Color Constancy Via Convex Kernel Optimization

This paper introduces a novel convex kernel based method for color constancy computation with explicit illuminant parameter estimation. A simple linear render model is adopted and the illuminants in a new scene that contains some of the color surfaces seen in the training image are sequentially estimated in a global optimization framework. The proposed method is fully data-driven and initialization invariant. Nonlinear color constancy can also be approximately solved in this kernel optimization framework with piecewise linear assumption. Extensive experiments on real-scene images validate the practical performance of our method.

• Type: Conference
• Year: 2007
• Where: ACCV
• Authors: Xiaotong Yuan, Stan Z. Li, Ran He
• Keywords: ACCV 2007, Color Constancy, Color Constancy Computation, Computer Vision, Optimization Framework