17 June 2021
Best demo paper award
VLSI Technology has awarded CSEM’s Petar Jokic and his co-authors a Best Demo Paper award for their work entitled “A Sub-mW Dual-Engine ML Inference System-on-Chip for Complete End-to-End Face-Analysi...
June 15, 2021
2021 NEWCAS Best Paper Award
The 19th IEEE International New Circuits and Systems Conference (NEWCAS) has awarded CSEM’s Petar Jokic and his co-authors the ResMIQ Best Student Paper award for their work entitled “Battery-Less Face Recognition at the Extreme Edge.” The award was presented (virtually) on June 15th in Toulon, France.
NEWCAS is an international conference and networking forum for engineers and researchers in the field of circuits and systems.
Petar Jokic's co-authors are Stephane Emery, CSEM, and Luca Benini, ETH Zurich.
Results in brief
Machine learning-based face recognition systems are commonly used in mobile platforms to assist the camera systems, unlock the device, or analyze the facial expressions. The computational complexity of the underlying algorithms as well as the power consumption of the entire imaging and processing system largely limit the deployment to powerful mobile processing systems with large rechargeable batteries. However, these computer vision capabilities would also be useful in miniaturized low-power applications with stringent battery-size limitations. The presented work assesses the feasibility of such a computer vision edge processing system on a battery-less credit card-sized demonstrator using an ultra-low-power image sensor and a machine learning system-on-chip, achieving self-sustainable operation using solar energy harvesting with a small onboard solar cell. It enables continuous 1 frame-per-second battery-less imaging and face recognition in indoor lighting conditions.