A Measurement Study of RFID-based Face Recognition

Conventional vision-based face recognition systems has the advantages of high accuracy and fast recognition speed, however, it also suffers from the limitation of poor privacy protection and lower accuracy under insufficient background lighting conditions and limited computing resources. In contrast, recently proposed RFID-based face recognition enjoys much better privacy protection and is independent on the lighting conditions of the environment. In this paper, we investigate the emerging RFID-based face recognition technologies and assume that tag configurations, input data sources, filtering algorithms and dynamic background are all factors that may impact the accuracy of RFID-based face recognition. We set up the testbed for performance measurement on RFID-based face recognition and proposes a measurement study to verify the impact of different factors on the recognition accuracy of RFID-based face recognition.