A study using artificial intelligence found a painting with mysterious origins is likely a Raphael, researchers say

A painting with mysterious origins is likely a Raphael masterpiece, UK researchers said after using facial recognition technology and artificial intelligence (AI) to analyze the portrait.

The Renaissance painting named de Brécy Tondo has been studied extensively for more than 40 years. Researchers from the University of Nottingham and the University of Bradford used an artificial intelligence facial recognition system developed by Hassan Ugail, a professor of visual computing at Bradford, to determine its likely creator.

Instead of DNA, the system uses DNN — a deep neural network — that recognizes patterns in images and videos. The system is more accurate than the human eye and was able to analyze the painting’s similarities to another by Raphael.

The Italian Renaissance painter is considered “more versatile than Michelangelo and more prolific than her older contemporary Leonardo” according to the National Gallery in London, which houses some of his paintings.

Ugail said the facial recognition system will be powered by artificial intelligence, “feeding millions of facial images to a machine learning algorithm that learns ‘deep’ features and characteristics of the human face.”

“These features can be physical attributes (e.g., facial shapes, colors, and textures) but also many (potentially thousands of features) that cannot be described either visually or physically,” Ugail said in an email to CBS News. “In that sense, the analysis performed by these facial recognition systems can compare two facial images in much more detail and outperform humans.”

The technology found that de Brécy’s tondo, which depicts a woman and a baby, closely matches Raphael’s Sistine Madonna, which also depicts a very similar woman and baby.

The so-called Madonnas in each painting had a 97 percent similarity, while the children in each had an 86 percent similarity – a similarity of over 75 percent is considered identical, according to the study.

According to Ugail, this technology is used to recognize and authenticate identities during criminal investigations and routine identity checks. It can also be used in medical image analysis to diagnose diseases like cancer.

The painting formed part of the de Brécy Trust, an art collection owned by the late George Lester Winward. He gave his collection to the Trust for study by art scholars and researchers.

The Trust had previously analyzed the de Brécy tondo and found that its pigments were those of works from before the 17th century and that it was not a Victorian copy, according to Howell Edwards, Professor and Honorary Scientific Advisor to the Trust.

A four-year analysis by the late Raphael specialist Dr. Murdoch Lothian revealed the tondo was likely a Raphael, Timothy Benoy, the trust’s honorary secretary, told CBS News via email.

“The view of other art historians interviewed, including some experts with Italian Renaissance and Raphael expertise, was that the tondo is a ‘possible’ Raphael.”

dr Christopher Brooke, a volunteer researcher at the University of Nottingham, told CBS News via email that the study was “a major step forward in the use of machine learning in art history.”

“It’s a very solid study with positive results,” said Brooke, a co-author of the study and an expert in church art and remote sensing techniques.

Raphael, whose full name was Raffaello Santi, was appointed architect of St. Peter’s Basilica in the Vatican until his death. Several architects took on the project, the most notable being Michelangelo. One of Raphael’s most famous paintings is The School of Athens.