• Capable of using images and video evidence of
varying quality and standards to provide real-time
and forensic surveillance solutions
• 2D to 3D pose correction technology and deep
neural network deliver unparalleled performance
• Capable to manage millions of templates
• Simple and quick enrolling
• Overcomes the challenges of subject pose, expression,
partial facial occlusions and environmental lighting
• 128-byte template size, more than 5X smaller than
similar software
• Accuracy as measured by ROC and Rank 1 testing
of publicly available data sets: FERET, LFW, IJB-A,
FRGC, PaSC, PUT, China Daily, MUCT
• Fast: 25 million comparisons per second
• Reliable: 3D matching light, pose, occlusion,
motion, crowd or expression
• Scalable: Scales easily and economically with low
system & storage requirements