Visual saliency analysis in paintings

Visual saliency is the property of a scene to draw the attention of different people to the same objects within it. Its investigation and development enabled many practical applications. In this paper we aim to use it for the study of visual art. As a first contribution we introduce an extensive database annotated in terms of visual saliency by considering data acquired from many users. Secondly, based on visual saliency regions, we identify some core differences between various artistic movements represented within. Thirdly, we evaluate comparatively several state-of-the-art saliency prediction algorithms, so to identify the most performing in the context of digitized paintings.