Thesis – Task-Aware Joint Optimization for Efficient Edge Face Recognition
Core
Develop a task-aware joint optimization framework for front-end processing and face recognition on resource-constrained edge devices to balance recognition reliability with computational efficiency.
Role type
Master's/Bachelor's thesis student in Computer Science or Software Engineering
Builds
FPGA-based edge systems for intercoms and access control
Domain
Computer Vision / Edge AI / Embedded Systems
Deliverable
research
Required skills
Deep learning, Convolutional Neural Networks (CNNs), FPGA development, Embedded systems programming, Image processing, Quantization techniques
Preferred skills
Spectral convolution, Sub-byte quantization, Low-power design
Technologies
FPGA, C/C++, Python, TensorFlow/PyTorch (implied by CNN context)
Responsibilities
Design and implement a joint optimization framework, Evaluate recognition reliability under varying imaging conditions, Optimize for computational complexity and energy consumption, Implement on FPGA-based edge systems
