Robust face recognition based on domain adaptation

• Grant number: 19/15357-8
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: January 01, 2020
• End date: December 31, 2020
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Aparecido Nilceu Marana
• Grantee: João Renato Ribeiro Manesco
• Host Institution: Faculdade de Ciências (FC). Universidade Estadual Paulista (UNESP). Campus de Bauru. Bauru , SP, Brazil

Abstract

In the last decades, for reasons of safety or convenience, biometric characteristics are increasingly being used to identify individuals who wish to have access to systems or places, and facial features are one of the most used characteristics for this purpose. For biometric identification to be effective, the rates of recognition accuracy must be high. However, these rates can be very low depending on the difference (displacement) between the domain of the images stored in the database of the biometric system (source images) and the images used at the moment of identification (target images). The objective of this research project is to study two recent methods of domain adaptation, TKL (Transfer Kernel Learning) and KEMA (Kernel Manifold Alignment), and to evaluate their performances in biometric facial recognition tasks, in which there are differences between the source and target images domains. (AU)