Compare 1:1 | Live
Service for Comparing Two Images and Performing a Liveness Detection Process on One of Them.
Last updated
Service for Comparing Two Images and Performing a Liveness Detection Process on One of Them.
Last updated
POST - https://api.verifik.co/v2/face-recognition/compare-live
The Compare with Liveness Detection API is designed to perform liveness detection on an image provided in the "probe" parameter. Once liveness detection is performed, it proceeds to perform a 1:1 comparison with the image sent in the "gallery" parameter. This API helps verify the authenticity of a face by checking for signs of life, ensuring that the face in the "probe" image comes from a real person and not a static image or video.
You can use the liveness score to determine whether the face in the probe image is live (above a specified threshold) or not. This API is valuable for improving security and ensuring that only live faces are allowed access to systems or services.
If you have read all the guides in this documentation, you may have noticed that these services perform very similar processes, so what sets them apart?
The differentiating factor between these services is how the comparison process is performed:
Face Verify: Performs the comparison between an image and a person already created within a collection.
Compare 1:1: Performs the comparison between two images. Unlike Face Verify, there is no restriction on where these images come from, making this service more versatile in how it performs the 1:1 comparison.
Compare 1:1 Live: Same operation as the Compare 1:1 service, with the added value of conducting a Liveness check on one of the supplied images.
Headers
Name | Value |
---|---|
Body
Name | Type | Description |
---|---|---|
Body Example
Response
Content-Type
application/json
Authorization
Bearer <token>
os
string
OS from where you are doing the operation. [DESKTOP, IOS, ANDROID]
probe
string
Face encoded in base64
gallery
Array
Array of images to compare with the face inside probe.
search_mode
string
search mode, it could be FAST, ACCURATE.
liveness_min_score
number
Percentage for the minimum value of the liveness test [ min 0.52 - max 1]