Face detection

Face detection is currently at the Preview stage.

This section describes how the face detection feature works in the service.

This feature lets you find human faces in an image. For example, you can use it to mark people in a photo or find all photos with portraits.

Request format

In the feature type, specify FACE_DETECTION:

{
    "folderId": "b1gvmob95yysaplct532",
    "analyze_specs": [{
        "content": "iVBORw0KGgo...",
        "features": [{
            "type": "FACE_DETECTION"
        }]
    }]
}

Service response

The service searches for human faces in the image and marks them with rectangles. In the response, the service returns the coordinates of the rectangles for all detected faces:

If two faces are adjacent, the rectangles may intersect.

The coordinates of a rectangle are calculated from the upper-left corner and specified counterclockwise:

1←4
↓ ↑
2→3

Sample response with the coordinates of the detected face:

{
  "results": [{
    "results": [{
      "faceDetection": {
        "faces": [{
          "boundingBox": {
            "vertices": [{
                "x": "410",
                "y": "404"
              },
              {
                "x": "410",
                "y": "467"
              },
              {
                "x": "559",
                "y": "467"
              },
              {
                "x": "559",
                "y": "404"
              }
            ]
          }
        }]
      }
    }]
  }]
}

Image requirements

An image in a request must meet the following requirements:

• Supported file formats: JPEG, PNG, PDF.

  The MIME-type of the file is specified in the mime_type property. The default is image.

• Maximum file size: 1 MB.

• Image size should not exceed 20 MP (length x width).

What's next

• Try detecting faces in an image
• See how to handle errors