---
Source: https://docs.microblink.com/platform/capabilities/selfie-face-match
Title: Selfie, Liveness & Face Match
Description: Verify user presence and match live selfies against ID document photos
---

# Selfie, Liveness & Face Match

:::tip[Availability]
Available in SDK v1.0+
:::

The Selfie, Liveness & Face Match capability verifies three key aspects of a verification attempt. 
It ensures that the user is a real, physically present person at the time of capture (selfie liveness), that the capture process itself is secure and has not been tampered with or manipulated in transit (capture liveness), and that the selfie matches the face extracted from a previously scanned identity document (face match).

This capability relies entirely on passive analysis, meaning the user is not required to perform any explicit actions such as blinking, turning their head, or following on-screen prompts. 

This capability produces three independent outputs: a face match score (0 - 100), a selfie liveness result, and a capture liveness outcome (pass/fail).

These signals can be evaluated independently or combined to define rules and outcomes.

This capability must come after a [Scan ID](scan-id.md) or [Scan & Verify ID](scan-verify-id.md) step, since it compares the selfie against the face image extracted from the document.

## How it works

Once the selfie is captured, the system processes the data to perform three distinct analyses:

### Selfie liveness

Selfie liveness verifies that the subject in the capture is a real, live person physically present in front of the device, and not a spoof such as a printed photo, a screen replay (video or image), or a mask or similar artifact. 
This protects against presentation attacks.

### Capture liveness

Capture liveness ensures that the capture process itself is trustworthy and that the data has not been tampered with or artificially injected. 
It protects against attack vectors such as injection attacks, man-in-the-middle attacks, and the use of untrusted or compromised devices.

### Face match

Face match determines whether the face in the selfie corresponds to the face extracted from the identity document by comparing biometric features.

The system detects key facial landmarks (such as the eyes, nose, mouth, and jawline) and analyzes the spatial relationships and distances between them to generate a mathematical representation of each face. 
These representations are then compared to assess their similarity and determine the likelihood that both images belong to the same person.

## Configuration

You can configure the **face analysis tolerance**, which determines how well the selfie must match the ID photo.
There are three levels:

- **Soft**: tolerates more variation between the selfie and the ID photo; lower false rejection rate but higher false acceptance rate
- **Regular**: a balanced middle ground; recommended for most use cases
- **Hard**: less tolerant of differences; lower false acceptance rate but higher false rejection rate

The tolerance level affects the face match score returned in the response.
The same underlying faces at the same threshold will yield a higher score at "soft" and a lower score at "hard."
This means that if you set the same numeric threshold in your rules, a "soft" calibration will accept more borderline matches than "hard."

## Rules

Rules can be configured along three independent dimensions:

- **Face match score**: the probability (50 to 100) that the person in the selfie is the same person shown on the ID document.
  If this score falls below the threshold you specify, the user is rejected or sent to manual review.

- **Liveness score**: the probability (50 to 100) that the person in the selfie is physically present.
  If this score falls below the threshold you specify, the user is rejected or sent to manual review.

- **Capture integrity**: whether or not the selfie capture has been detected as having been tampered with.
  For example, if an injection attack was detected, then the workflow will end up in manual review, or will be rejected, based on what you set here.

Because the face match score is influenced by the tolerance calibration, the same numeric threshold produces different effective strictness depending on which tolerance level you selected.
Choose your threshold after deciding on the tolerance level, and test the combination against your user population to find the right balance.


Last updated on Jun 11, 2026