FACE SDK

Top-ranked facial recognition for server, mobile and embedded solutions requiring image and streaming video processing

World class algorithm
Face recognition algorithm developed by 3DiVi is top-ranked in NIST FRVT
Open sourced samples
Quickly build web, mobile, desktop or server applications with open sourced samples
Liveness
Passive and active methods against face spoofing with photo or video (presentation attack). 3D, RGB/IR, RGB cameras are supported
Edge processing of streaming video
Set of algorithms optimized for on-device processing of real time video with no cloud computing required

FEATURES

Masked Faces
Reliably detect masks and masked faces
Streaming Video Processing
Face detection, tracking and matching from multiple video streams in real time
Liveness
Passive (RGB, IR, 3D) or active liveness detection for mobile or web application
Face Landmarks
Detect size, pitch, roll, yaw of a face along with 3D mesh and 300 facial landmarks
Face Analytics
Gender, age and emotions detection
Automatic Best Shot
Capture best shot from real time video based on face image quality parameters

FACE RECOGNITION DEMO APP

Evaluate the functionality and quality of the facial recognition algorithm by 3DiVi. Good for quick testing with your smartphone.

3DiVi Face SDK 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.

VIEW TECHNICAL SPECS

Case Studies

Learn how 3DiVi Face SDK is used in projects around the world

Omnigo
Search for scammers and other unwanted individuals by blacklisting using the face recognition module in the Las Vegas casinos.
Learn More
Papillon Access Control System
Access Control System with 3D Face Terminals.
Learn More
Eocortex
Adding facial recognition to a Video Management System
Learn More

VIEW CASES

DEVELOPER DOCUMENTATION

VIEW DOCUMENTATION

Testimonials

3DiVi did everything we need to complement our biometric solution. Integrating their technology with ours was very quick, simple and cost efficient. We highly recommend them as a lead partner in face matching.
Ahmad H. Shar'ab
Mobile-Technologies, Director of Sales
I have concluded 3DiVi Face SDK testing with one of our biggest customers and I am happy to say that the results are really good. Recognition works 6 times better compared to the solution of another vendor that we used earlier.
Soren Frederiksen
Omnigo, Vice President
3DiVi face recognition solution exceeded our expectations for performance (accuracy, search time, computational efficiency), positively differentiating us against competition and thus helping us to win a big tender for a nationwide security project.
Igor Greshnev
Papillon, CTO
At first, we were afraid that our new face based access control system would cause lines at turnstiles during rush hours, but this did not happen, 3DiVi algorithm works very quickly.
Andrey Dzygar
Facepass, CEO

Earn more with 3DiVi

Become a partner and accelerate time to market of your face recognition solution with our premium support via chat. As a partner get free SDK licenses and discounts up to 30%.

BECOME A PARTNER

GET STARTED

GET STARTED WITH 3DiVi FACE SDK

Fill in the form and we will get in touch with you shortly