Where the old world meets the new: AI used to help preserve our heritage

Researchers from UCL and Duke University used AI to analyse high-resolution digital X-ray images from the Ghent Altarpiece – a large and complex 15th-century altarpiece in St Bavo's Cathedral, Belgium.  – as part of a larger UCL-led research collaboration also involving the National Gallery.

The brothers Van Eyck’s Ghent Altarpiece originally consisted of twelve panels and has survived near destruction over the centuries and seizure by the Nazis in the 1940s. 

While X-ray images can help to establish a piece’s condition and provide insights into an artist’s technique, the nature of X-rays means that everything is picked up in the image and although this is informative, it can make them difficult to interpret. This is particularly true for the Ghent’s side panels, which were painted on both sides.

Academics used a newly developed algorithm to study mixed X-ray images containing features from the front and back of the painting’s double-sided panels and scientists have deconstructed them into two clear images. 

Lead academic Professor Miguel Rodrigues (UCL Electronic and Electrical Engineering) said: 

“This approach demonstrates that artificial intelligence-oriented techniques — powered by deep learning — can be used to potentially solve challenges arising in art investigation

We’d like to see the impact that the development of similar AI-oriented approaches will have on our ability to reveal other hidden features in a painting, such as earlier concealed designs. 

The information and techniques revealed in this project will not only enable art historians, conservators and heritage scientists to better understand Old Master paintings but also help experts protect and restore delicate pieces. 

Alongside the scientists involved in the project, the Ghent Altarpiece Conservation Team’s work continues and they will next research how the algorithm may lead to new insights supporting their conservation work.

The research was funded by the EPSRC and the Simons Foundation.

Links

• UCL Electronic and Electrical Engineering
• Professor Miguel Rodrigues
• The Engineering and Physical Sciences Research Council
• The Simons Foundation
• The Ghent Altarpiece: the truth about the most stolen artwork of all time (Guardian)
• Hidden works of Goya, Van Gogh and Van Eyck could be discovered using artificial intelligence (Telegraph)

Image

• Credit: Sailko, Source: Wikimedia Commons, Licence: CC BY-SA 3.0