ICC++: Explainable Image Retrieval for Art Historical Corpora using Image Composition Canvas
This addresses the time-consuming challenge of objectively linking thousands of digitized artworks for art historians and digital humanities researchers, though it appears incremental as an improvement over the existing ICC method.
The authors tackled the problem of manually linking digitized artworks with similar compositional elements by developing ICC++, which outperformed traditional and state-of-the-art methods in image retrieval for art historical corpora, including beating the best deep learning-based approach when combined with deep features.
Image compositions are helpful in the study of image structures and assist in discovering the semantics of the underlying scene portrayed across art forms and styles. With the digitization of artworks in recent years, thousands of images of a particular scene or narrative could potentially be linked together. However, manually linking this data with consistent objectiveness can be a highly challenging and time-consuming task. In this work, we present a novel approach called Image Composition Canvas (ICC++) to compare and retrieve images having similar compositional elements. ICC++ is an improvement over ICC specializing in generating low and high-level features (compositional elements) motivated by Max Imdahl's work. To this end, we present a rigorous quantitative and qualitative comparison of our approach with traditional and state-of-the-art (SOTA) methods showing that our proposed method outperforms all of them. In combination with deep features, our method outperforms the best deep learning-based method, opening the research direction for explainable machine learning for digital humanities. We will release the code and the data post-publication.