Classification and clustering of typographic fonts from the Museu Paulista collection using machine learning techniques

• Grant number: 24/23738-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2025
• End date: April 30, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Paula Dornhofer Paro Costa
• Grantee: Matheus Hencklein Ponte
• Host Institution: Faculdade de Engenharia Elétrica e de Computação (FEEC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

Curating and classifying historical collections are essential processes for preserving cultural heritage, but they are often performed manually, leading to slow progress and increased susceptibility to errors. This project addresses the specific challenge of classifying and clustering movable types and ornaments into typographic families, using the collection of the Museu Paulista as a case study. The proposal involves applying computer vision models to identify visual patterns that can automate steps in the curatorial process. Based on the collected data, the aim is to build an initial database and implement machine learning models as a proof of concept. Beyond exploring technical possibilities, the project seeks to foster collaboration between artificial intelligence and curatorship, establishing an interdisciplinary foundation for future studies and applications in cultural heritage preservation.