© The Institution of Engineering and Technology
Illumination estimation is important in many approaches to colour constancy, where object colour is measured without the effect of the spectral distribution of the illumination. Many illumination estimation methods for achieving colour constancy, particularly those based on the dichromatic reflection model, have performance limitations because they operate on images composed of blended specular and diffuse reflection components, and they may require image segmentation into regions; segmentation is a well-known image-processing challenge. This study proposes an illumination estimation method, which uses constrained blind signal separation anchored on the dichromatic reflection model, connected to a linear model of the illumination spectrum. Unlike conventional methods that use mixed-image components, the proposed method uses a specular image component extracted explicitly by blind signal separation. This can yield better illumination estimates, and blind signal separation can avoid image segmentation problems. Results of experiments show that the proposed method can recover the illumination spectral distribution, and that the extracted specular component yields better illumination estimation than mixed components. Similar results were observed for the two blind signal separation techniques assessed in this study; namely, the spatially constrained FastICA and independent component analysis based on mutual information.
References
-
-
1)
-
Shrestha, R., Hardeberg, J.Y.: `Computational color constancy using a stereo camera', Sixth European Conf. Colour in Graphics, Imaging, and Vision (CGIV), 2012, 1, p. 69–74.
-
2)
-
K. Barnard ,
L. Martin ,
A. Coath ,
B. Funt
.
A comparison of computational color constancy algorithms-part II experiments with image data.
IEEE Trans. Image Process.
,
9 ,
985 -
996
-
3)
-
Finlayson, G., Schaefer, G.: `Convex and non-convex illuminant constraints for dichromatic colour constancy', Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 2001, 1, p. 598–604.
-
4)
-
A. Hyvarinen ,
E. Oja
.
A fast fixed-point algorithm for independent component analysis.
Neural Comput.
,
1483 -
1492
-
5)
-
S. Tominaga ,
B. Wandell
.
Standard surface-reflectance model and illuminant estimation.
J. Opt. Soc. Am. A
,
4 ,
576 -
584
-
6)
-
S. Umeyama ,
G. Godin
.
Separation of diffuse and specular components of surface reflection by use of polarization and statistical analysis of images.
IEEE Trans. Pattern Anal. Mach. Intell.
,
5 ,
639 -
647
-
7)
-
N. Das ,
A. Routray ,
P. Dash ,
D. India
.
Ica methods for blind source separation of instantaneous mixtures: a case study.
Neural Inf. Process., Lett. Rev.
,
11 ,
225 -
246
-
8)
-
A. Paviotti ,
D.A. Forsyth ,
G.M. Cortelazzo
.
Lightness recovery for pictorial surfaces.
Int. J. Comput. Vis.
,
1 ,
54 -
77
-
9)
-
A. Gijsenij ,
T. Gevers ,
J. van de Weijer
.
Generalized gamut mapping using image derivative structures for color constancy.
Int. J. Comput. Vis.
,
127 -
139
-
10)
-
A. Cichocki ,
S.i. Amari
.
(2003)
Adaptive blind signal and image processing: learing algorithm and applications.
-
11)
-
J. Toro ,
B. Funt
.
A multilinear constraint on dichromatic planes for illumination estimation.
IEEE Trans. Image Process.
,
1 ,
92 -
97
-
12)
-
J. Nieves ,
C. Plata ,
E. Valero ,
J. Romero
.
Unsupervised illuminant estimation from natural scenes: an rgb digital camera suffices.
Appl. Opt.
,
20 ,
3574 -
3584
-
13)
-
E. Huizingh
.
(2007)
Applied Statistics with SPSS.
-
14)
-
C.W. Hesse ,
C.J. James
.
The FastICA algorithm with spatial constraints.
IEEE Signal Process. Lett.
,
11 ,
792 -
795
-
15)
-
Yonghong, L., Haixia, L., Aichun, Y.: `Color recovering based on dichromatic reflection model and finite dimensional linear model', Proc. Int. Conf. Measuring Technology and Mechatronics Automation, April 2009, 1, p. 441–444.
-
16)
-
R. Tan ,
K. Ikeuchi ,
K. Nishino
.
Color constancy through inverse-intensity chromaticity space.
J. Opt. Soc. Am. A
,
21 ,
321 -
334
-
17)
-
H. Lee
.
Method for computing the scene-illuminant chromaticity from specular highlights.
J. Opt. Soc. Am. A
,
10 ,
1694 -
1699
-
18)
-
Tan, R.T.: `Illumination color and intrinsic surface properties-physics-based color analyses from a single image', 2003, PhD, The University of Tokyo.
-
19)
-
D. Foster
.
Color constancy.
Vis. Res.
,
7 ,
674 -
700
-
20)
-
H. Lee ,
E. Breneman ,
C. Schulte
.
Modeling light reflection for computer color vision.
IEEE Trans. Pattern Anal. Mach. Intell.
,
4 ,
402 -
409
-
21)
-
D. Judd ,
D. MacAdam ,
G. Wyszecki ,
H. Budde ,
H. Condit ,
S. Henderson ,
J. Simonds
.
Spectral distribution of typical daylight as a function of correlated color temperature.
J. Opt. Soc. Am.
,
8 ,
1031 -
1040
-
22)
-
Kino flo lighting systems, ‘true match lamps spectral charts’. Available at http:// www.kinoflo.com/Kino.
-
23)
-
The imaging source, ‘spectral sensitivity and color formats’. Available at http://www.theimagingsource.com.
-
24)
-
R. Tan ,
K. Ikeuchi
.
Separating reflection components of textured surfaces using a single image.
IEEE Trans. Pattern Anal. Mach. Intell.
,
2 ,
178 -
193
-
25)
-
G. Finlayson ,
G. Schaefer
.
Solving for colour constancy using a constrained dichromatic reflection model.
Int. J. Comput. Vis.
,
3 ,
127 -
144
-
26)
-
L.T. Maloney ,
D.H. Brainard
.
Color and material perception: achievements and challenges.
J. Vis.
,
9 ,
1 -
6
-
27)
-
Gijsenij, A., Gevers, T.: `Color constancy using image regions', Proc. IEEE Int. Conf. Image Processing, October 2007, 3, p. 501–504.
-
28)
-
I. Marin-Franch ,
D. Foster
.
Estimating information from image colors: an application to digital cameras and natural scenes.
IEEE Trans. Pattern Anal. Mach. Intell.
-
29)
-
S.D. Hordley
.
Scene illuminant estimation: past, present, and future.
Color Res. Appl.
,
4 ,
303 -
314
-
30)
-
D.H. Foster ,
S.M.C. Nascimento ,
K. Amano
.
Information limits on neural identification of colored surfaces in natural scenes.
Vis. Neurosci.
,
3 ,
331 -
336
-
31)
-
Yao, L.: `Estimation illumination chromaticity', Proc. Second Int. Symp. Intelligent Information Technology Application, 2008, 3, p. 756–760.
-
32)
-
T. Lehmann ,
C. Palm
.
Color line search for illuminant estimation in real-world scenes.
J. Opt. Soc. Am. A
,
11 ,
2679 -
2691
-
33)
-
Kwon, O., Cho, Y., Kim, Y., Ha, Y.: `Illumination estimation based on valid pixel selection in highlight region', Proc. Int. Conf. Image Processing, 2004, 4, p. 2419–2422.
-
34)
-
S. Tominaga ,
B. Wandell
.
Natural scene-illuminant estimation using the sensor correlation.
Proc. IEEE
,
1 ,
42 -
56
-
35)
-
K. Barnard ,
V. Cardei ,
B. Funt
.
A comparison of computational color constancy algorithms-part I: methodology and experiments with synthesized data.
IEEE Trans. Image Process.
,
9 ,
972 -
984
-
36)
-
S. Shafer
.
Using color to separate reflection components.
Color Res. Appl.
,
4 ,
210 -
218
-
37)
-
E.M. Valero ,
J.L. Nieves ,
S.M.C. Nascimento ,
K. Amano ,
D.H. Foster
.
Recovering spectral data from natural scenes with an RGB digital camera and colored filters.
Color Res. Appl.
,
5 ,
352 -
360
-
38)
-
J. Toro
.
Dichromatic illumination estimation without pre-segmentation.
Pattern Recognit. Lett.
,
7 ,
871 -
877
-
39)
-
Schaefer, G.: `Robust dichromatic colour constancy', Proc. Int. Conf. Image Analysis and Recognition, 2004, 3212, p. 257–264.
-
40)
-
G. Klinker ,
S. Shafer ,
T. Kanade
.
A physical approach to color image understanding.
Int. J. Comput. Vis.
,
1 ,
7 -
38
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2011.0376
Related content
content/journals/10.1049/iet-ipr.2011.0376
pub_keyword,iet_inspecKeyword,pub_concept
6
6