Skip to content

Face SDK Introduction

Regula Face SDK is a cross-platform biometric verification solution for a digital identity verification process. The SDK enables convenient and reliable face capture on the client side (mobile, web, and desktop) and further processing on the client or server side.

This section introduces the Face SDK essential features: Face Detection, Face Comparison (aka Match), Face Identification (aka Search), and Liveness Assessment.

Face Detection

Face Detection can analyze images, recognize faces in them, and return cropped and aligned portraits of the detected people. Face Detection includes the following features:

Face attributes evaluation estimates the age range of a person; checks whether the eyes are occluded, closed, or open; detects the facial expression or a smile; shows if there are glasses, sunglasses, head coverage, medical mask, etc.

Face image quality assessment is a fast and handy way to check whether a portrait meets certain standards, for example, ICAO, Schengen visa, USA visa.

For facial image assessment, you can use one of the predefined scenarios or create your set of characteristics and attributes checks and save it as a custom scenario.

Face Comparison (1:1)

Face Comparison is a convenient and powerful way to match two or more portraits in the same image or in different ones and find out whether the face belongs to the same person, how similar the detected faces are.

The comparison can be performed on the client side without using a web server, see the Mobile section for details.

Face Identification (1:N)

The Face Identification module lets you match a face in an image against a database of faces. You can create and manage such a database with identities, upload photos, and associate them with names. When you show the system a photo, it can search for a match in the database.

Liveness Assessment

Is it a real human being looking at the camera? Not a mannequin or a 3D image? The Liveness verification module is created to check whether the biometric information source accessing the camera is a physically present live person.

In addition to enhancing security measures against spoofing attacks, deepfakes, and fraud, the liveness verification module offers an extra capability. By leveraging advanced AI algorithms, it can also provide an estimated age of the person with an accuracy of approximately +/-3 years.


The liveness verification can be performed only using a camera with a resolution of HD 1024x720 or higher.

Liveness detection can be performed in two modes: active and passive.

The active mode requires users to turn their head during the session. This guarantees highly accurate liveness detection.

The passive liveness check simply involves taking a selfie. This approach offers improved user experience, however, the accuracy of the active liveness detection result will be higher.

Whether to use passive or active liveness check is specified in the request code. Switching between the two options doesn't require any modifications on the backend meaning that on the same backend, both active and passive procedures can be performed.