Colour constancy is traditionally interpreted as the stable appearance of the colour of a surface despite changes in the spectral composition of the illumination. When colour constancy has been assessed quantitatively, however, by observers making matches between surfaces illuminated by different sources, its completeness has been found to be poor. An alternative operational approach to colour constancy may be taken which concentrates instead on detecting the underlying chromatic relationship between the parts of a surface under changes in the illuminant. Experimentally the observer's task was to determine whether a change in the appearance of a surface was due to a change in its reflecting properties or to a change in the incident light. Observers viewed computer simulations of a row of three Mondrian patterns of Munsell chips. The centre pattern was a reference pattern illuminated by a simulated, spatially uniform daylight; one of the outer patterns was identical but illuminated by a different daylight; and the other outer pattern was equivalent but not obtainable from the centre pattern by such a change in illuminant. Different patterns and different shifts in daylight were generated in each experimental trial. The task of the observer was to identify which of the outer patterns was the result of an illuminant change. Observers made reliable discriminations of the patterns with displays of durations from several seconds to less than 200 ms, and, for one observer, with displays of 1 ms. By these measures, human observers appear capable of colour constancy that is extremely rapid, and probably preattentive in origin.
