Color Constancy by Local Averaging

As the color of an object partly depends on the color of the illumination, computer vision systems that rely on color features are likely to benefit from a property that most humans have naturally: color constancy. Color constancy is the ability to recognize colors of objects, invariant to the color of the light source. In this paper, an new algorithm is proposed based on local averaging, which is tested on a publicly available data set. The proposed method is shown to be at least competitive to current state-of-the-art methods, however, at lower computational costs.