Visual Artificial Intelligence for the Digital Humanities

Over the past ten years, images have started to gradually appear on the radar of digital humanists. Recent developments in digital art history in particular have shown that the importance of images for DH research goes beyond ensuring their accessibility through databases and interfaces. In fact, images are where digital humanities and "artificial intelligence" meet. Furthermore, beyond practical problems, the automated classification of images on the one hand, and the automated production of images on the other raise fundamental questions at the interface of computer science and the humanities: how is reality represented in machine learning systems, and how and why do human-held preconceptions, biases, and misjudgements enter such systems?

The workshop will address both the theoretical and practical challenges of visual artificial intelligence applications in DH. Starting from scratch (what is a digital image, what is "computer vision"?) and using both existing tools (imgs.ai) and custom code, we will gradually explore useful image processing strategies, including but not limited to: scraping (building large-scale image datasets from Web sources), batch processing ("cleaning" image datasets and adapting them to the affordances of a machine), feature extraction (extracting semantic information from image datasets), clustering (visually sorting and reviewing image datasets), and classification (analyzing image datasets using pre-trained machine learning systems). Participants are encouraged to apply these strategies to provided practice datasets and eventually work on their on image corpora or image corpora ideas from all areas of visual culture, including but not limited to cultural heritage data, historical image corpora, museum and archival collections, artworks, etc.

The first week will introduce participants to the field through readings, discussions, and the exploration of existing approaches to visual artificial intelligence in the digital humanities (e.g. imgs.ai). The second week will be dedicated to hands-on experimentation with image datasets.

The workshop requires a willingness to pick up basic concepts of the Python programming language. Previous computer programming experience in any language is beneficial but not required.