Color Constancy based on Image Similarity via Bilayer Sparse Coding
This addresses the problem of accurate illumination estimation for computer vision applications, but it is incremental as it builds on prior work by combining content and color information more directly.
The paper tackled illumination estimation in computational color constancy by proposing a bilayer sparse coding model that integrates low-level color distribution and high-level scene content, achieving superior performance over existing methods on two real-world image sets.
Computational color constancy is a very important topic in computer vision and has attracted many researchers' attention. Recently, lots of research has shown the effects of high level visual content information for illumination estimation. However, all of these existing methods are essentially combinational strategies in which image's content analysis is only used to guide the combination or selection from a variety of individual illumination estimation methods. In this paper, we propose a novel bilayer sparse coding model for illumination estimation that considers image similarity in terms of both low level color distribution and high level image scene content simultaneously. For the purpose, the image's scene content information is integrated with its color distribution to obtain optimal illumination estimation model. The experimental results on two real-world image sets show that our algorithm is superior to other prevailing illumination estimation methods, even better than combinational methods.