Google researchers are experimenting with real-time facial recognition that continuously authenticates users from a mobile phone's point of view, looking up the user's nose.
Researchers at the University of Maryland, Rutgers University, and Google's Advanced Technology and Projects (ATAP) developed the technology called "facial segment-based face detector" (FSFD) to detect partially cropped and occluded faces captured using a smartphone's front-facing camera, according to a whitepaper detailing the technology.
The method is designed to verify a user for secure transactions during everyday use.
The authentication process is divided into three phases designed to ultimately learn and “detect facial segments in the frame, and cluster the results to obtain the region which is most likely to contain a face," researchers said in the whitepaper.
Researchers said the method performs better than many state-of-the-art face detection methods in terms of accuracy and processing speed.
