ARIES: Enabling Visual Exploration and Organization of Art Image Collections

Abstract

Art historians have traditionally used physical light boxes to prepare exhibits or curate collections. On a light box, they can place slides or printed images, move the images around at will, group them as desired, and visual-ly compare them. The transition to digital images has rendered this workflow obsolete. Now, art historians lack well-designed, unified interactive software tools that effectively support the operations they perform with physi-cal light boxes. To address this problem, we designed ARIES (ARt Image Exploration Space), an interactive image manipulation system that enables the exploration and organization of fine digital art. The system allows images to be compared in multiple ways, offering dynamic overlays analogous to a physical light box, and sup-porting advanced image comparisons and feature-matching functions, available through computational image processing. We demonstrate the effectiveness of our system to support art historians tasks through real use cases.

Computer Vision Applications for Art History: Reflections and paradigms for future research

“…Another direction pursued is to provide art historians with tools that facilitate the search and retrieval of artwork images from large databases (Seguin et al 2016;Crissaff et al 2018). Furthermore, many of the previously mentioned applications for recognising higher-level features, such as objects and people, are utilised to annotate artworks with additional metadata, other than the commonly used (e.g., artist, style, period), in image retrieval systems.…”

Digital art history in 2021

“…Tools for digitally locating and analyzing images in ways that are both meaningful to and usable by art historians lag far behind the text‐based tools available to linguists, historians, and specialists in literature. ARIES, or ARt Image Exploration Space, is one of few such tools designed specifically for art historians (Crissaff et al., 2018; Deutch, 2021). ARIES effectively reproduces fundamental affordances of a lightbox, prioritizing close comparison of pairs of images, but takes advantage of features like relative scaling and sophisticated image overlays that are only possible in a digital medium.…”

A language to analyze, describe, and explore collections of visual art

“…There are personalized digital archives that go beyond the primary purpose of making individual or groups of images from the field of visual art available [4]. Recent browser developments have aimed to help people find images in large collections or to examine and compare images and image groups [5][6][7]. In contrast, the proposed LadeCA language, which allows users to analyze, describe, and explore collections of visual art, focuses less on individual images and instead focuses on image sets and their properties to make large image sets accessible as a whole.…”