Robust Estimation of Surface Color from Single Image Using Illumination Variance

Color appearance of an object varies due to the color of the illumination. To arrive at color constancy, we have developed a physics-based method of estimating surface colors and removing the illumination colors by utilizing illumination variance. In this paper, we focus on the use of this method to deal with outdoor scenes, since very few physics-based methods have successfully handled outdoor color constancy. Our method is based on shadowed and non-shadowed regions. Based on their difference of illumination, we estimate the illumination colors and then remove them. To reliably estimate the illumination colors in outdoor scenes, we include the analysis of noise, since the presence of noise is inevitable in natural images. As a result, compared to existing methods, the proposed method is more effective and robust to handle outdoor scenes. In addition, the proposed method requires only a single input image, making it useful for many applications of computer vision. Our implementation on outdoor objects shows significant increases in accuracy and robustness.