Computational Color Constancy

Computational color constancy aims to estimate the actual color in an acquired scene disregarding its illuminant. Several strategies have been proposed in the last few years. In general these require some information about the camera being used, or exploit the statistical properties of the expected illuminants and surface reflectances. From a computational perspective, once the illuminant has been estimated, the image colors can be corrected on the basis of this estimate. The correction generates a new image of the scene as if it was taken under a known canonical illuminant. In this article we briefly review state of the art methods and illustrate recent research on classification-based color constancy, where automatically extracted image features are used to drive the selection and application of the best algorithm for each image. Finally, we highlight research trends in this field.