Liveness Check

1.0 Authorization

This API requires an access token. To get more info on how to generate this access token, click on Generating Access Token

2.0 Base Url

All requests to the Liveness check API must be done using the web API URL below.

Test Environment: https://api-devapps.vfdbank.systems/vtech-wallet/api/v2/wallet2

Live Environment: https://api-apps.vfdbank.systems/vtech-wallet/api/v2/wallet2 in the live environment

3.0 How To Use The Liveness Check API

1. The developer should call the LIVENESS CHECK api to get the liveness probability of an image

3.1 Liveness Check

API Context : /checkliveness

This endpoint returns the liveness probability of an image.

API METHOD: POST

REQUEST HEADERS

Key	Value
AccessToken	{{token}}

Sample Request

{
    "base64Image":"/9j/4AAQSkZJRgABAQEASABIAAD/4S/SRXhpZgAATU0AKgAAAAgACwALAAIAAAAmAAAIngESA....."
}

Request Field Description

Field	Description	Status
base64Image	Image to evaluate, encoded in base64	Mandatory

Sample Response

{
    "status": "00",
    "message": "Successful",
    "data": {
        "probability": "0.13133287",
        "score": "-1.8892249",
        "quality": "0.30681747"
    }
}

Response Fields Description

Field	Description
probability	The main response of the system, and it should always be used to make a liveness check decision. The image is accepted as "live" when probability is greater than 0.5. Probability value range is from 0 to 1
score	This can be used for BPCER / APCER tuning and is provided mostly for calibration purposes. The range of score value is unbound.
quality	This is a mark of image "goodness". High values indicate that the image is quality enough for liveness checking.

4.0 Image Requirements

To run the processing, the Liveness Check API requires an image to match the set of conditions below.

4.1 Image Format

The Liveness Check API supports JPEG, PNG, and BMP in Base64 formats. Lossless formats are preferred, as lossy compression can have a negative effect on accuracy. If you use lossy formats, make sure the compression is at a minimal level. For example, for JPEG, 70 is the lowest practical compression level.

4.2 Image Resolution

The Liveness Check API processes the area around the face, so the optimal resolution will depend on the image composition. Assuming a portrait orientation, with the face centered and taking at least 1/4 of the image area, the recommended image resolution range is from 600x800 to 960x1280.

4.3 Image Composition

• There should only be one main face on the image. It should be fully visible within a frame and fully open without any occlusions. No crop is allowed. Small faces in the background are not taken into account.
• The minimum size of a face box that can be processed is 150x150 pixels.
• The padding between the face box and the image's borders should be at least 15 pixels.
• The distance between the pupils on the face should be at least 50 pixels.
• The out-of-plane rotation angle (face pitch and yaw) should be no more than ±30 degrees.

Images that do not match these conditions will be rejected. Other conditions can affect accuracy:

• Motion blur effect can significantly increase BPCER (the rate of errors classifying a genuine person as a spoof).
• Texture filtering can significantly increase APCER (the rate of errors allowing impostors through).
• Spotlights on the faces and nearest surroundings can significantly increase BPCER.
• Ill-lighted environments and colored light can significantly increase BPCER.
• Fish-eye lenses are not supported.
• Sunglasses may be confusing.