Playground biometrics demo BioID home page

RESTful JSON API LivenessDetection

Performs liveness detection on one or two live images. Depending on the number of live images and the tags provided in the call, different versions of our liveness detection will be executed:

One image: Only passive liveness detection will be performed. Due to the limitation to a single image, only the texture based liveness detection can be used to make a decision.

Two images: Passive and active liveness detection will be performed. Beside of the texture based liveness detection on each of the provided images a motion based 3D detection on each two consecutive images is executed. All decisions must indicate a live person to finally declare the entire call as live.

Two images with tagged second image: Passive and active liveness detection will be performed. Additionally a challenge-response mechanism is applied. As we have a motion direction calculated for the face found in the second image, we can check whether this is the same direction as demanded by the tags, i.e. whether the head moved up, down, left or right as requested. Also refer to the Liveness Detection Modes.

Request

POST /api/v1/livenessdetection

Request Body

Content type: application/json

{
  "liveImages": [
    {
      "image": "string",
      "tags": [
        "string"
      ]
    }
  ]
}

The LivenessDetection request object has a single field:

liveImages
A list of one or two live images. If a second image is provided, the tags of these images can optionally be used for challenge-response. The image data itself needs to be base64 encoded of course.

Request Headers

This API requires a valid JWT in the Authorization request header and accepts an optional reference number.

Authorization Required Bearer authentication. Please refer to BWS API Authentication for a description of how to provide a valid JWT here.
Reference-Number Optional, client specific reference number, which will be added to the BWS bookkeeping as well as to the response header. You typically use this reference to link the resulting BWS bookkeeping entries with your logs.

Response

Response Body

Content type: application/json

{
  "status": "SUCCEEDED",
  "errors": [
    {
      "errorCode": "string",
      "message": "string"
    }
  ],
  "imageProperties": [
    {
      "rotated": 0,
      "faces": [
        {
          "leftEye": {
            "x": 0,
            "y": 0
          },
          "rightEye": {
            "x": 0,
            "y": 0
          },
          "textureLivenessScore": 0,
          "motionLivenessScore": 0,
          "movementDirection": 0
        }
      ],
      "qualityScore": 0,
      "qualityAssessments": [
        {
          "check": "string",
          "score": 0,
          "message": "string"
        }
      ],
      "frameNumber": 0
    }
  ],
  "live": true,
  "livenessScore": 0
}

On success the API returns a LivenessDetection response object with the fields as follows:

status
The status of the BWS job that processed the request. The following fields are typically only set, when the job has succeeded.
errors
A list of errors that might have occurred while the request has been processed.
imageProperties
The calculated image properties for each of the provided images in the given order.
live
The liveness decision made by BWS. If this field is set to true, the provided images are supposed to be recorded from a live person. No errors are reported in this case. When this field is set to false, there is at least one error reported that explains, why the provided images are not supposed to be recorded from a live person.
livenessScore

An informative liveness score (a value between 0.0 and 1.0) that reflects the confidence level of the live decision. The higher the score, the more likely the person is a live person. If this score is exactly 0.0, it has not been calculated and an error has been be reported.

The liveness score is the average of all calculated passive and active liveness detection scores. For the liveness decision, the individual passive and active liveness detection scores are used.

BWS Errors

In case that the live field is set to false, at least one of the following errors is reported in the errors field:

FaceNotFound
No suitable face was found in at least one of the provided images.
MultipleFacesFound
More than one face has been found in at least one of the provided images.
ThumbnailExtractionFailed
None of the found faces could be extracted, typically because they are too close to the edge. There should have been reported one or more FullyVisibleFace quality check results.
RejectedByPassiveLiveDetection
At least one of the live images seem not to be recorded from a live person.
RejectedByActiveLiveDetection
The 3D detector observed some unnatural motion.
RejectedByChallengeResponse
At least one of the head-movement challenge-response criteria (as provided in the tags of the second image) was not fulfilled.

HTTP Status Codes

The call returns one of the standard HTTP status codes, e.g.:

200 (OK)
The response body contains the LivenessDetection response object as described above.
400 (Bad Request)
The call failed, typically due to an invalid argument. The response body contains a JSON object with the reported gRPC error code and message.
401 (Unauthorized)
The request does not have valid authentication credentials for the operation.
408 (Request Timeout)
Client application cancelled the request.
500 (Internal Server Error)
Server experienced some unexpected behaviour.
503 (Service Unavailable)
The service is currently unavailable. This is a most likely a transient condition and may be corrected by retrying with a backoff.

Response Headers

All successful BWS calls return a response header containing additional information about the request:

jobid The Job-ID (a GUID) that has been assigned to this BWS call.
bws-version The version of the BWS gRPC service.
reference-number An optional reference number as provided in the request header.
date The timestamp when the request has been received at the server.
... Other headers that might have been added by the server (NGINX, Kestrel, ...) that was handling the request.

Example:

Here is a short example of how to call into the LivenessDetection RESTful JSON API using live images loaded from files.

Please refer to BWS API Authentication for a description of the methods CreateAuthenticatedClient and GenerateToken.

This sample code makes use of some C# JSON data transfer objects, which you can find in the BwsJsonDto.cs source file.

using HttpClient httpClient = CreateAuthenticatedClient(new Uri(options.Host), GenerateToken(options.ClientId, options.Key));
var request = new LivenessDetectionRequest();
foreach (string file in options.Files)
{
    request.LiveImages.Add(new ImageData { Image = Convert.ToBase64String(File.ReadAllBytes(file)) });
}
var response = await httpClient.PostAsync("/api/v1/livenessdetection", JsonContent.Create(request));
if (response.IsSuccessStatusCode)
{
    var responseContent = await response.Content.ReadFromJsonAsync<LivenessDetectionResponse>();
    // ...
    Console.WriteLine($"This was live: {responseContent.Live} (confidence: {responseContent.LivenessScore})");
}
else
{
    Console.WriteLine($"Server response: {response.StatusCode}");
}
todo
todo