Liveness detection
Active and passive liveness checks, iBeta-certified at PAD Level 1 and Level 2 under ISO/IEC 30107-3.
Regula Face SDK is a biometric verification solution for face ID verification, liveness detection, face matching, and face identification.
Regula Face SDK confirms the real person behind every interaction with secure facial biometrics.
Prevent identity fraud with advanced biometric verification and liveness.
Match faces across IDs, selfies, and databases with fast, accurate comparison.
Deploy high-performance verification across cloud and enterprise environments.
PAD Level 1&2 ISO 30107-3
Top 3 FRVT age assurance
Privacy by default
ISO 9001
BSI TR-03105 Teil 5.1
BSI TR-03105 Teil 5.2
Biometric fraud attempts are growing in volume and sophistication. Regula Face SDK is designed to detect and reject the full spectrum of presentation attacks:
static images held up to the camera
video played from a phone or tablet
synthetic video fed directly into the camera stream
faces created or swapped using generative models
physical forgeries designed to fool depth sensors
Skip integration headaches and cut development time. With ready-to-run Linux, Windows, and Docker packages, clear docs, and code samples, you can launch faster—whether building a new app or enhancing an existing one.
Use our ready-made samples or bring your own. Run liveness checks, test face matching, see quality scores and understand exactly how the technology works.
The strongest proof comes from the people using the product. Explore how Regula performs across the metrics identity verification teams care about.
What is a biometric verification system?
A biometric verification system confirms a person's identity using unique physical traits — most commonly facial features, fingerprints, or iris patterns. In the context of face recognition, it compares a live biometric sample (a selfie or video frame) against a stored reference image to confirm the person is who they claim to be.
What is the difference between face verification and face identification?
Face verification (1:1) checks whether two images show the same person — for example, a selfie versus a passport portrait. Face identification (1:N) searches a database to find who a person is, or to check whether they appear in a watchlist. Regula Face SDK supports both modes.
What is liveness detection and why does it matter?
Liveness detection determines whether the biometric sample comes from a live person present in front of the camera — not a photo, video, or mask. Without liveness detection, any face recognition system can be bypassed with a printed photo. It is a mandatory component of any compliant biometric identity verification flow.
What is the difference between active and passive liveness detection?
Active liveness detection asks the user to perform a specific action — blinking, turning their head, or following a visual prompt. Passive liveness detection works silently in the background, with no user action required. Passive detection reduces friction in the user experience while maintaining a strong security level. Regula Face SDK supports both, and the mode can be selected based on your risk model.
What are the most common types of biometric authentication?
The most widely deployed types are face recognition, fingerprint scanning, iris recognition, and voice recognition. Face-based biometric authentication dominates remote identity verification because it works through a standard front-facing camera — no additional hardware required.
Can facial recognition technology be used for identity verification in online services?
Yes. A facial recognition SDK integrates into mobile apps and websites to verify users at account opening, login, or payment confirmation. The user takes a selfie; the SDK checks liveness, assesses image quality, and matches the face to the reference on file — all in a few seconds.
How does Regula Face SDK protect against deepfake attacks?
The liveness detection engine in Regula Face SDK is trained on a dataset that includes AI-generated and deepfake attack samples. It analyzes texture, micro-movement patterns, and reflection artifacts that are absent in synthetic faces. The model is updated continuously as new attack techniques emerge.