A novel ultrasonic sensing based human face recognition

This paper presents a novel ultrasonic sensing based face recognition system, which can complement traditional vision-based recognition due to its unobtrusiveness, low-cost and robust to environmental conditions. For different configurations of Transmitter-Receiver (TR) pairs, ultrasonic chirp signal is chosen as the transmitted signal and used to demodulate the echoes for face recognition. Features directly related with the geometry of human face are extracted and verified in the designed experiments. Our results demonstrate that the proposed system can achieve a high recognition rate of 99% when required to recognize one hundred and ten different human faces, which encourages the application of ultrasound sensing for face recognition as an attractive alternative method.