A comparison of computational color constancy Algorithms. II. Experiments with image data

By Kobus Barnard, Lindsay Martin, Adam Coath, Brian V. Funt. IEEE Transactions on Image Processing, 2002

414 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Illuminant estimation for color constancy: why spatial-domain methods work and the role of the color distribution. (2014, methodology): “Though a comparison of non-learning based methods with learning based methods is not completely fair, but for the sake of completeness we have compared our method with both non-learning based methods (GW [2], WP [19], SoG [20], GGW [11], BP [31], GE1 [21], GE2 [21]) as well as learning based methods”
Computational Color Constancy: Survey and Experiments (2011, positive): “has been shown that segmenting the image and computing the average color of all segments may improve the performance of the gray-world algorithm [51], [52].”
Introduction to Autonomous Mobile Robots (2004, background): “For more details on the fields of color constancy and luminosity constancy, consult [40].”
Edge-Based Color Constancy (2007, neutral): “Obtaining color constancy is of importance for many computer vision applications, such as image retrieval, image classification, color object recognition and object tracking [2], [3], [4].”
Enhancing the low quality images using Unsupervised Colour Correction Method (2010, methodology): “The maximum pixel values of each colour component R .n ax , G max and B m ax are calculated [15] : R max = max I R (i,j) (1) ;,} G max = max I G (i,j) (2) ;,} B max = max IB(i,j) (3) i, } In the first step, the prominent colour cast chann el is found using the above equations.”