Docent Lab is a pioneering research initiative, combining the expertise of Docent's scientific team with the collaborative efforts of artists, institutions, and private collections, unlocking the transformative potential of art for everyone.
Through our research program, Docent Lab merges the power of machine learning and data analytics to change how art is discovered and experienced. We actively foster the exchange of ideas, merging scientific advancements with artistic collaboration worldwide. By harnessing the synergy between technology and creativity, we help unleash the universal power of art.
In 2022, Turner prize winning artist, Oscar Murillo, and Docent Lab joined forces to explore the extensive and intricate archive of the Frequencies canvases series. The collaboration was showcased during the Venice Biennale at the Scuola Grande della Misericordia.
Docent Lab is collaborating with Oscar Murillo on the digitalisation and development of Frequencies, a long-term international project initiated in 2013. Frequencies involved sending blank canvases to classrooms in over 400 schools worldwide, with students aged 10-16 invited to freely draw, write and mark the canvases alongside their daily activities over six months. Together, they harness Docent's pioneering AI technology and methodology to categorise and analyse the monumental collection of over 40,000 canvases. Docent’s Computer Vision and Natural Language Processing technologies automatically identify the content of each canvas’ drawings and writings to understand their meanings and emotions and generate new works based on these insights.
Recommendation systems have been widely used in various domains such as music, films, e-shopping etc. After mostly avoiding digitisation, the art world has recently reached a technological turning point due to the pandemic, making online sales grow significantly as well as providing quantitative online data about artists and artworks.
In this work, we present a content-based recommendation system on contemporary art relying on images of artworks and contextual metadata of artists. We gathered and annotated artworks with advanced and art-specific information to create a completely unique database that was used to train our models. With this information, we built a proximity graph between artworks. Similarly, we used NLP techniques to characterize the practices of the artists and we extracted information from exhibitions and other event history to create a proximity graph between artists.
The power of graph analysis enables us to provide an artwork recommendation system based on a combination of visual and contextual information from artworks and artists.