Color correction algorithm for color constancy finite dimensional linear model under complex illumination

摘要

In order to improve the performance of color correction classifier for color constancy finite dimensional linear model under complex illumination, an image color correction hierarchical association rule classifier based on axiomatic fuzzy sets under complex illumination with finite dimensional linear model of color constancy is proposed. Firstly, in order to improve the accuracy of the algorithm, based on the feature extraction of image data sets, the AFS attribute representation of image set fuzzy concept is constructed by using axiomatic theory (AFS) to improve the recognition degree of image set attributes. Secondly, in order to improve the computational efficiency of the algorithm, the hierarchical structure association rules are used to construct a color correction classifier for color constancy finite dimensional linear model under complex illumination. The ontology information between concepts is used to improve the ability of parallel classification. Finally, the experimental results show that the proposed algorithm has high computational accuracy and efficiency. (C) 2018 Elsevier B.V. All rights reserved.