Multispectral image analysis of cultural heritage works - Contributions to the identification of materials and pigments

• Grant number: 25/24605-6
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: December 01, 2025
• End date: November 30, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Nina Sumiko Tomita Hirata
• Grantee: Lucas Leimig Piquet
• Host Institution: Instituto de Matemática e Estatística (IME). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Associated research grant: 22/15304-4 - Learning context rich representations for computer vision, AP.TEM

Abstract

In the analysis of works of art, a fundamental step is the identification of materials and pigments used. Techniques such as X-ray fluorescence and Raman spectroscopy allow the identification of chemical elements or compounds at specific points in the artwork. On the other hand, multi-spectral imaging techniques enable the collection of the approximate spectral response over a dense set of points. By integrating these two techniques, the complementarity between them can be leveraged to obtain a more efficient characterization of materials and pigments in a work. In this project, the main objective will be the development of computational methods for identifying regions in the image with similar spectral responses or with a specific spectral pattern, in order to aid the process of a detailed spectroscopic analysis.