Forensic Study of Paintings Through the Comparison of Fabrics

2025-06-25

AI Summary

Traditional canvas thread-density mapping fails to handle discontinuous canvas rolls, hindering artwork authentication and attribution. To address this, we propose a Siamese-network-based framework for canvas texture comparison. Our method directly learns fabric texture features from high-resolution scan images, eliminating reliance on thread-density maps. It incorporates a multi-sample prediction aggregation mechanism to produce robust similarity scores, enabling— for the first time—reliable discrimination between canvases sharing identical weave structures and comparable thread densities. Evaluated on the Prado National Museum’s plain-weave canvas dataset, our approach achieves accurate determination of canvas provenance relationships, demonstrating high precision and practical utility. This work establishes a scalable, generalizable paradigm for painting material provenancing, forgery detection, and cultural heritage preservation.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Matrix & Tensor Methods
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Data transparency and provenance

Abstract

The study of canvas fabrics in works of art is a crucial tool for authentication, attribution and conservation. Traditional methods are based on thread density map matching, which cannot be applied when canvases do not come from contiguous positions on a roll. This paper presents a novel approach based on deep learning to assess the similarity of textiles. We introduce an automatic tool that evaluates the similarity between canvases without relying on thread density maps. A Siamese deep learning model is designed and trained to compare pairs of images by exploiting the feature representations learned from the scans. In addition, a similarity estimation method is proposed, aggregating predictions from multiple pairs of cloth samples to provide a robust similarity score. Our approach is applied to canvases from the Museo Nacional del Prado, corroborating the hypothesis that plain weave canvases, widely used in painting, can be effectively compared even when their thread densities are similar. The results demonstrate the feasibility and accuracy of the proposed method, opening new avenues for the analysis of masterpieces.

Problem

• Authenticating paintings by comparing canvas fabrics without thread density maps
• Developing deep learning to assess textile similarity in art canvases
• Enabling robust comparison of plain weave canvases with similar thread densities

Innovation

• Deep learning for textile similarity assessment
• Siamese model compares canvas image pairs
• Robust similarity score from multiple samples