Combining Strategies for Automatic White Estimation in Real Images

Abstract

In this paper we consider combining strategies of several white balance algorithms available in the literature to improve the illuminant chromaticity estimation and correction for digital images. We have tested and compared the original algorithms and the combining strategies on three databases of carefully controlled real data, composed respectively of multispectral CFA and RGB images. The experimental results, evaluated using the Wilcoxon Sign Test, are reported and commented.