Abstract
Artistic image understanding is an interdisciplinary research field of increasing importance for the computer vision and the art his- tory communities. For computer vision scientists, this problem offers challenges where new techniques can be developed; and for the art his- tory community new automatic art analysis tools can be developed. On the positive side, artistic images are generally constrained by compo- sitional rules and artistic themes. However, the low-level texture and color features exploited for photographic image analysis are not as ef- fective because of inconsistent color and texture patterns describing the visual classes in artistic images. In this work, we present a new database of monochromatic artistic images containing 988 images with a global semantic annotation, a local compositional annotation, and a pose an- notation of human sub jects and animal types. In total, 75 visual classes are annotated, from which 27 are related to the theme of the art im- age, and 48 are visual classes that can be localized in the image with bounding boxes. Out of these 48 classes, 40 have pose annotation, with 37 denoting human sub jects and 3 representing animal types. We also provide a complete evaluation of several algorithms recently proposed for image annotation and retrieval. We then present an algorithm achieving remarkable performance over the most successful algorithm hitherto pro- posed for this problem. Our main goal with this paper is to make this database, the evaluation process, and the benchmark results available for the computer vision community.