Researchers employ machine learning to assess artwork legitimacy

Enthusiasm abounds as we take a look at the amazing breakthrough in artwork analysis achieved by researchers! Through their application of AI analysis to Raphael’s famed painting, Madonna della Rosa, the study published in Heritage Science has identified that the face of St Joseph in the artwork was likely not wholly painted by Raphael himself.
However, there is no need for alarm as this is common for Renaissance artists to collaborate with students and assistants, creating debate about correctly attributing works from this era.
The researchers leveraged machine learning to locate different techniques used in the work to peel back its origins. They used a well-known AI model called ResNet50, originally designed for recognizing objects in images, and adapted it to focus on artworks, specifically to identify features unique to Raphael’s paintings.
To add even more accuracy to this process, they also used a method known as Support Vector Machine (SVM) which helped the AI to classify the artworks correctly. This combined approach proved highly successful, boasting a 98% success rate in identifying Raphael’s paintings.
In addition to this, the researchers further developed techniques to analyze the brushstrokes in a painting, as each artist has a unique way of applying paint. This analysis provides another layer of verifying authenticity.
Mathematician and computer scientist Hassan Ugail from the University of Bradford described the process: “Using deep feature analysis, we used pictures of authenticated Raphael paintings to train the computer to recognize his style to a very detailed degree, from the brushstrokes, the color palette, the shading and every aspect of the work”.
Ugail went on to emphasize the AI’s extended capability versus human analysis, noting, “The computer sees far more deeply than the human eye, to microscopic level.”
The analysis revealed that while the Madonna, Child, and St John were consistent with Raphael’s work, St Joseph’s face did not match his style. Ugail remarked, “When we tested the della Rosa as a whole, the results were not conclusive, so then we tested the individual parts and while the rest of the picture was confirmed as Raphael, Joseph’s face came up as most likely not Raphael.”
This AI’s findings add weight to the long-standing theory that Giulio Romano, a pupil of Raphael, may have contributed to the painting, particularly in the depiction of St Joseph, though this remains unconfirmed.
Ugail described how AI forms just one part of a multifaceted authentication process that “involves looking at many aspects, from its provenance, pigments, condition of the work, and so on. However, this sort of software can be used as one tool to assist in the process.”
It is truly remarkable to see how AI is able to break down even the most ambiguous and highly subjective topics with the help of novel machine learning. Not long ago, researchers created an AI model capable of discerning the origin of wine based on its “terroir,” and now, the technology is identifying artwork’s authenticity!
This is a groundbreaking breakthrough in the world of art analysis, and a remarkable example of how AI can be used for the greater good of humanity.