Protect access to your workplace with facial security
3D body (skeletal) tracking middleware
Edge AI hardware
for face and body tracking
for face and body tracking
Facial recognition platform for video processing
Advanced face liveness detection for digital onboarding and KYC
Scalable fasial recognition API for on-pream or AWS cloud deployment
Facial and body recognition library for server, mobile and embedded solutions
3DiVi Inc., founded in 2011, is one of the leading developers of AI and machine learning (ML) technologies for computer vision.
Let's talk business
Just fill in the form and we will contact you shortly
On-premise license request
Just fill in the form and we will contact you shortly
Face recognition Accuracy
NIST FRVT 1:1 Performance Summary
VISA - Full Frontal image type. The images are of size 252x300 pixels. The mean interocular distance (IOD) is 69 pixels.
Mugshot - Full Frontal image type. The images are of variable sizes. The mean IOD is 113 pixels.
Border - The images are taken with a camera oriented by an attendant toward a cooperating subject. This is done under time constraints so there are role, pitch and yaw angle variations. Also background illumination is sometimes strong, so the face is under-exposed. There is some perspective distortion due to close range images. Some faces are partially cropped.
Wild - The images include many photojournalism-style images. Resolution varies very widely. The images are very unconstrained, with wide yaw and pitch pose variation. Faces can be occluded, including hair and hands.
Mugshot - Full Frontal image type. The images are of variable sizes. The mean IOD is 113 pixels.
Border - The images are taken with a camera oriented by an attendant toward a cooperating subject. This is done under time constraints so there are role, pitch and yaw angle variations. Also background illumination is sometimes strong, so the face is under-exposed. There is some perspective distortion due to close range images. Some faces are partially cropped.
Wild - The images include many photojournalism-style images. Resolution varies very widely. The images are very unconstrained, with wide yaw and pitch pose variation. Faces can be occluded, including hair and hands.
Face Recognition Accuracy (TAR, %)
For different algorithms (methods)
Memory Characteristics
* – the amount of memory consumed does not depend on the number of the Recognizer objects created by this method
Performance parameters
For Desktop
For Mobile
Note: Google Pixel 3 was used for the speed test.
Accuracy of Face Attributes Detection
Ask an Expert
3DiVi computer vision experts are always ready to help you to find a solution matching your requirements
Ask an Expert
Just fill in the form below and we will contact you shortly to answer your questions.