Can Computers Map Artistic Influence?

Norman Rockwell, Shuffleton's Barbershop (1950) Image via: Wikiart

Norman Rockwell, Shuffleton’s Barbershop (1950)
Image via: Wikiart

Scientists at Rutgers, State University of New Jersey, claim that computers equipped with face-and object-recognition technology are able to make connections between artworks which could lead to a new understanding of the way artists influence each other, The Telegraph reports.

In an experiment for which machines were fed 1,710 images of artworks by 66 artists spanning five centuries, they were able to detect well-known parallels—between, say, Diego Velazquez’s Portrait of Pope Innocent X and Francis Bacon’s Study After Velazquez’s Portrait of Pope Innocent—as well as similarities never detected by art historians before.

Among these are the links between Frédéric Bazille’s Studio 9 rue de la Condamine (1870) and Norman Rockwell’s Shuffleton’s Barber Shop.

Frédéric Bazille, Studio; 9 rue de la Condamine (1870) Photo: wikimedia Commons

Frédéric Bazille, Studio; 9 rue de la Condamine (1870)
Photo: wikimedia Commons

“The painting might not look similar at the first glance, however, a closer look reveals striking similarity in compositions and subject matter, that is detected by our automated methodology,” say the scientists in their paper.

The Bazille-Rockwell connection seems mainly based on the recognition of similar elements in the paintings. What this means as far as the future of art scholarship is concerned remains to be seen.

“We are not asserting truths but instead suggesting a possible path towards a difficult task of measuring influence,” the scientists prudently conclude.

Follow Artnet News on Facebook:

Want to stay ahead of the art world? Subscribe to our newsletter to get the breaking news, eye-opening interviews, and incisive critical takes that drive the conversation forward.