Person Detection

The Person Detection API allows you to detect faces and people in images. It follows the general Ximilar API rules described in First steps.

Endpoints

The service provides two endpoints:

https://api.ximilar.com/identity/v2/face      (for detecting faces)
https://api.ximilar.com/identity/v2/person    (for detecting people)

POST/v2/face

Face Detection

Quickstart

Given a list of image records, this method detects all faces in the images. For each face, it returns a bounding box and a confidence score.

Required attributes

  • Name
    records
    Type
    dict
    Max
    Maximum:10
    Description

    A batch of JSON records (max 10). Each record represents a single image, defined by _url or _base64.

Returns

HTTP error code 2XX, if the method was OK, and other HTTP error code, if the method failed. The response body is a JSON object (map) with the following fields:

  • Name
    records
    Type
    dict
    Description

    JSON array with the input records, each record enriched by field _objects containing detected faces with bounding boxes and probabilities.

  • Name
    status
    Type
    dict
    Description

    A JSON map/dictionary with a status of the method processing. It contains these subfields: code (numeric code of the operation status; it follows the concept of HTTP status codes) and text (text describing the status code).

Request

POST
/v2/face
curl https://api.ximilar.com/identity/v2/face -H "Content-Type: application/json" -H "Authorization: Token __API_TOKEN__" -d '{
  "records": [
    {
      "_url": "__PATH_TO_IMAGE_URL__"
    }
  ]
}'

Response

{
  "records": [
    {
      "_url": "__SOME_URL__",
      "_status": {
        "code": 200,
        "text": "OK"
      },
      "_width": 2736,
      "_height": 3648,
      "_objects": [
        {
          "name": "face",
          "bound_box": [
            2103,
            467,
            2694,
            883
          ],
          "prob": 0.9890862107276917
        },
        {
          "name": "face",
          "bound_box": [
            100,
            100,
            500,
            883
          ],
          "prob": 0.9890862107276917
        }
      ]
    }
  ]
}

POST/v2/person

Person Detection

Quickstart

Given a list of image records, this method returns detected people in the images. For each image it predicts positions of people with bounding boxes and confidence scores.

Required attributes

  • Name
    records
    Type
    dict
    Max
    Maximum:10
    Description

    A batch of JSON records (max 10). Each record represents a single image, defined by _url or _base64.

Returns

HTTP error code 2XX, if the method was OK, and other HTTP error code, if the method failed. The response body is a JSON object (map) with the following fields:

  • Name
    records
    Type
    dict
    Description

    JSON array with the input records, each record enriched by field _objects containing detected people with bounding boxes and probabilities.

  • Name
    status
    Type
    dict
    Description

    A JSON map/dictionary with a status of the method processing. It contains these subfields: code (numeric code of the operation status; it follows the concept of HTTP status codes) and text (text describing the status code).

Request

POST
/v2/person
curl https://api.ximilar.com/identity/v2/person -H "Content-Type: application/json" -H "Authorization: Token __API_TOKEN__" -d '{
  "records": [
    {
      "_url": "__PATH_TO_IMAGE_URL__"
    }
  ]
}'

Response

{
  "records": [
    {
      "_url": "__SOME_URL__",
      "_status": {
        "code": 200,
        "text": "OK"
      },
      "_width": 2736,
      "_height": 3648,
      "_objects": [
        {
          "name": "person",
          "bound_box": [
            2103,
            467,
            2694,
            883
          ],
          "prob": 0.9890862107276917
        },
        {
          "name": "person",
          "bound_box": [
            100,
            100,
            500,
            883
          ],
          "prob": 0.9890862107276917
        }
      ]
    }
  ]
}

Was this page helpful?