Abstract

Color pixel distributions provide a useful cue for object recognition but are dependent on scene illumination. We develop an algorithm that assigns color descriptors to an object that depend on the surface properties of the object and not on the illumination. An object is defined by a set of possibly textured surfaces and gives rise to a color pixel distribution. For a trichromatic system, the algorithm assumes a three-dimensional linear model for surface spectral reflectance. There are no assumptions about the contents of the scene and only weak constraints on the illumination. The global color invariants can be computed in an amount of time that is proportional to the number of pixels that define an object. A set of experiments on complex scenes under various illuminants demonstrates that the global color constancy algorithm performs significantly better than previous recognition algorithms based on color distribution.

© 1994 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. M. Nagao, T. Matsuyama, Y. Ikeda, “Region extraction and shape analysis in aerial photographs,” Comput. Graphics Image Process. 10, 195–223 (1979).
    [Crossref]
  2. T. O. Binford, “Survey of model-based image analysis systems,” Int. J. Robot. Res. 1, 18–64 (1982).
    [Crossref]
  3. M. Swain, D. Ballard, “Color indexing,” Int. J. Comput. Vision 7, 11–32 (1991).
    [Crossref]
  4. G. Healey, S. Shafer, L. Wolff, eds., Physics-Based Vision: Principles and Practice. COLOR (Jones & Bartlett, Boston, Mass., 1992).
  5. B. Funt, G. Finlayson, “Color constant color indexing,” Tech. Rep. CSS/LCCR TR 91-09 (Simon Fraser University School of Computing Science, Burnaby, B.C., 1991).
  6. E. H. Land, J. J. McCann, “Lightness and retinex theory,”J. Opt. Soc. Am. 61, 1–11 (1971).
    [Crossref] [PubMed]
  7. P. Sallstrom, “Colour and physics. Some remarks concerning the physical aspects of human colour vision,” Tech. Rep. 73-09 (Institute of Physics, University of Stockholm, 1973).
  8. M. Brill, “A device performing illuminant-invariant assessment of chromatic relations,”J. Theor. Biol. 71, 473–478 (1978).
    [Crossref] [PubMed]
  9. G. Buchsbaum, “A spatial processor model for object colour perception,” J. Franklin Inst. 310, 1–26 (1980).
    [Crossref]
  10. M. D’Zmura, P. Lennie, “Mechanisms of color constancy,” J. Opt. Soc. Am. A 3, 1662–1672 (1986).
    [Crossref]
  11. G. Healey, “Estimating spectral reflectance using highlights,” Image Vision Comput. 9, 333–337 (1991).
    [Crossref]
  12. S. Tominaga, B. Wandell, “Component estimation of surface spectral reflectance,” J. Opt. Soc. Am. A 7, 312–317 (1990).
    [Crossref]
  13. L. Maloney, B. Wandell, “Color constancy: a method for recovering surface spectral reflectance,” J. Opt. Soc. Am. A 3, 29–33 (1986).
    [Crossref] [PubMed]
  14. J. Cohen, “Dependency of the spectral reflectance curves of the Munsell color chips,” Psychonomic Sci. 1, 369–370 (1964).
  15. L. Maloney, “Evaluation of linear models of surface spectral reflectance with small numbers of parameters,” J. Opt. Soc. Am. A 3, 1673–1683 (1986).
    [Crossref] [PubMed]
  16. J. P. S. Parkkinen, J. Hallikainen, T. Jaaskelainen, “Characteristic spectra of Munsell colors,” J. Opt. Soc. Am. A 6, 318–322 (1989).
    [Crossref]
  17. D. Forsyth, “A novel algorithm for color constancy,” Int. J. Comput. Vision 5, 5–36 (1990).
    [Crossref]
  18. J. Ho, B. V. Funt, M. S. Drew, “Separating a color signal into illumination and surface reflectance components: theory and applications,”IEEE Trans. Pattern Anal. Mach. Intell. 12, 966–977 (1990).
    [Crossref]
  19. M. D’Zmura, “Color constancy: surface color from changing illumination,” J. Opt. Soc. Am. A 9, 490–493 (1992).
    [Crossref]
  20. G. Taubin, D. Cooper, “Object recognition based on moment (or algebraic) invariants,” in J. Mundy, A. Zisserman, eds., Geometric Invariance in Computer Vision (MIT Press, Cambridge, Mass., 1992), pp. 375–397.
  21. M. D’Zmura, G. Iverson, “Color constancy. I. Basic theory of two-stage linear recovery of spectral descriptions for lights and surfaces.” J. Opt. Soc. Am. A 10, 2148–2165 (1993).
    [Crossref]

1993 (1)

1992 (1)

1991 (2)

M. Swain, D. Ballard, “Color indexing,” Int. J. Comput. Vision 7, 11–32 (1991).
[Crossref]

G. Healey, “Estimating spectral reflectance using highlights,” Image Vision Comput. 9, 333–337 (1991).
[Crossref]

1990 (3)

S. Tominaga, B. Wandell, “Component estimation of surface spectral reflectance,” J. Opt. Soc. Am. A 7, 312–317 (1990).
[Crossref]

D. Forsyth, “A novel algorithm for color constancy,” Int. J. Comput. Vision 5, 5–36 (1990).
[Crossref]

J. Ho, B. V. Funt, M. S. Drew, “Separating a color signal into illumination and surface reflectance components: theory and applications,”IEEE Trans. Pattern Anal. Mach. Intell. 12, 966–977 (1990).
[Crossref]

1989 (1)

1986 (3)

1982 (1)

T. O. Binford, “Survey of model-based image analysis systems,” Int. J. Robot. Res. 1, 18–64 (1982).
[Crossref]

1980 (1)

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

1979 (1)

M. Nagao, T. Matsuyama, Y. Ikeda, “Region extraction and shape analysis in aerial photographs,” Comput. Graphics Image Process. 10, 195–223 (1979).
[Crossref]

1978 (1)

M. Brill, “A device performing illuminant-invariant assessment of chromatic relations,”J. Theor. Biol. 71, 473–478 (1978).
[Crossref] [PubMed]

1971 (1)

1964 (1)

J. Cohen, “Dependency of the spectral reflectance curves of the Munsell color chips,” Psychonomic Sci. 1, 369–370 (1964).

Ballard, D.

M. Swain, D. Ballard, “Color indexing,” Int. J. Comput. Vision 7, 11–32 (1991).
[Crossref]

Binford, T. O.

T. O. Binford, “Survey of model-based image analysis systems,” Int. J. Robot. Res. 1, 18–64 (1982).
[Crossref]

Brill, M.

M. Brill, “A device performing illuminant-invariant assessment of chromatic relations,”J. Theor. Biol. 71, 473–478 (1978).
[Crossref] [PubMed]

Buchsbaum, G.

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

Cohen, J.

J. Cohen, “Dependency of the spectral reflectance curves of the Munsell color chips,” Psychonomic Sci. 1, 369–370 (1964).

Cooper, D.

G. Taubin, D. Cooper, “Object recognition based on moment (or algebraic) invariants,” in J. Mundy, A. Zisserman, eds., Geometric Invariance in Computer Vision (MIT Press, Cambridge, Mass., 1992), pp. 375–397.

D’Zmura, M.

Drew, M. S.

J. Ho, B. V. Funt, M. S. Drew, “Separating a color signal into illumination and surface reflectance components: theory and applications,”IEEE Trans. Pattern Anal. Mach. Intell. 12, 966–977 (1990).
[Crossref]

Finlayson, G.

B. Funt, G. Finlayson, “Color constant color indexing,” Tech. Rep. CSS/LCCR TR 91-09 (Simon Fraser University School of Computing Science, Burnaby, B.C., 1991).

Forsyth, D.

D. Forsyth, “A novel algorithm for color constancy,” Int. J. Comput. Vision 5, 5–36 (1990).
[Crossref]

Funt, B.

B. Funt, G. Finlayson, “Color constant color indexing,” Tech. Rep. CSS/LCCR TR 91-09 (Simon Fraser University School of Computing Science, Burnaby, B.C., 1991).

Funt, B. V.

J. Ho, B. V. Funt, M. S. Drew, “Separating a color signal into illumination and surface reflectance components: theory and applications,”IEEE Trans. Pattern Anal. Mach. Intell. 12, 966–977 (1990).
[Crossref]

Hallikainen, J.

Healey, G.

G. Healey, “Estimating spectral reflectance using highlights,” Image Vision Comput. 9, 333–337 (1991).
[Crossref]

Ho, J.

J. Ho, B. V. Funt, M. S. Drew, “Separating a color signal into illumination and surface reflectance components: theory and applications,”IEEE Trans. Pattern Anal. Mach. Intell. 12, 966–977 (1990).
[Crossref]

Ikeda, Y.

M. Nagao, T. Matsuyama, Y. Ikeda, “Region extraction and shape analysis in aerial photographs,” Comput. Graphics Image Process. 10, 195–223 (1979).
[Crossref]

Iverson, G.

Jaaskelainen, T.

Land, E. H.

Lennie, P.

Maloney, L.

Matsuyama, T.

M. Nagao, T. Matsuyama, Y. Ikeda, “Region extraction and shape analysis in aerial photographs,” Comput. Graphics Image Process. 10, 195–223 (1979).
[Crossref]

McCann, J. J.

Nagao, M.

M. Nagao, T. Matsuyama, Y. Ikeda, “Region extraction and shape analysis in aerial photographs,” Comput. Graphics Image Process. 10, 195–223 (1979).
[Crossref]

Parkkinen, J. P. S.

Sallstrom, P.

P. Sallstrom, “Colour and physics. Some remarks concerning the physical aspects of human colour vision,” Tech. Rep. 73-09 (Institute of Physics, University of Stockholm, 1973).

Swain, M.

M. Swain, D. Ballard, “Color indexing,” Int. J. Comput. Vision 7, 11–32 (1991).
[Crossref]

Taubin, G.

G. Taubin, D. Cooper, “Object recognition based on moment (or algebraic) invariants,” in J. Mundy, A. Zisserman, eds., Geometric Invariance in Computer Vision (MIT Press, Cambridge, Mass., 1992), pp. 375–397.

Tominaga, S.

Wandell, B.

Comput. Graphics Image Process. (1)

M. Nagao, T. Matsuyama, Y. Ikeda, “Region extraction and shape analysis in aerial photographs,” Comput. Graphics Image Process. 10, 195–223 (1979).
[Crossref]

IEEE Trans. Pattern Anal. Mach. Intell. (1)

J. Ho, B. V. Funt, M. S. Drew, “Separating a color signal into illumination and surface reflectance components: theory and applications,”IEEE Trans. Pattern Anal. Mach. Intell. 12, 966–977 (1990).
[Crossref]

Image Vision Comput. (1)

G. Healey, “Estimating spectral reflectance using highlights,” Image Vision Comput. 9, 333–337 (1991).
[Crossref]

Int. J. Comput. Vision (2)

D. Forsyth, “A novel algorithm for color constancy,” Int. J. Comput. Vision 5, 5–36 (1990).
[Crossref]

M. Swain, D. Ballard, “Color indexing,” Int. J. Comput. Vision 7, 11–32 (1991).
[Crossref]

Int. J. Robot. Res. (1)

T. O. Binford, “Survey of model-based image analysis systems,” Int. J. Robot. Res. 1, 18–64 (1982).
[Crossref]

J. Franklin Inst. (1)

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

J. Opt. Soc. Am. (1)

J. Opt. Soc. Am. A (7)

J. Theor. Biol. (1)

M. Brill, “A device performing illuminant-invariant assessment of chromatic relations,”J. Theor. Biol. 71, 473–478 (1978).
[Crossref] [PubMed]

Psychonomic Sci. (1)

J. Cohen, “Dependency of the spectral reflectance curves of the Munsell color chips,” Psychonomic Sci. 1, 369–370 (1964).

Other (4)

P. Sallstrom, “Colour and physics. Some remarks concerning the physical aspects of human colour vision,” Tech. Rep. 73-09 (Institute of Physics, University of Stockholm, 1973).

G. Healey, S. Shafer, L. Wolff, eds., Physics-Based Vision: Principles and Practice. COLOR (Jones & Bartlett, Boston, Mass., 1992).

B. Funt, G. Finlayson, “Color constant color indexing,” Tech. Rep. CSS/LCCR TR 91-09 (Simon Fraser University School of Computing Science, Burnaby, B.C., 1991).

G. Taubin, D. Cooper, “Object recognition based on moment (or algebraic) invariants,” in J. Mundy, A. Zisserman, eds., Geometric Invariance in Computer Vision (MIT Press, Cambridge, Mass., 1992), pp. 375–397.

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 (17)

Fig. 1
Fig. 1

H(ρ).

Fig. 2
Fig. 2

H ˜(ρ).

Fig. 3
Fig. 3

H().

Fig. 4
Fig. 4

H ˜ ( L ˜ ρ ).

Fig. 5
Fig. 5

Balloon histograms.

Fig. 6
Fig. 6

Cereal box histograms.

Fig. 7
Fig. 7

Chalk box histograms.

Fig. 8
Fig. 8

Dragon histograms.

Fig. 9
Fig. 9

Lemur histograms

Fig. 10
Fig. 10

Tiger histograms.

Fig. 11
Fig. 11

Difference of ratios image.

Plate 9
Plate 9

Balloon.

Plate 10
Plate 10

Cereal box.

Plate 11
Plate 11

Chalk box.

Plate 12
Plate 12

Dragon.

Plate 13
Plate 13

Lemur.

Plate 14
Plate 14

Tiger.

Tables (6)

Tables Icon

Table 1 Invariants: Rank Assigned for Correct Match in Data Base

Tables Icon

Table 2 Invariant Distances

Tables Icon

Table 3 Color Indexing: Rank Assigned for Correct Match in Data Base

Tables Icon

Table 4 Color-Indexing Histogram Intersections

Tables Icon

Table 5 CCCI: Rank Assigned for Correct Match in Data Base

Tables Icon

Table 6 Color-Constant Histogram Intersections

Equations (13)

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

ρ k i = λ l ( λ ) s i ( λ ) f k ( λ ) d λ ,             1 k n ,
s i ( λ ) = 1 j n σ j i S j ( λ ) ,
ρ i = A σ i ,
A k j = λ l ( λ ) S j ( λ ) f k ( λ ) d λ .
ρ i = A σ i ,             ρ ˜ i = A ˜ σ i .
ρ ˜ i = M ρ i ,
H ˜ ( M ρ ) = H ( ρ ) .
A α = 1 H ( ρ ) ( ρ - H ¯ ) α H ( ρ ) d ρ ,
X [ 2 ] ( ρ ) = ( ρ 1 2 2 ,             ρ 1 ρ 2 ,             ρ 1 ρ 3 ,             ρ 2 2 2 ,             ρ 2 ρ 3 ,             ρ 3 2 2 ) T .
X [ 1 , 1 ] ( ρ ) = ( ρ 1 2 ρ 1 ρ 2 ρ 1 ρ 3 ρ 1 ρ 2 ρ 2 2 ρ 2 ρ 3 ρ 1 ρ 3 ρ 2 ρ 3 ρ 3 2 ) .
A [ d ] = 1 H ( ρ ) X [ d ] ( ρ - H ¯ ) H ( ρ ) d ρ ,
A [ k , l ] = 1 H ( ρ ) X [ k , l ] ( ρ - H ¯ ) H ( ρ ) d ρ .
L A [ 1 , 1 ] L T = I ,

Metrics