Abstract

The aim of computational color constancy is to estimate the actual surface color in an acquired scene disregarding its illuminant. Many solutions try to first estimate the illuminant and then correct the image with the illuminant estimate. Based on the linear image formation model, we propose in this work a new strategy to estimate the illuminant. Inspired by the feedback modulation from horizontal cells to the cones in the retina, we first normalize each local patch with its local maximum to obtain the so-called locally normalized reflectance estimate (LNRE). Then, we experimentally found that the ratio of the global summation of true surface reflectance to the global summation of LNRE in a scene is approximately achromatic for both indoor and outdoor scenes. Based on this substantial observation, we estimate the illuminant by comput- ing the ratio of the global summation of the intensities to the global summation of the locally normalized intensities of the color-biased im- age. The proposed model has only one free parameter and requires no explicit training with learning-based approach. Experimental results on four commonly used datasets show that our model can produce compet- itive or even better results compared to the state-of-the-art approaches with low computational cost.