Face recognition provides a desirable solution for authentication and surveillance in Internet of Things platforms for elderly care. However, its inclusion is challenging because of the possibly reduced interaction capabilities of users, the high variety of interaction devices, and the need of managing biometric data securely. Our approach relies on lightweight deep neural networks for secure recognition and to guide users during interaction. An automated procedure selects the appropriate inference engine, model configurations, and batch size, based on edge device characteristics. Biometric data is homomorphically encrypted to preserve privacy. An evaluation with respect to state-of-the-art alternatives shows its potential.

To read the full text: Click here!