3D FACE AUTHENTICATION
FOR CUSTOMER IDENTITY, POS, & PAYMENTS
Leave credit cards, loyalty cards, and barcodes at home and still complete in-person transactions with the highest level of consumer privacy.
3DWallet’s in-motion, off-axis recognition works with real-world lighting for a faster, more accurate user experience. It’s designed to succeed where other solutions consistently fail:
Privacy — customers control face biometrics stored on their devices instead of a central database
Alignment — off-axis flexibility plus fast recognition means faces don’t need to be perfectly aligned
Appearance changes — patented auto-learning adjusts for makeup, beards, glasses, & face occlusions
Skin tones — no issues detecting various skin tones & races
what makes 3DWallet better?
3DWallet’s recognition works when and where your customers expect, even when other solutions don’t. After a customer opts in, they will be transparently recognized without having to carefully position their face in front of a camera. 3DWallet works on most Bluetooth-enabled smartphones and on many POS platforms with a light footprint.
| 3DWallet | Others | |
|---|---|---|
| Works in-motion without careful face alignment | ✔ | ✘ |
| Works for all skin tones and races | ✔ | ✘ |
| Works when appearance changes (makeup, beards, glasses) | ✔ | ✘ |
| Works in all lighting, including strong back light & side light | ✔ | ✘ |
| Immune to spoofing with masks, photos, and videos | ✔ | ✘ |
| Recognition and anti-spoofing happen simultaneously | ✔ | ✘ |
| Patented simultaneous multi-factor security | ✔ | ✘ |
| Uses 2X more data for the best True 3D authentication | ✔ | ✘ |
3dwallet
UNIQUE TECHNOLOGIES
Continuous Edge Auto Learning
Secure and fast customer-controlled Edge Recognition compatible with most Bluetooth enabled smartphones
Continuous Security
True 3D recognition + simultaneous 2D recognition
3D Anti-Spoofing
Simultaneous Multi-Factor Security
SPECIFICATIONS
False Rejection Rate: Approaches 0% with 1-3 uses
FAR: Better than 1 in 1,000,000 without occlusions
Supports 1 to Many configurations (1:N)
With beards and occlusions:
1:1 FAR of better than 1 in 1,000,000 with beards typical in the Middle East/Europe. 1:N better than 1 in 800,000
With both a beard and normal-sized sunglasses, we would expect a 1:1 FAR of better than 1 in 250,000. 1:N better than 1 in 200,000.
1:1 FAR of better than 1 in 1,000,000 with makeup. 1:N better than 1 in 800,000/
Yaw and roll: up to +/- 45 degrees supported for off-axis recognition (optional +/- 60 degrees)
Speed: Typically less than 70ms (Detection, Extraction, Template Creation, & Matching)
1,0000 users on an i7, 16GB RAM, and SSD
Larger databases can be supported with similar performance and suitable hardware
On-device or cloud recognition
Embedded Linux, Windows and Android Support
Typical memory requirements: 35MB ROM, 60MB RAM
Works with the leading low-cost 3D cameras including:
Time of Flight (ToF)
Structured Light (SL)
Active Stereo (AS)