Face Similarity

Overview

Our Face Similarity API analyzes the similarity between two faces using a combination of our visual similarity model and our face detection model. This API accepts two images as input: a reference and target image. Hive then returns a "similarity score" that is correlated to how similar the face in the reference image is to the face in the target image. If there are multiple faces in the reference image, only the largest face will be analyzed. A bounding box and similarity score will be returned for each face in the query image. If there are no faces detected in either image, then the API call will fail.

Request Format

curl --location --request POST 'https://api.thehive.ai/api/v2/task/sync' \
--header 'Authorization: Token <your_token>' \
--form 'urls="[\"http://example_url_1.jpg\",\"http://example_url_2.jpg\"]"'

Response

The output of our Face Similarity API contains a geometric description of the detected face in the target image as well as a similarity score to indicate how similar that face is to the face in the reference image. To see an annotated example of an API response object for this model, you can visit our API reference page.