Document Liveness
Passive liveness detection enhances security for person and/or document authentication solutions. It adds detection and alerting capabilities when a printed photo or digital image or a screenshot from monitor/TV is presented for identity authentication or physical access control workflows.
Features
- Works with a single image of the identity document
- Independent of document type
- Helps prevent attacks that humans cannot detect
- Reduces the time needed for human visual review and inspection
- Requires no special capture-side software
- Collects no OCR or identity data
Specifications
- Image orientation: portrait or landscape
- Minimum image size: 1080p
- Supported documents: passports, ID cards, and driver’s licenses from all over the world
- Allowed compression: maximum JPEG 70; prefer JPEG 90 or 100
API call
To perform a document liveness check.
This API currently supports basic authentication. All endpoints require an Authentication header in the following form:
Authorization: 'Basic ' + Base64.encode(username + ':' + password)
Send a HTTP POST request to:
/api/v1/document/liveness
The following parameters are used for requests and responses:
| Parameter | Direction | Description |
|---|---|---|
| sessionId | request | unique, short-lived code to be generated by the client to track specific sessions |
| frontSideImageBase | request | front side document photo, Base64 format or URL link to it |
| backSideImageBase | request | back side document photo, Base64 format or URL link to it |
| sessionId | response | unique, short-lived code to be generated by the client to track specific sessions. Same as in request |
| score | response | score of the сheck. A higher score indicates a higher liveness level, with the default threshold set at 0.25. We recommend sending all scores in the range of 0.25 to 0.5 for manual review. |
| hasError | response | boolean parameter - true - verification process ended up with some error; false - no errors |
| error | response | error message in case of hasError set to true, informing about type of error: DOCUMENT_TOO_SMALL, DOCUMENT_CROPPED etc. |
Request:
{
"documentImageBase": "data:image/png;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAIBAQEBAQIBAQECAgICAgQDAgICAgUEBAMEBgUGBgYFBgYGBwkIBgcJBwYGCAsICQoKCgoKBggLDAsKDAkKCgr
...
+SSyDCtmmrGoXzc8AcrURjKEjNOK6DII0ZyJFVgepUdKv26X0WVhuGcMPlBP3RVeFluDiNdvY8VbEUnO2UjaOTnrXoUZc8dTOdSUZEotL7A/eD/AL6oqVLJCoJmk6f3qKv2Rz+0if/Z",
"sessionId": "bbbf9002-c3a2-4308-b103-d80b9f5a2b84"
}
Response - passive liveness passed
{
"sessionId": "bbbf9002-c3a2-4308-b103-d80b9f5a2b84",
"score": 0.9997104,
"hasError": false
}
Response - passive liveness not passed:
{
"sessionId": "bbbf9002-c3a2-4308-b103-d80b9f5a2b84",
"score": 0.002324,
"hasError": false
}
Response - error
{
"sessionId": "bbbf9002-c3a2-4308-b103-d80b9f5a2b84",
"hasError": true,
"error": "DOCUMENT_NOT_FOUND"
}
List of errors
| Error | Meaning | Description |
|---|---|---|
| DOCUMENT_TOO_CLOSE_TO_CAMERA | Document is too close to the camera | |
| DOCUMENT_TOO_CLOSE_TO_BORDER | Document is too close to the image border | |
| DOCUMENT_PHOTO_NOT_FOUND | Portrait photo not detected on the document (valid for a front side only) | |
| DOCUMENT_CROPPED | Document is cropped (part of the document is not present in the image) | |
| DOCUMENT_NOT_FOUND | Document is not detected in the image | |
| TOO_MANY_DOCUMENTS | Too many documents were detected in the image | |
| DOCUMENT_TOO_SMALL | Document size in the image is too small |