• AI analysis indicates that St. Joseph's face in Raphael's 'Madonna della Rosa' was likely painted by someone other than Raphael.
• Researchers trained an AI model to identify Raphael's painting style with 98% accuracy, then analyzed the individual faces in the painting.
• The AI-driven discovery supports existing art historical speculation and highlights AI's role in art authentication and analysis.

An AI analysis of Raphael's 'Madonna della Rosa' has revealed that the face of St. Joseph was likely not painted by Raphael himself. Researchers from the UK and the US trained an AI model, leveraging deep feature analysis and machine learning techniques, to recognize Raphael's distinct style. When applied to the painting, the AI identified inconsistencies in St. Joseph's face compared to the rest of the artwork, corroborating long-standing suspicions among art critics. This discovery highlights the potential of AI in art authentication and historical analysis.

• What: AI analysis determined that the face of St. Joseph in Raphael's 'Madonna della Rosa' was likely painted by someone other than Raphael.
• Who: Researchers from the UK and the US, led by Professor Hassan Ugail, conducted the AI analysis.
• When: The Madonna della Rosa was painted between 1518 and 1520. Art critics began suspecting inconsistencies in the mid-1800s. The research findings were published in 2023.
• Where: The research was conducted by teams in the UK and the US, with the painting itself housed at the Museo Nacional del Prado.

The AI-driven discovery provides compelling evidence supporting long-held suspicions about collaboration in the creation of 'Madonna della Rosa.' The use of deep feature analysis and machine learning allows for a detailed examination of artistic styles, revealing nuances that might be missed by the human eye. While the identity of the second artist remains uncertain, Giulio Romano, a pupil of Raphael, is a likely candidate. This event underscores the potential of AI as a valuable tool in art authentication, offering new insights into historical masterpieces.

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. The computer sees far more deeply than the human eye, to microscopic level.

This is not a case of AI taking people's jobs. The process of authenticating a work of art 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.

AI analysis, employing deep learning algorithms trained on Raphael's authenticated works with up to 98% accuracy, has strongly indicated that while most of 'Madonna della Rosa' aligns with Raphael's style, the face of St. Joseph was likely executed by a different artist. This corroborates long-standing art historical debates and suspicions regarding the painting's authorship. The AI's ability to analyze brushstrokes, color palettes, and shading at a microscopic level provides objective, quantifiable evidence that supports the theory of collaborative work, potentially involving Raphael's pupil, Giulio Romano. This discovery underscores the potential of AI as a powerful tool in art authentication, capable of uncovering previously unseen details and prompting a re-evaluation of traditional art historical narratives, while also raising questions about the dynamics of Renaissance workshops and the complexities of artistic collaboration. Further investigation, potentially involving AI analysis of other artists' styles, could reveal the identity of the second artist and shed light on the collaborative practices employed in Raphael's workshop.