ICC++: Explainable Image Retrieval for Art Historical Corpora using Image Composition Canvas

TL;DR

This paper introduces ICC++, an explainable image retrieval method for art historical images based on compositional elements, outperforming existing techniques and advancing explainable AI in digital humanities.

Contribution

ICC++ advances image retrieval in art history by incorporating compositional features and improving over previous methods with quantitative and qualitative validation.

Findings

ICC++ outperforms traditional and state-of-the-art methods.

Combines deep features with compositional analysis for better retrieval.

Supports explainable machine learning in digital humanities.

Abstract

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.