You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
You can use computed embedding to perform recognition and verification. To obtain embedding, you can
841
+
use [calculator plugin](https://github.com/exadel-inc/CompreFace/blob/EFRS-1333_ability_to_send_embeddings_instead_of_the_image_for_recognition/docs/Face-services-and-plugins.md#face-plugins)
842
+
in each Face service.
843
+
The base rule is to use `Content-Type: application/json` header and send JSON in the body.
844
+
845
+
### Recognize Faces from a Given Image, Embedding
846
+
The service is used to determine similarities between input embeddings and embeddings within the Face Collection. An example:
847
+
848
+
```shell
849
+
curl -X POST "http://localhost:8000/api/v1/recognition/embeddings/recognize?prediction_count=<prediction_count>" \
850
+
-H "Content-Type: application/json" \
851
+
-H "x-api-key: <service_api_key>" \
852
+
-d {"embeddings": [[<array_of_embedding>], ...]}
853
+
```
854
+
855
+
| Element | Description | Type | Required | Notes |
| x-api-key | header | string | required | an api key of the Face recognition service, created by the user |
859
+
| embeddings | body | array | required | an input embeddings. The length depends on the model (e.g. 512 or 128) |
860
+
| prediction_count | param | integer | optional | the maximum number of subject predictions per embedding. It returns the most similar subjects. Default value: 1 |
0 commit comments