Some NIST face analysis evaluations test whether software can detect presentation attacks, where a spoof image is used in attempts to gain access to a device or space or simply to hide someone's true identity. Presentation attacks can take many forms, such as wearing makeup, holding up a printed photo or displaying a digital photo of another person.
Credit: M. Ngan, N. Hanacek/NIST
Face recognition software is commonly used as a gatekeeper for accessing secure websites and electronic devices, but what if someone can defeat it by simply wearing a mask resembling another person’s face? Newly published research from the National Institute of Standards and Technology (NIST) reveals the current state of the art for software designed to detect this sort of spoof attack.
The new study appears together with another that evaluates software’s ability to call out potential problems with a photograph or digital face image, such as one captured for use in a passport. Together, the two NIST publications provide insight into how effectively modern image-processing software performs an increasingly significant task: face analysis.
Face analysis is distinct from face recognition, which may be a more familiar term. Broadly speaking, face recognition aims to identify a person based on an image, while face analysis is concerned with image characterization, such as flagging images that are themselves problematic — whether because of nefarious intent or simply due to mistakes in the photo’s capture.
The two publications are the first on the subject to appear since NIST divided its Face Recognition Vendor Test (FRVT) program into two tracks, Face Recognition Technology Evaluation (FRTE) and Face Analysis Technology Evaluation (FATE). Efforts involving ..
Support the originator by clicking the read the rest link below.
