AI discovers ‘hidden detail’ inside Raphael’s famous Madonna painting revealing 500-year-old mystery

[ad_1]

ARTIFICIAL intelligence has discovered something unusual hidden inside a Raphael painting.

New research has found that a face in Raphael’s Madonna della Rosa work was not painted by the Renaissance artist.

1

AI has discovered something unusual hidden inside a Raphael paintingCredit: PA

The revelation about the face, depicting Saint Joseph, was identified by an AI neural network.

Researchers have long debated whether the painting was a Raphael original or not.

But now, thanks to AI, the experts believe that the face may have been painted by Raphael’s pupil, Giulio Romano.

This is one of the first instances of AI potentially identifying a hidden detail in a painting that is otherwise impossible to discern.

HOW DOES IT WORK?

The AI algorithm was trained on a custom analysis dataset of other Raphael paintings.

Specifically, the team used a modified pre-trained architecture developed by Microsoft called ResNet50.

They combined ResNet50 with a traditional machine-learning technique called a Support Vector Machine.

In turn, the algorithm seamlessly learned the brushstrokes, color palettes, and shading that are typical of Raphael’s work.

When the AI analyzed the Madonna della Rosa, it was able to detect some subtle differences in the face of St. Joseph.

“The computer sees far more deeply than the human eye, to a microscopic level,” mathematician and computer scientist Hassan Ugail from the University of Bradford in the UK said.

The researchers’ innovative method is accurate 98% of the time when it comes to identifying Raphael’s paintings, researchers noted.

Experts believe the Madonna della Rosa was painted between the years 1518 to 1520.

However, it wasn’t until the mid-1800s that art critics began to question whether Raphael had painted the entire thing.

Thanks to AI, experts may soon have the answer once and for all.

“This is not a case of AI taking people’s jobs,” Ugail said.

“The process of authenticating a work of art involves looking at many aspects, from its provenance, pigments, condition of the work, and so on,” he added.

“However, this sort of software can be used as one tool to assist in the process.”

The use of AI in art history is still in its early stages, but it has the potential to provide major insights.



[ad_2]