A painting with a mysterious origin is likely a Raphael masterpiece, researchers in the UK have said after using facial recognition technology and artificial intelligence (AI) analyze the portrait.
Renaissance painting, no de Bracey Tondo, has been widely studied for over 40 years. Researchers from the University of Nottingham and Bradford University used an artificial intelligence facial recognition system developed by Hassan Ugail, a professor of visual computing at Bradford, to identify its likely creator.
Instead of DNA, the system uses a DNN – a deep neural network – that identifies patterns in images and videos. The system is more accurate than the human eye and was able to analyze the similarity of a painting with another created by Raphael.
The Italian Renaissance artist is considered “more versatile than Michelangelo and more prolific than their older contemporary Leonardo.” in accordance with The National Gallery in London, which houses some of his paintings.
Ugail said the facial recognition system is aided by artificial intelligence “by which millions of facial images are fed into a machine learning algorithm that learns the ‘deep’ features and characteristics of the human face.”
“These traits can be physical attributes (such as facial shapes, colors, and textures), but also include many (potentially thousands of traits) that cannot be described visually or physically,” Ughail told CBS News in an email. “In this sense, the analysis performed with these facial recognition systems can compare two images of faces in much greater detail and can outperform humans.”
The technology found that de Bresi’s Tondo, which depicts a woman and child, closely matches Raphael’s Sistine Madonna, which also depicts a very similar woman and child.
The so-called Madonnas in each painting were 97% similar, while the children in each were 86% similar – according to the study, a similarity of more than 75% is considered identical.
Ugail said the technology is used for identity recognition and authentication in criminal investigations and routine identity checks. It can also be used in the analysis of medical images to diagnose diseases such as cancer.
The picture was a part de Bracy Trust, art collection that belonged to the late George Lester Winward. He donated his collection to a trust so that it would be available for study by art historians and researchers.
He had trust before analyzed de Brécy Tondo and found its pigments According to Howell Edwards, professor and honorary scientific adviser to the trust, these were pre-17th century works and were not a Victorian copy.
A four-year analysis by the late Raphael expert Dr. Murdoch Lothian found that Tondo was likely a Raphael, Timothy Benoy, the trust’s honorary secretary, told CBS News via email.
“The opinion of other art historians we consulted, including some with expertise in the Italian Renaissance and Raphael, was that the Tondo is a ‘possible’ Raphael.”
Dr. Christopher Brookeemeritus research fellow at the University of Nottingham, told CBS News via email that the study is “a major step forward in the use of machine learning in art history.”
“This is a very well-founded study with positive results,” said Brooke, a co-author of the study and an expert on the history of church art and remote sensing techniques.
Raphael, whose full name was Raphael Santi, was credited as the architect of St. Peter’s Basilica in the Vatican until his death. Several architects took on the project, with the most prominent of them. One of Raphael’s most famous paintings is The School of Athens.
This article is first published on Source link