Curvature Estimation Using Machine Learning Algorithms

• Grant number: 23/17907-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: February 01, 2024
• End date: January 31, 2025
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: João Do Espirito Santo Batista Neto
• Grantee: Matheus Paiva Angarola
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 19/07316-0 - Singularity theory and its applications to differential geometry, differential equations and computer vision, AP.TEM

Abstract

This proposal is part of the context of machine learning algorithms for estimating mean and Gaussian curvature, as a counterpoint to conventional geometric techniques. The research involves analysing and implementing regression algorithms trained from a feature vector containing information extracted from the 3D mesh (mapped as a graph), together with information used in the geometric calculation. Once the machine learning regression model has been trained on this labelled data, it is hoped that the test phase will produce results close to those obtained by the geometric approach, but in a considerably shorter processing time. a This research is part of one of the focus areas of the thematic project FAPESP 2019/07316-0.