This project has been built using the Zooniverse Project Builder but is not yet an official Zooniverse project. Queries and issues relating to this project directed at the Zooniverse Team may not receive any response.
Building a classification model for cultural heritage imagery with a subset of the AAT Getty vocabulary
Learn moreYou can do real research by clicking to get started here!
Chat with the research team and other volunteers!
Every click counts! Join Europeana Image classification pilot's community to complete this project and help researchers produce important results. Click "View more stats" to see even more stats.
Connect with the research team on Talk to learn more about this project!
Enrichment is used at Europeana for generating additional metadata about Cultural Heritage Objects. This metadata is useful for indexing our data and building search and recommendation functionalities.
This project focuses on enrichment based on content, in particular using computer vision techniques for generating labels from the content of images. In particular, we frame our problem as image classification, where each image can have one or more labels.
The Europeana Entity Collection is a set of contextual resources (concepts, persons, places…) that Europeana intends to use for describing and browsing CHOs, these concepts being mapped to standardized vocabularies such as DBpedia and AAT Getty. The Europeana Entity Collection is intended as a dynamic set, with concepts from different vocabularies being pulled in depending on identified needs.
We focused on a subset of 20 basic types for images from the CHO Type vocabulary : building, archaeological_site, ceramics, clothing, costume_accessories, drawing, map, furniture, inscription, jewellery, painting, photograph, postcard, sculpture, specimen, tapestry, toy, weaponry, woodwork. These concepts (with their URIs in the Entity Collections and Getty AAT) are available at the github repository.