IREX Ranked #1 in NIST Face Recognition Vendor Test, among all the U.S. companies

Alexandria, VAJanuary, 20 2021 –  IREX announced today that its face recognition algorithm was ranked #1 in accuracy among all the U.S. companies for the Border Dataset in the most recent Face Recognition Vendor Tests (FRVT) conducted by the National Institute of Standards and Technology (NIST).

In the FRVT report released by NIST on January 19, 2021, the IREX’s face recognition algorithm was ranked in top 50 in accuracy for all photo datasets among 267 algorithms submitted by 170 companies around the world. 

Border Photos and Wild Photos are the most relevant datasets to identify missing people and suspects in non-cooperative mode from arbitrary city cameras. These datasets are less constrained in terms of viewing angle, lighting, and resolution when compared to the other FRVT datasets.

The following table gives the False Non-Match Rate (FNMR) to achieve the given False Match Rate (FMR) of the top algorithms by the US vendors according to the latest NIST FRVT 1:1 Verification Report:

Dataset
FMR
Border
1E-05
Wild
1-E04
irex-000 (US)0.0078 0.0285
rankone-010 (US)0.01170.0320
camvi-004 (US)0.01410.0284
paravision-003 (US)0.0156 0.0278

FNMR to achieve the given FMR. Smaller is better.

The IREX face recognition algorithm is highly optimized for non-cooperative recognition in real-world CCTV systems. While the FRVT estimates the recognition accuracy on still images, IREX uses an additional layer of neural networks to create aggregated templates from multiple video frames. The advanced technique further increases the real-world accuracy.

The IREX algorithm also detects various facial features including; gender, age, glasses, beard, mustaches, face mask, headdress, and skin color. IREX can generate alerts for safety regulation violations such as the lack of face mask, protective glasses or helmet. 

The IREX algorithm does identify people wearing masks. According to the NISTIR 8331 – Ongoing FRVT Part 6B: Face recognition accuracy with face masks using post-COVID-19 algorithms, IREX ranked #51 of 179 algorithms evaluated to date. 

IREX will be shortly submitting its face recognition library for the FRVT 1:N Identification Test.

Watch the IREX face recognition demo to find missing children.

About IREX

Headquartered in Alexandria, VA, U.S., IREX is a video-based cloud service for evidence-based safety designed to empower cities, governments and security teams. With over 20 Artificial Intelligence modules built in, IREX allows cities to adapt to ever-changing threats to combat 21st-century problems such as overcrowding, missing people, crime, hostile protests, mass shootings, and illegal immigration. IREX partners with the National Child Protection Task Force to fight human trafficking and locate missing children.