Thesis – Task-Aware Joint Optimization for Efficient Edge Face Recognition

This thesis project focuses on developing a task-aware joint optimization framework for front-end processing and face recognition on resource-constrained edge devices. The role involves optimizing front-end parameters to preserve essential identity-discriminative information while reducing processing overhead, combined with a lightweight, quantized recognition network. The proposed approach will be evaluated for recognition reliability, computational complexity, and energy consumption, with implementation targeting FPGA-based edge systems.