This Article 
 Bibliographic References 
 Add to: 
Learning Outdoor Color Classification
November 2006 (vol. 28 no. 11)
pp. 1713-1723
We present an algorithm for color classification with explicit illuminant estimation and compensation. A Gaussian classifier is trained with color samples from just one training image. Then, using a simple diagonal illumination model, the illuminants in a new scene that contains some of the surface classes seen in the training image are estimated in a maximum likelihood framework using the Expectation Maximization algorithm. We also show how to impose priors on the illuminants, effectively computing a maximum a posteriori estimation. Experimental results are provided to demonstrate the performance of our classification algorithm in the case of outdoor images.

[1] K. Barnard, L. Martin, and B. Funt, “Colour by Correlation in a Three Dimensional Colour Space,” Proc. Sixth European Conf. Computer Visualiztion (ECCV '00), pp. 375-389, 2000.
[2] K. Barnard, L. Martin, B. Funt, and A. Coath, “A Data Set for Colour Research,” Color Research and Application, vol. 27, no. 3, pp.147-151, 2002.
[3] K. Barnard, G. Finlayson, and B. Funt, “Color Constancy for Scenes with Varying Illumination,” Computer Visualization and Image Understanding, vol. 65, no. 2, pp. 311-321, Feb. 1997.
[4] J. Besag, “On the Statistical Analysis of Dirty Pictures,” J. Royal Statistical Soc. B., vol. 48, pp. 259-302, 1986.
[5] D.H. Brainard and W.T. Freeman, “Bayesian Color Constancy,” J.Optical Soc. Am., A, vol. 14, pp. 1393-1411, July 1997.
[6] S. Buluswar and S.D. Draper, “Color Models for Outdoor Machine Vision,” Computer Visualiztion and Image Understanding, vol. 85, no. 2, pp. 71-99, 2002.
[7] G.D. Finlayson, M. Drew, and B. Funt, “Color Constancy: Generalized Diagonal Transform Suffices,” J. Optical Soc. Am., A, vol. 11, no. 11, pp. 3011-3019, Nov. 1994.
[8] G.D. Finlayson, S.D. Hordley, and P.M. 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.
[9] D.A. Forsyth, J. Haddon, and S. Ioffe, “The Joy of Sampling,” Int'l J. Computer Visualization, vol. 41, pp. 109-134, 2001.
[10] D. Forsyth, “A Novel Approach for Color Constancy,” Int'l J. Computer Visualization, vol. 5, pp. 5-36, 1990.
[11] G. Healey, “Segmenting Images Using Normalized Colors,” IEEE Trans. Systems, Man, and Cybernetics, vol. 22, no. 1, pp. 64-73, Jan. 1992.
[12] M.D. Grossberg and S.K. Nayar, “What Is the Space of Camera Response Functions?” Proc. IEEE Computer Vision and Pattern Recognition, 2003.
[13] E.T. Jaynes, Probability Theory: The Logic of Science. Cambridge Univ. Press, 2003.
[14] C. Jiang and M.O. Ward, “Shadow Identification,” Proc. IEEE Computer Vision and Pattern Recognition, 1992.
[15] D. Judd, D. MacAdam, and G. Wyszecki, “Spectral Distribution of Typical Daylight as a Function of Correlated Color Temperature,” J. Optical Soc. Am., vol. 54, no. 8, pp. 1031-1040, 1964.
[16] R. Manduchi, A. Castano, A. Talukder, and L. Matthies, “Obstacle Detection and Terrain Classification for Autonomous Off-Road Navigation,” Autonomous Robots, vol. 18, pp. 81-102, 2005.
[17] R. Manduchi, “Learning Outdoor Color Classification from Just One Training Image,” Proc. European Conf. Computer Vision, 2004.
[18] J. Matas, R. Marik, and J. Kittler, “Illumination Invariant Colour Recognition,” Proc. Fifth British Machine Vision Conf., 1994.
[19] G.J. McLachlan and T. Krisnan, The EM Algorithm and Extensions. Wiley, 1997.
[20] W.H. Press, B.P. Flannery, S.A. Teukolsky, and W.T. Vetterling, Numerical Recipes: The Art of Scientific Computing. Cambridge Univ. Press, 1986.
[21] B.D. Ripley, Pattern Recognition and Neural Networks. Cambridge Univ. Press, 1996.
[22] G. Schaefer, “How Useful Are Colour Invariants for Image Retrieval?” Proc Second Int'l Conf. Computer Vision and Graphics, 2004.
[23] D.A. Slater and G. Healey, “What Is the Spectral Dimensionality of Illumination Functions in Outdoor Scenes?” Proc. IEEE Computer Vision and Pattern Recognition, pp. 105-110, 1998.
[24] W.K. Smith, A.K. Knapp, and W.A. Reiners, “Penumbral Effects on Sunlight Penetration in Plant Communities,” Ecology, vol. 70, no. 6, pp. 1603-1609, Dec. 1989.
[25] Y. Tsin, R.T. Collins, V. Ramesh, and T. Kanade, “Bayesian Color Constancy for Outdoor Object Recognition,” Proc. IEEE Computer Vision and Pattern Recognition, Dec. 2001.
[26] Y. Weiss and E.H. Adelson, “A Unified Mixture Framework for Motion Segmentation: Incorporating Spatial Coherence and Estimating the Number of Models,” Proc. IEEE Computer Vision and Pattern Recognition, pp. 321-326, 1996.
[27] G. Wyszecki and W.S. Styles, Color Science: Concepts and Methods, Quantitative Data and Formulae. Wiley, 1982.
[28] J. Zhang, J.W. Modestino, and D.A. Langan, “Maximum-Likelihood Parameter Estimation for Unsupervised Stochastic Model-Based Image Segmentation,” IEEE Trans. Image Processing, vol. 3, no. 4, pp. 404-420, July 1994.

Index Terms:
Color constancy, classification, expectation maximization.
Roberto Manduchi, "Learning Outdoor Color Classification," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 11, pp. 1713-1723, Nov. 2006, doi:10.1109/TPAMI.2006.231
Usage of this product signifies your acceptance of the Terms of Use.