Brian Funt, Kobus Barnard and Lindsay Martin, "Is colour constancy good enough?" 5th European Conference on Computer Vision, 1998, pages 445-459.
The copyright for the above paper has been transfered to Springer-Verlag. As part of the agreement , Springer-Verlag kindly allows authors to have the text of the papers on their personal web pages and thus the text versions of the paper will remain after publication. The paper will be published in the appropriate Lecture Notes in Computing Science (LNCS)
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.
Keywords: colour, colour constancy, object recognition, image indexing
Full text (gzipped postscript)