| It is generally accepted that the key operation underlying color constancy is the estimation of the scene illuminant(s), but as illuminant estimation has proven to be a very difficult computational problem, color constancy algorithms continue to fall far short of human performance. Many existing color constancy algorithms attempt to determine the illuminant based solely on the information contained within the scene, ignoring probability. We have developed a Bayesian-inspired approach to color constancy involving the following five heuristics: (1) The most probable illuminant in a scene lies along the line (in color space) that connects the scene average M and the a priori most probable illuminant L. (2) The scene average M is computed using a single chromaticity estimate per object surface (i.e. "one surface one vote"), rather than a single estimate per image pixel. (3) Object surface contributions to M, the scene average, are weighted by surface brightness, reflecting the well known brightest-is-whitest principle. (4) Scenes with high surface counts which contain relatively more illuminant information pull illuminant estimates radially outward towards M. (5) Scenes with large color gamuts pull the illuminant estimate radially inward towards an illumination with equal power in each wavelength.; To test our algorithm, we (1) automatically generated a large number of color image composites with varying backgrounds constructed from the images of 100 real objects photographed under 5 different illuminants, and (2) ran a color histogramming recognition benchmark to test our approach against several other published color constancy algorithms. In our most recent tests, our algorithm achieved 65.3% recognition rates compared to 44.8% for uncorrected images, and outperformed all other algorithms tested. |
