The main aim of the Saint George on a Bike project (SGoaB) was to enhance the quality and quantity of open information connected to European cultural heritage images by leveraging AI technologies to create rich metadata descriptions and contextualisation of objects, images and symbols. In particular, the project focused on paintings of the 12th - 18th centuries (especially iconography).
The target audiences for this project that could make use of the metadata generated by SGoaB include professionals working at cultural heritage institutions, research institutions, cultural tourism and cultural and creative industries.
To achieve its goals, SGoaB translated information about culture, symbols, and centuries of evolving artistic traditions into a format that could be understood by machine learning and AI; and advanced traditional machine learning techniques that focus on recognising objects in images. The metadata generated by these tools which were based on a mix of deep learning, language models, semantic information, and cultural heritage-specific heuristics allowed users a better understanding of artwork content and their historical context.
The enriched metadata produced by the tools created during the project helped enhance the discoverability and accessibility of the cultural collections available through platforms such as Europeana.eu and European (open) data portals.
This project was a Public Open Data Generic Services project, and it was co-financed by the Connecting Europe Facility of the European Union.
Visit the project website and learn more through the video below.
