Is machine colour constancy good enough?
This paper presents a negative result: current machine colour constancy algorithms are not good enough for colour-based object recognition. This result has surprised us since we have previously used the better of these algorithms successfully to correct the colour balance of images for display. Colour balancing has been the typical application of colour constancy, rarely has it been actually put to use in a computer vision system, so our goal was to show how well the various methods would do on an obvious machine colour vision task, namely, object recognition. Although all the colour constancy methods we tested proved insufficient for the task, we consider this an important finding in itself. In addition we present results showing the correlation between colour constancy performance and object recognition performance, and as one might expect, the better the colour constancy the better the recognition rate.
KeywordsConvex Hull Colour Constancy Colour Correction Colour Balance Clipping Level
Unable to display preview. Download preview PDF.
- 1.Funt, B.V. and Cardei, V., Barnard, K., Learning Color Constancy, IS&T Fourth Color Imaging Conference, Scottsdale, Nov. 1996.Google Scholar
- 3.Funt, B.V., and Finlayson G.D., Color Constant Color Indexing, IEEE Trans. Patt. Anal. and Mach. Intell, 17(5), May 1995.Google Scholar
- 4.Healey, G. and Slater, D. “Global Color Constancy: recognition of objects by use of illumination invariant properties of color distributions,” J. Opt. Soc. Am. A, 11(11):3003–3010, Nov. 1994.Google Scholar
- 5.Barnard, K., Finlayson, G., Funt, B., Colour Constancy for Scenes with Spectrally Varying Illumination, ECCV'96 Fourth European Conference on Computer Vision, Vol. II, pages 3–15, April 1996.Google Scholar
- 7.Finlayson, G., Funt, B. and Barnard, J., Colour Constancy Under a Varying Illumination, Proc. Fifth Intl. Conf. on Comp. Vis., Jun 1995.Google Scholar
- 9.Finlayson, G., Drew, M., and Funt, B., Color Constancy: Generalized Diagonal Transforms Suffice, J. Opt. Soc. Am. A, 11(11):3011–3020, 1994Google Scholar
- 10.Finlayson, G. Color in Perspective, PAMI Oct. 1996. Vol. 18 number 10, p 1034–1038Google Scholar
- 13.Kobus Barnard, “Computational colour constancy: taking theory into practice,” MSc thesis, Simon Fraser University, School of Computing (1995).Google Scholar
- 14.Hertz, J., Krogh, A., and Palmer, R.G. Introduction to the Theory of Neural Computation, Addison-Wesley Publishing Company, 1991.Google Scholar
- 15.Rumelhart, D.E., Hinton, G.E., and. Williams, R.J, Learning Internal Representations by Error Propagation in D.E. Rumelhart & J.L. McClelland (Eds.), Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Vol.1: Foundations. MITGoogle Scholar
- 16.Brainard, D., Brunt, W., and Speigle, J., Color Constancy in the nearly natural image. I. Asymmetric matches, Journal of the Optical Society of America A, V 14, pp.2091–2110, Sept. 1997.Google Scholar