Judging Aesthetic Quality in Paintings Based on Artistic Inspired Color Features

Abstract

In this work, using a new set of color features in the field of computer vision and image processing which are inspired by the work of artists, we try to classify different subjective properties of paintings, including aesthetic quality, beauty, and liking of color. We then investigate if observers have individual tastes and opinions when evaluating different properties of artworks. The extracted features are used in a 5-fold CV SVM to classify scores provided by individual observers. This work in fact, confirms that the properties which could be related to aesthetic issues in paintings are "in the eye of the beholder". In other words, using the scores provided by the individual observers, we are not only able to reach a higher classification rate but also can find which properties are important for an observer when evaluating an image. Finally, we compare our proposed color features to a set of state-of-the-art color features used in the field of computer vision.