Color harmony for image indexing

Abstract

A predictive model for estimating the perceived harmony of ordinary multi-colored images is proposed and evaluated. The model is based on earlier research concerning two-color harmonies. Color regions of images are extracted using mean shift segmentation. Global and local harmony scores are derived for two-color combinations included in different subsets of all segmented regions. Statistical measurements of the obtained harmony scores are used for predicting the perceived overall harmony. The model is validated in a psychophysical experiment, where human observers are judging images on a harmony scale. The findings show that humans do perceive harmony in multi-colored images in similar ways, and that the proposed model results in useful predictions of harmony. The model can be applied in automatic labeling or classification of images.