Please use this identifier to cite or link to this item:
|Title:||Illuminant estimation for color constancy: Why spatial-domain methods work and the role of the color distribution|
|Source:||Cheng, D., Prasad, D.K., Brown, M.S. (2014-01-05). Illuminant estimation for color constancy: Why spatial-domain methods work and the role of the color distribution. Journal of the Optical Society of America A: Optics and Image Science, and Vision 31 (5) : 1049-1058. ScholarBank@NUS Repository. https://doi.org/10.1364/JOSAA.31.001049|
|Abstract:||Color constancy is a well-studied topic in color vision. Methods are generally categorized as (1) low-level statistical methods, (2) gamut-based methods, and (3) learning-based methods. In this work, we distinguish methods depending on whether they work directly from color values (i.e., color domain) or from values obtained from the image's spatial information (e.g., image gradients/frequencies). We show that spatial information does not provide any additional information that cannot be obtained directly from the color distribution and that the indirect aim of spatial-domain methods is to obtain large color differences for estimating the illumination direction. This finding allows us to develop a simple and efficient illumination estimation method that chooses bright and dark pixels using a projection distance in the color distribution and then applies principal component analysis to estimate the illumination direction. Our method gives state-of-the-art results on existing public color constancy datasets as well as on our newly collected dataset (NUS dataset) containing 1736 images from eight different highend consumer cameras. © 2014 Optical Society of America.|
|Source Title:||Journal of the Optical Society of America A: Optics and Image Science, and Vision|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Mar 8, 2018
WEB OF SCIENCETM
checked on Feb 12, 2018
checked on Mar 12, 2018
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.