This Article 
 Bibliographic References 
 Add to: 
Color Constant Color Indexing
May 1995 (vol. 17 no. 5)
pp. 522-529

Abstract—Objects can be recognized on the basis of their color alone by color indexing, a technique developed by Swain and Ballard [15] which involves matching color-space histograms. Color indexing fails, however, when the incident illumination varies either spatially or spectrally. Although this limitation might be overcome by preprocessing with a color constancy algorithm, we instead propose histogramming color ratios. Since the ratios of color RGB triples from neighboring locations are relatively insensitive to changes in the incident illumination, this circumvents the need for color constancy preprocessing. Results of tests with the new color-constant-color-indexing algorithm on synthetic and real images show that it works very well even when the illumination varies spatially in its intensity and color.

[1] R.S. Berns and K.H. Petersen,“Empirical modelling of systematicspectrophotometric errors,” Color Res. Appl., vol. 4, p. 243, 1988.
[2] G. Buchsbaum and A. Gottschalk,“Trichromacy, opponent colours coding andoptimum colour information transmission in the retina,” Proc. R. Society London B., vol. 220, pp. 89-113, 1983.
[3] R. Duda, P. Hart, and D. Stork, Pattern Classification. New York: John Wiley&Sons, 2001.
[4] G.D. Finlayson,Colour Object Recognition. Simon Fraser Univ. School of Computing Science, 1992.
[5] G.D. Finlayson,M.S. Drew,, and B.V. Funt,“Spectral sharpening: Sensor transformations for improvedcolor constancy,” J. Opt. Soc. Am. A, vol. 11, pp. 1553-1563, 1994.
[6] D.A. Forsyth, “A Novel Algorithm for Color Constancy,” Int'l J. Computer Vision, vol. 5, no. 1, pp. 5-36, 1990.
[7] S. Chakradhar and S. Dey,"Retiming and resynthesis for optimum partial scan," Proc. 31st ACM/IEEE Design Automation Conf., 1994.
[8] B.V. Funt and J. Ho,“Color from black and white,” Proc Second Int’l. Conf. Computer Vision,Tarpon Springs, pp. 2-8. IEEE Computer Society, Dec. 1988, and Int’l. J. Computer Vision, vol. 3, pp. 109-117, 1989.
[9] B.K.P. Horn,“Determining lightness from an image,” Computer Vision, Graphics, and Image Processing, vol. 3, pp. 277-299, 1974.
[10] E.L. Krinov,“Spectral reflectance properties of natural formations,” Technical Translation TT-439, Nat’l. Research Council of Canada, 1947.
[11] E.H. Land and J.J. McCann,“Lightness and retinex theory,” J. Opt. Soc. Am., vol. 61, pp. 1-11, 1971.
[12] D. Marr,Vision. Freeman, 1982.
[13] C.S. McCamy,H. Marcus,, and J.G. Davidson,“A color-rendition chart,” J. App. Photog. Eng., pp. 95-99, 1976.
[14] C.L. Novak and S.A. Shafer,“Supervised color constancy using a color chart,” Technical Report CMU-CS-90-140. Carnegie Mellon Univ. School of Computer Science, 1990.
[15] M.J. Swain and B.H. Ballard, “Color Indexing,” Int'l J. Computer Vision, vol. 7, no. 1, pp. 11-32, 1991.
[16] G. West and M.H. Brill,“Necessary and sufficient conditions for von Krieschromatic adaption to give colour constancy,” J. Math. Biol., vol. 15, pp. 249-258, 1982.
[17] G. Wyszecki and W.S. Stiles,Color Science: Concepts and Methods,Quantitative Data and Formulas.New York: John Wiley&Sons, 2nd ed., 1982.

Index Terms:
Color indexing, color constancy, retinex, object recognition.
Brian V. Funt, Graham D. Finlayson, "Color Constant Color Indexing," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 5, pp. 522-529, May 1995, doi:10.1109/34.391390
Usage of this product signifies your acceptance of the Terms of Use.