| KEYWORD |
Microelectronics
Real-time Face Recognition for Industrial Applications
Tesi esterna in azienda
Parole chiave IMAGE ANALYSIS, MACHINE LEARNING
Riferimenti LUCIANO LAVAGNO
Riferimenti esterni Marcello babbi, Reply Torino
Gruppi di ricerca Microelectronics
Tipo tesi APPLIED RESEARCH
Descrizione Reply has established an experimental laboratory in Area 42 where new ideas and challenges are
addressed in the field of Edge AI and Computer Vision. Starting from the developed edgeoptimized
model (MobNet), the student will be involved in the design and validation of a new face
recognition model extending solution capabilities. The thesis project aims to develop and
optimized a Deep Learning algorithm able to recognize multiple different faces to enable hand-less
lab control access and operator authentication.
Conoscenze richieste Python programming, some knowledge of Machine Learning, image processing
Note The student will be involved in:
❑ State-of-the-art literature review
❑ SW requirements definition for edge deployment
❑ Data pre-processing and feature engineering
❑ On-edge performance optimization and compression methods development (e.g. pruning, quantization);
❑ Developing and implementing a deep learning-based model for image analysis
❑ HW computational requirements trade-off
Scadenza validita proposta 11/10/2024
PROPONI LA TUA CANDIDATURA