weijer, T. Gevers, and A. Gijsenij, “Edge-based color constancy,” IEEE Trans. Image Process. 16, 2207–2214 (2007).
[CrossRef]

T. Gevers and A. W. M. Smeulders, “Color based object recognition,” Pattern Recogn. 32, 453–464 (1999).
[CrossRef]

Gijsenij, A.

A. Gijsenij, T. Gevers, and J. van de Weijer, “Computational color constancy: survey and experiments,” IEEE Trans. Image Process. 20, 2475–2489 (2011).
[CrossRef]

A. Gijsenij, T. Gevers, and J. van de Weijer, “Generalized gamut mapping using image derivative structures for color constancy,” Int. J. Comput. Vis. 86, 127–139 (2010).
[CrossRef]

A. Gijsenij, T. Gevers, and M. Lucassen, “A perceptual analysis of distance measures for color constancy algorithms,” J. Opt. Soc. Am. A 26, 2243–2256 (2009).
[CrossRef]

J. van de Weijer, T. Gevers, and A. Gijsenij, “Edge-based color constancy,” IEEE Trans. Image Process. 16, 2207–2214 (2007).
[CrossRef]

Hordley, S.

Hordley, S. D.

G. D. Finlayson, S. D. Hordley, and R. Xu, “Convex programming colour constancy with a diagonal-offset model,” in Proceedings of IEEE International Conference on Image Processing (IEEE, 2005), pp. 948–951.

Ikeuchi, K.

R. T. Tan, K. Nishino, and K. Ikeuchi, “Illumination chromaticity estimation using inverse-intensity chromaticity space,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2003), pp. 673–680.

Land, E. H.

E. H. Land and J. J. McCann, “Lightness and retinex theory,” J. Opt. Soc. Am. A 61, 1–11 (1971).
[CrossRef]

Lucassen, M.

Martin, L.

K. Barnard, L. Martin, B. Funt, and A. Coath, “A data set for color research,” Color Res. Appl. 27, 147–151 (2002).
[CrossRef]

K. Barnard, L. Martin, A. Coath, and B. Funt, “A comparison of computational color constancy algorithms—Part II: experiments with image data,” IEEE Trans. Image Process. 11, 985–996 (2002).
[CrossRef]

McCann, J. J.

E. H. Land and J. J. McCann, “Lightness and retinex theory,” J. Opt. Soc. Am. A 61, 1–11 (1971).
[CrossRef]

Minka, T.

P. V. Gehler, C. Rother, A. Blake, T. Minka, and T. Sharp, “Bayesian color constancy revisited,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2008), pp. 1–8.

Nishino, K.

R. T. Tan, K. Nishino, and K. Ikeuchi, “Illumination chromaticity estimation using inverse-intensity chromaticity space,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2003), pp. 673–680.

Rother, C.

P. V. Gehler, C. Rother, A. Blake, T. Minka, and T. Sharp, “Bayesian color constancy revisited,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2008), pp. 1–8.

Schettini, R.

F. Gasparini and R. Schettini, “Color balancing of digital photos using simple image statistics,” Pattern Recogn. 37, 1201–1217 (2004).
[CrossRef]

Sharp, T.

P. V. Gehler, C. Rother, A. Blake, T. Minka, and T. Sharp, “Bayesian color constancy revisited,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2008), pp. 1–8.

Shi, L.

B. Funt and L. Shi, “MaxRGB reconsidered,” J. Imaging Sci. Technol. 56, 20501 (2012).
[CrossRef]

Smeulders, A. W. M.

J. M. Geusebroek, R. V. D. Boomgaard, and A. W. M. Smeulders, “Color invariance,” IEEE Trans. PAMI 23, 1338–1350 (2001).
[CrossRef]

T. Gevers and A. W. M. Smeulders, “Color based object recognition,” Pattern Recogn. 32, 453–464 (1999).
[CrossRef]

Tan, R. T.

R. T. Tan, K. Nishino, and K. Ikeuchi, “Illumination chromaticity estimation using inverse-intensity chromaticity space,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2003), pp. 673–680.

Tominaga, S.

Trezzi, E.

G. D. Finlayson and E. Trezzi, “Shades of gray and color constancy,” in Proceedings of the 12th Color Imaging Conference (IS&T/SID, 2004), pp. 37–41.

van de Weijer, J.

A. Gijsenij, T. Gevers, and J. van de Weijer, “Computational color constancy: survey and experiments,” IEEE Trans. Image Process. 20, 2475–2489 (2011).
[CrossRef]

A. Gijsenij, T. Gevers, and J. van de Weijer, “Generalized gamut mapping using image derivative structures for color constancy,” Int. J. Comput. Vis. 86, 127–139 (2010).
[CrossRef]

J. van de Weijer, T. Gevers, and A. Gijsenij, “Edge-based color constancy,” IEEE Trans. Image Process. 16, 2207–2214 (2007).
[CrossRef]

Wandell, B. A.

Xu, R.

G. D. Finlayson, S. D. Hordley, and R. Xu, “Convex programming colour constancy with a diagonal-offset model,” in Proceedings of IEEE International Conference on Image Processing (IEEE, 2005), pp. 948–951.

Color Res. Appl. (1)

K. Barnard, L. Martin, B. Funt, and A. Coath, “A data set for color research,” Color Res. Appl. 27, 147–151 (2002).
[CrossRef]

IEEE Trans. Image Process. (3)

K. Barnard, L. Martin, A. Coath, and B. Funt, “A comparison of computational color constancy algorithms—Part II: experiments with image data,” IEEE Trans. Image Process. 11, 985–996 (2002).
[CrossRef]

A. Gijsenij, T. Gevers, and J. van de Weijer, “Computational color constancy: survey and experiments,” IEEE Trans. Image Process. 20, 2475–2489 (2011).
[CrossRef]

J. van de Weijer, T. Gevers, and A. Gijsenij, “Edge-based color constancy,” IEEE Trans. Image Process. 16, 2207–2214 (2007).
[CrossRef]

IEEE Trans. PAMI (1)

J. M. Geusebroek, R. V. D. Boomgaard, and A. W. M. Smeulders, “Color invariance,” IEEE Trans. PAMI 23, 1338–1350 (2001).
[CrossRef]

Int. J. Comput. Vis. (2)

D. Forsth, “A novel algorithm for color constancy,” Int. J. Comput. Vis. 5, 5–36 (1990).
[CrossRef]

A. Gijsenij, T. Gevers, and J. van de Weijer, “Generalized gamut mapping using image derivative structures for color constancy,” Int. J. Comput. Vis. 86, 127–139 (2010).
[CrossRef]

J. Franklin Inst. (1)

G. Buchsbaum, “A spatial processor model for object color perception,” J. Franklin Inst. 310, 1–26 (1980).
[CrossRef]

J. Imaging Sci. Technol. (1)

B. Funt and L. Shi, “MaxRGB reconsidered,” J. Imaging Sci. Technol. 56, 20501 (2012).
[CrossRef]

J. Opt. Soc. Am. A (4)

Pattern Recogn. (2)

F. Gasparini and R. Schettini, “Color balancing of digital photos using simple image statistics,” Pattern Recogn. 37, 1201–1217 (2004).
[CrossRef]

T. Gevers and A. W. M. Smeulders, “Color based object recognition,” Pattern Recogn. 32, 453–464 (1999).
[CrossRef]

Vis. Res. (1)

D. H. Foster, “Color constancy,” Vis. Res. 51, 674–700 (2011).
[CrossRef]

Other (5)

G. D. Finlayson, S. D. Hordley, and R. Xu, “Convex programming colour constancy with a diagonal-offset model,” in Proceedings of IEEE International Conference on Image Processing (IEEE, 2005), pp. 948–951.

R. T. Tan, K. Nishino, and K. Ikeuchi, “Illumination chromaticity estimation using inverse-intensity chromaticity space,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2003), pp. 673–680.

G. D. Finlayson and E. Trezzi, “Shades of gray and color constancy,” in Proceedings of the 12th Color Imaging Conference (IS&T/SID, 2004), pp. 37–41.

P. V. Gehler, C. Rother, A. Blake, T. Minka, and T. Sharp, “Bayesian color constancy revisited,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2008), pp. 1–8.

A. Gijsenij and T. Gevers, “Color constancy: research website on illuminant estimation,” http://colorconstancy.com .

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (8)

Fig. 1.
Fig. 1.

Two critical clues for developing our color constancy approach. (a) Example image with the yellowish color deviation. (b) Color-corrected image based on the ground-truth illuminant color. (c), (d) are the chromaticity distributions (blue dots) of (a), (b) on the a*b* plane, and the red point is the median chromaticity. (e), (f) are the lightness images L* of (a), (b). Clearly, the change of the chromaticity is larger than that of the lightness, and an image under the white light like (b) has a nearly neutral distribution; that is, the median chromaticity is very close to the neutral point (a*=0, b*=0).

Fig. 2.
Fig. 2.

Flowchart of the proposed color constancy method: Color calibration step corrects the input image via the estimated illuminant and the Von Kries model. Details are described in Section 3.

Fig. 3.
Fig. 3.

(a) Image with the greenish color deviation. (b) Corresponding normalized accumulative color histograms HRA, HGA, HBA. After selecting a suitable percentage p, the representative pixels can be directly obtained by the intensity bounds Rp, Gp, Bp.

Fig. 4.
Fig. 4.

a*b* distribution (green circular dots) and the median chromaticities (red triangular dots) of a greenish input image and of subsequent corrected images at different percentage values. As shown, increasing the percentage value moves the median chromaticity toward the neutral point at a*=0 and b*=0; the neutralization distance, calculated by L2 distance, also becomes smaller. In addition, when the gap between the maximum and the minimum components (illustrated with RGB bars) of the L2-normalized illuminant color is larger than a certain threshold, the overcorrection problem occurs (as shown in the bottom-right example at p=45%). The reddish deviation can be obviously seen from the brightest intensity part in the red channel image, compared to the deviations of p=1% and p=10%.

Fig. 5.
Fig. 5.

Color-corrected results of two SFU test images with various illuminant estimation methods (annotated above the images). Angular errors of all methods are also shown in the right-bottom portion of the color-corrected images.

Fig. 6.
Fig. 6.

Color-corrected results of two MRC test images with various illuminant estimation methods (annotated above the images). Angular errors of all methods are also shown in the right-bottom portion of the color-corrected images.

Fig. 7.
Fig. 7.

Color-corrected results of web images (rendered under the reddish, greenish, bluish, and nearly neutral light source) with several low-level statistics-based approaches and the proposed method (annotated above the images). The numbers in (·) represent the total scores given by the 14 subjects for subjective performance judgment (the highest score that an algorithm can get on each image is 42).

Fig. 8.
Fig. 8.

Color-corrected results of the red room illuminated by the white light (upper row) and the white room illuminated by the red light (bottom row): Several low-level statistics-based approaches and the proposed method (annotated above the images) are compared in this experiment.

Tables (5)

Tables Icon

Table 1. Illuminant Estimation with Representative Pixels

Tables Icon

Table 2. Percentage Selection by Chromaticity Neutralization

Tables Icon

Table 3. Summarized Angular Errors (unit: degree) and SD Values of the Proposed and the Compared Methods on the SFU Real-World Image Set (11,346 images)

Tables Icon

Table 4. Summarized Angular Errors (unit: degree) and SD Values of the Proposed and the Compared Methods on the MRC Real-World Image Set (568 images)

Tables Icon

Table 5. Summarized Angular Errors (unit: degree) and SD Values of the Proposed and the Compared Methods on Part of a MRC Real-World Image Set with Larger Color Deviations (200 images)

Equations (1)

Equations on this page are rendered with MathJax. Learn more.

εangle=cos1(eE·eGeEeG).

Metrics