Paravision joins podium for mugshot and webcam biometric accuracy in NIST facial recognition testing

Paravision has cracked the top three in biometric accuracy rankings in multiple categories in the latest edition of the National Institute of Standards and Technology’s (NIST’s) Face Recognition Vendor Test (FRVT) 1:N Identification report. The company says it is now the only biometrics provider to be ranked in the top five in both the NIST FRVT 1:1 Verification and 1:N Identification reports.

The NIST report published on March 24 shows the Paravision-005 algorithm ranks second in mugshot investigation accuracy for each of the first four time lapse durations tested, and third in the first (lowest time-lapse) mugshot identification category. The company says it was third overall in the aging tests, and first among companies form the U.S. and Europe.

The report tested more than 200 algorithms from 60 vendors. The time lapse duration (or aging) match test is newly included, matching facial images separated by up to 18 years.

According to the company announcement, Paravision also ranks third in matching mugshots and webcam photos worldwide, and first among technology providers from the U.S. and Europe, and first worldwide in matching faces in profile.

The announcement also highlights Paravision’s improvement in performance and ranking over the past two years since it first submitted its facial recognition algorithms to NIST for evaluation.

Paravision rebranded from Ever AI last year and integrated its biometric technology with Booz Allen’s enterprise AI platform in November.

Article Topics

accuracy  |  biometrics  |  facial recognition  |  mugshots  |  NIST  |  Paravision  |  testing