AI analysis casts doubt on Van Eyck paintings in Italian and US museums

2026-02-07 · Source: AI (artificial intelligence) | The Guardian · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Creative Industries & Arts · Depth: Fundamental Awareness, short

Summary

An AI-powered analysis by Swiss company Art Recognition, in collaboration with Tilburg University, casts significant doubt on the authenticity of two "Saint Francis of Assisi Receiving the Stigmata" paintings attributed to 15th-century Flemish master Jan van Eyck. The near-identical unsigned works, housed in the Philadelphia Museum of Art and the Royal Museums of Turin, were subjected to scientific tests that failed to detect Van Eyck's brushstrokes. The Philadelphia version registered as "91% negative" and the Turin version as "86% negative" for his hand. This contrasts with "The Arnolfini Portrait," another Van Eyck work, which showed an 89% likelihood of authenticity. Leading Van Eyck scholar Till-Holger Borchert suggests these findings support theories that both paintings are studio works, not directly by the master.

Key takeaway

For art historians and museum curators evaluating the authenticity of Old Master paintings, these AI-driven findings suggest a need to re-examine existing attributions. You should consider integrating AI brushstroke analysis as a supplementary tool in provenance research, especially for works with uncertain origins or those suspected of being studio productions. This technology offers a new lens for distinguishing masterworks from workshop copies, potentially leading to significant reclassifications.

Key insights

AI analysis of brushstrokes can challenge long-held attributions of master paintings, suggesting studio works over direct authorship.

Principles

• AI can identify artist-specific brushstroke patterns.
• High negative percentages indicate low authenticity likelihood.

Method

Art Recognition uses AI to analyze brushstrokes in paintings, comparing them against known authentic works to determine the likelihood of a specific artist's hand.

In practice

• Apply AI brushstroke analysis to disputed artworks.
• Use AI for art authentication in museum collections.

Topics

• AI Art Authentication
• Jan van Eyck
• Brushstroke Analysis
• Art Recognition

Best for: AI Scientist, Research Scientist, Domain Expert, Tech Journalist

Related on AIssential

• Case Western Reserve Researchers Using AI at Hair-Width Scale to Reveal Renaissance Master’s Hidden Hand | Newswise - Newswise — AI and physics reveal microscopic brushstroke patterns to attribute and authenticate Renaissance art.
• The AI Illusion (Part 2): The AI Detection Mirage — Current AI image detectors are unreliable, often misidentifying human art or hallucinating evidence.
• ForensicConcept: Transferable Forensic Concepts for AIGI Detection — This framework enables auditable, transferable forensic concept extraction from AIGI detectors, boosting generalization across unseen generators.
• Evaluation of Image Matching for Art Skills Assessment — Automated drawing skill assessment is feasible using computer vision, with SIFT-based key point matching proving effective for hand-drawn image comparison.
• Is Richard Tice’s picture AI-manipulated? Here are five giveaways — AI-generated or edited images often exhibit specific, identifiable artifacts like distorted hands or garbled text.
• Perplexity Kills Ads Over Trust Concerns — Achieving photorealistic AI images requires detailed prompting, structured inputs, reprompting from real photos, and post-processing imperfections.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by AI (artificial intelligence) | The Guardian.