Color Constancy Via Convex Kernel Optimization
- Cite this paper as:
- Yuan X., Li S.Z., He R. (2007) Color Constancy Via Convex Kernel Optimization. In: Yagi Y., Kang S.B., Kweon I.S., Zha H. (eds) Computer Vision – ACCV 2007. ACCV 2007. Lecture Notes in Computer Science, vol 4843. Springer, Berlin, Heidelberg
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.
Unable to display preview. Download preview PDF.