This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Color Constancy with Spatio-Spectral Statistics
Aug. 2012 (vol. 34 no. 8)
pp. 1509-1519
ASCII Text
x 
 
K. Hirakawa, A. Chakrabarti, T. Zickler, "Color Constancy with Spatio-Spectral Statistics," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 8, pp. 1509-1519, Aug., 2012.
 
 
BibTex
x
 
@article{ 10.1109/TPAMI.2011.252,
author = {K. Hirakawa and A. Chakrabarti and T. Zickler},
title = {Color Constancy with Spatio-Spectral Statistics},
journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence},
volume = {34},
number = {8},
issn = {0162-8828},
year = {2012},
pages = {1509-1519},
doi = {http://doi.ieeecomputersociety.org/10.1109/TPAMI.2011.252},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - JOUR
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
TI - Color Constancy with Spatio-Spectral Statistics
IS - 8
SN - 0162-8828
SP1509
EP1519
EPD - 1509-1519
A1 - K. Hirakawa,
A1 - A. Chakrabarti,
A1 - T. Zickler,
PY - 2012
KW - maximum likelihood estimation
KW - band-pass filters
KW - image colour analysis
KW - statistical prior information
KW - spatio-spectral statistics
KW - maximum likelihood approach
KW - color constancy problem
KW - spectral distribution
KW - dominating scene illuminant
KW - white balanced images
KW - spatial band-pass filters
KW - color images
KW - maximum likelihood estimation
KW - Image color analysis
KW - Color
KW - Maximum likelihood estimation
KW - Covariance matrix
KW - Training
KW - Lighting
KW - illumination statistics.
KW - Color constancy
KW - statistical modeling
KW - spatial correlations
KW - maximum likelihood
VL - 34
JA - IEEE Transactions on Pattern Analysis and Machine Intelligence
ER -
 
K. Hirakawa, Intell. Signal Syst. Lab., Univ. of Dayton, Dayton, OH, USA
A. Chakrabarti, Sch. of Eng. & Appl. Sci., Harvard Univ., Cambridge, MA, USA
T. Zickler, Sch. of Eng. & Appl. Sci., Harvard Univ., Cambridge, MA, USA
We introduce an efficient maximum likelihood approach for one part of the color constancy problem: removing from an image the color cast caused by the spectral distribution of the dominating scene illuminant. We do this by developing a statistical model for the spatial distribution of colors in white balanced images (i.e., those that have no color cast), and then using this model to infer illumination parameters as those being most likely under our model. The key observation is that by applying spatial band-pass filters to color images one unveils color distributions that are unimodal, symmetric, and well represented by a simple parametric form. Once these distributions are fit to training data, they enable efficient maximum likelihood estimation of the dominant illuminant in a new image, and they can be combined with statistical prior information about the illuminant in a very natural manner. Experimental evaluation on standard data sets suggests that the approach performs well.

[1] G. Buchsbaum, "A Spatial Processor Model for Object Colour Perception," J. Franklin Inst., vol. 310, no. 1, pp. 1-26, 1980.
[2] E. Land, "The Retinex Theory of Color Vision," Scientific Am., vol. 237, no. 6, pp. 108-128, 1977.
[3] D. Forsyth, "A Novel Algorithm for Color Constancy," Int'l J. Computer Vision, vol. 5, no. 1, pp. 5-36, 1990.
[4] D. Brainard and W. Freeman, "Bayesian Color Constancy," J. Optical Soc. of Am. A, vol. 14, no. 7, pp. 1393-1411, 1993.
[5] C. Rosenberg, T. Minka, and A. Ladsariya, "Bayesian Color Constancy with Non-Gaussian Models," Proc. Advances in Neural Information Processing Systems, 2003.
[6] P. Gehler, C. Rother, A. Blake, T. Minka, and T. Sharp, "Bayesian Color Constancy Revisited," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[7] J. van de Weijer, T. Gevers, and A. Gijsenij, "Edge-Based Color Constancy," IEEE Trans. Image Processing, vol. 16, no. 9, pp. 2207-2214, Sept. 2007.
[8] A. Gijsenij, T. Gevers, and J. van de Weijer, "Generalized Gamut Mapping Using Image Derivative Structures for Color Constancy," Int'l J. Computer Vision, vol. 86, no. 2, pp. 127-139, 2010.
[9] G. West and M.H. Brill, "Necessary and Sufficient Conditions for Von Kries Chromatic Adaptation to Give Color Constancy," J. Math. Biology, vol. 15, no. 2, pp. 249-258, 1982.
[10] G. Finlayson, M. Drew, and B. Funt, "Diagonal Transforms Suffice for Color Constancy," Proc. IEEE Int'l Conf. Computer Vision, 1993.
[11] H. Chong, S. Gortler, and T. Zickler, "The Von Kries Hypothesis and a Basis for Color Constancy," Proc. IEEE Int'l Conf. Computer Vision, 2007.
[12] K. Barnard, "Improvements to Gamut Mapping Colour Constancy Algorithms," Proc. European Conf. Computer Vision, 2000.
[13] G. Finlayson, S. Hordley, and P. Hubel, "Color by Correlation: A Simple, Unifying Framework for Color Constancy," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 11, pp. 1209-1221, Nov. 2001.
[14] L. Shi, W. Xiong, and B. Funt, "Illumination Estimation via Thin-Plate Spline Interpolation," J. Optical Soc. of Am. A, vol. 28, no. 5, pp. 940-948, 2011.
[15] A. Hurlbert and T. Poggio, "Synthesizing a Color Algorithm from Examples," Science, vol. 239, no. 4839, pp. 482-485, 1988.
[16] V. Cardei, B. Funt, and K. Barnard, "Estimating the Scene Illumination Chromaticity Using a Neural Network," J. Optical Soc. of Am. A, vol. 19, no. 12, pp. 2374-2386, 2002.
[17] W. Xiong and B. Funt, "Estimating Illumination Chromaticity via Support Vector Regression," J. Imaging Science and Technology, vol. 50, p. 341, 2006.
[18] R. Gershon, A. Jepson, and J. Tsotsos, "From [r, g, b] to Surface Reflectance: Computing Color Constant Descriptors in Images," Perception, vol. 17, pp. 755-758, 1988.
[19] B. Singh, W. Freeman, and D. Brainard, "Exploiting Spatial and Spectral Image Regularities for Color Constancy," Proc. Workshop Statistical and Computational Theories of Vision, 2003.
[20] A. Chakrabarti, K. Hirakawa, and T. Zickler, "Color Constancy Beyond Bags of Pixels," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[21] I. Selesnick, "The Estimation of Laplace Random Vectors in Additive White Gaussian Noise," IEEE Trans. Signal Processing, vol. 56, no. 8, pp. 3482-3496, Aug. 2008.
[22] F. Sinz, S. Gerwinn, and M. Bethge, "Characterization of the p-Generalized Normal Distribution," J. Multivariate Analysis, vol. 100, no. 5, pp. 817-820, 2009.
[23] L. Shi and B. Funt, "Re-Processed Version of the Gehler Color Constancy Dataset of 568 Images," Accessed from http://www.cs.sfu.ca/~colourdata/, 2012.
[24] A. Gijsenij, T. Gevers, and J. van de Weijer, "Computational Color Constancy: Survey and Experiments," IEEE Trans. Image Processing, vol. 33, no. 9, pp. 2475-2489, Sept. 2011.
[25] K. Barnard, "A Comparison of Computational Color Constancy Algorithm-Part 1: Theory and Experiments with Synthetic Data," IEEE Trans. Image Processing, vol. 11, no. 9, pp. 972-984, Sept. 2002.
[26] R. Hogg and E. Tanis, Probability and Statistical Inference. Macmillan, 1977.
[27] S. Hordley and G. Finlayson, "Reevaluation of Color Constancy Algorithm Performance," J. Optical Soc. of Am. A, vol. 23, no. 5, pp. 1008-1020, 2006.
[28] F. Ciurea and B. Funt, "A Large Image Database for Color Constancy Research," Proc. IS&T/SID Color Imaging Conf., 2003.
[29] K. Barnard, L. Martin, A. Coath, and B. Funt, "A Comparison of Computational Color Constancy Algorithms. II. Experiments with Image Data," IEEE Trans. Image Processing, vol. 11, no. 9, pp. 985-996, Sept. 2002.
[30] A. Chakrabarti, D. Scharstein, and T. Zickler, "An Empirical Camera Model for Internet Color Vision," Proc. British Machine Vision Conf., 2009.
[31] K. Saenko, B. Kulis, M. Fritz, and T. Darrell, "Adapting Visual Category Models to New Domains," Proc. European Conf. Computer Vision, 2010.
[32] K. Hirakawa and T. Parks, "Chromatic Adaptation and White-Balance Problem," Proc. IEEE Conf. Image Processing, 2005.
[33] A. Werner, "The Spatial Tuning of Chromatic Adaptation," Vision Research, vol. 43, no. 15, pp. 1611-1623, 2003.
[34] M. Webster, "Human Colour Perception and Its Adaptation," Network: Computation in Neural Systems, vol. 7, no. 4, pp. 587-634, 1996.
[35] T. Hansen, M. Olkkonen, S. Walter, and K. Gegenfurtner, "Memory Modulates Color Appearance," Nature Neuroscience, vol. 9, no. 11, pp. 1367-1368, 2006.
[36] M. Olkkonen, T. Hansen, and K. Gegenfurtner, "Color Appearance of Familiar Objects: Effects of Object Shape, Texture, and Illumination Changes," J. Vision, vol. 8, no. 5, p. 13, 2008.

Index Terms:
maximum likelihood estimation,band-pass filters,image colour analysis,statistical prior information,spatio-spectral statistics,maximum likelihood approach,color constancy problem,spectral distribution,dominating scene illuminant,white balanced images,spatial band-pass filters,color images,maximum likelihood estimation,Image color analysis,Color,Maximum likelihood estimation,Covariance matrix,Training,Lighting,illumination statistics.,Color constancy,statistical modeling,spatial correlations,maximum likelihood
Citation:
K. Hirakawa, A. Chakrabarti, T. Zickler, "Color Constancy with Spatio-Spectral Statistics," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 8, pp. 1509-1519, Aug. 2012, doi:10.1109/TPAMI.2011.252
Usage of this product signifies your acceptance of the Terms of Use.