Color Constancy using Natural Image Statistics

Although many color constancy methods exist, they are all based on specific assumptions such as the set of possible light sources, or the spatial and spectral characteristics of images. As a consequence, no algorithm can be considered as universal. However, with the large variety of available methods, the question is how to select the method that induces equivalent classes for different image characteristics. Furthermore, the subsequent question is how to combine the different algorithms in a proper way. To achieve selection and combining of color constancy algorithms, in this paper, natural image statistics are used to identify the most important characteristics of color images. Then, based on these image characteristics, the proper color constancy algorithm (or best combination of algorithms) is selected for a specific image. To capture the image characteristics, the Weibull parameterization (e.g. texture and contrast) is used. Experiments show that, on a large data set of 11,000 images, our approach outperforms current state-of-the-art single algorithms, as well as simple alternatives for combining several algorithms.

[1]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[2]  Arnold W. M. Smeulders,et al.  PicToSeek: combining color and shape invariant features for image retrieval , 2000, IEEE Trans. Image Process..

[3]  James C. Bezdek,et al.  Presupervised and post-supervised prototype classifier design , 1999, IEEE Trans. Neural Networks.

[4]  David A. Forsyth,et al.  A novel algorithm for color constancy , 1990, International Journal of Computer Vision.

[5]  Steven D. Hordley,et al.  Scene illuminant estimation: Past, present, and future , 2006 .

[6]  Arnold W. M. Smeulders,et al.  c ○ 2005 Springer Science + Business Media, Inc. Manufactured in The Netherlands. A Six-Stimulus Theory for Stochastic Texture , 2002 .

[7]  Ingeborg Tastl,et al.  Gamut Constrained Illuminant Estimation , 2006, International Journal of Computer Vision.

[8]  Graham D. Finlayson,et al.  Shades of Gray and Colour Constancy , 2004, CIC.

[9]  Brian V. Funt,et al.  Committee-Based Color Constancy , 1999, CIC.

[10]  E. Land.  The retinex theory of color vision. , 1977, Scientific American.

[11]  Graham D. Finlayson,et al.  Color by Correlation: A Simple, Unifying Framework for Color Constancy , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Antonio Torralba,et al.  Contextual Priming for Object Detection , 2003, International Journal of Computer Vision.

[13]  G. Buchsbaum.  A spatial processor model for object colour perception , 1980 .

[14]  Antonio Torralba,et al.  Statistics of natural image categories , 2003, Network.

[15]  Joost van de Weijer,et al.  Color constancy based on the Grey-edge hypothesis , 2005, IEEE International Conference on Image Processing 2005.

[16]  D H Brainard,et al.  Bayesian color constancy. , 1997, Journal of the Optical Society of America. A, Optics, image science, and vision.

[17]  Brian V. Funt,et al.  A Large Image Database for Color Constancy Research , 2003, CIC.

[18]  Graham D. Finlayson,et al.  Re-evaluating colour constancy algorithms , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[19]  Marc Ebner,et al.  Evolving color constancy , 2006, Pattern Recognit. Lett..

[20]  Cor J. Veenman,et al.  Robust Scene Categorization by Learning Image Statistics in Context , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[21]  Gerald Schaefer,et al.  A combined physical and statistical approach to colour constancy , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).