Abstract
This paper introduces a novel challenge to “scene-referred” pleasant color reproduction. Principal component of objective color in reference image is transferred to that of source image by PCA matching, so that color atmosphere is transferred from one scene to another without any color targets or test chart. Image segmentation is a first step to vision system and used as a pre-processing for many image processing applications. In the previous papers, we reported an object-to-object color transformation between images with color similarity based on unsupervised image segmentation by color clustering. This paper proposes an advanced image segmentation method by [k-means+Bayesian] classifier and demonstrates “scene-to-scene color interchange” between different images with color dissimilarity.
