# Detect faces in images

Robot: `/image/facedetect`

🤖/image/facedetect detects faces in images and can return either their coordinates or the faces themselves as new images.

You can specify padding around the extracted faces, tailoring the output for your needs.

This <dfn>Robot</dfn> works well together with [🤖/image/resize](/docs/robots/image-resize.md) to bring the full power of resized and optimized images to your website or app.

<div class="alert alert-note"><p><strong>How to improve the accuracy:</strong></p>
<ul>
<li>Ensure that your pictures have the correct orientation. This <dfn>Robot</dfn> achieves the best performance when the faces in the image are oriented upright and not rotated.</li>
<li>If the <dfn>Robot</dfn> detects objects other than a face, you can use <code>"faces": "max-confidence"</code> within your <dfn>Template</dfn> for selecting only the detection with the highest confidence.</li>
<li>The number of returned detections can also be controlled using the <code>min_confidence</code> parameter. Increasing its value will yield less results but each with a higher confidence. Decreasing the value, on the other hand, will provide more results but may also include objects other than faces.</li>
</ul></div>

Stage: ga

## Usage example

Detect all faces in uploaded images, crop them, and save as separate images:

```json
{
  "steps": {
    "faces_detected": {
      "robot": "/image/facedetect",
      "use": ":original",
      "crop": true,
      "faces": "each",
      "crop_padding": "10px"
    }
  }
}
```

## Parameters

* `interpolate`: Controls whether Assembly Variables are interpolated for individual instruction fields.

  By default, most Robot instruction fields interpolate Assembly Variables. Set this to `false` to treat every instruction field as literal text, or set an individual field path to `false` to treat only that field as literal text. For Robot-specific fields that are literal by default, set this to `true` or set that field path to `true` to opt back into interpolation.

  Use field names such as `path`, or dotted paths such as `ffmpeg.vf` for nested objects.

* `output_meta`: Allows you to specify a set of metadata that is more expensive on CPU power to calculate, and thus is disabled by default to keep your Assemblies processing fast.

  For images, you can add `"has_transparency": true` in this object to extract if the image contains transparent parts and `"dominant_colors": true` to extract an array of hexadecimal color codes from the image.

  For images, you can also add `"blurhash": true` to extract a [BlurHash](https://blurha.sh) string — a compact representation of a placeholder for the image, useful for showing a blurred preview while the full image loads.

  For videos, you can add the `"colorspace": true` parameter to extract the colorspace of the output video.

  For videos, you can also add `"interlaced": true` to detect whether the video is interlaced. This combines the cheap ffprobe `field_order` flag with a bounded `idet` sampling pass over the first frames of the source, exposing `interlaced`, `field_order`, and a diagnostic `interlace_detection` object under `file.meta`. This is computationally expensive and billed accordingly.

  For audio, you can add `"mean_volume": true` to get a single value representing the mean average volume of the audio file.

  You can also set this to `false` to skip metadata extraction and speed up transcoding.

* `user_meta`: Adds custom metadata to each file emitted by this Robot without modifying the file’s contents.

  The values are merged with any existing `user_meta` carried by the input file. If both objects contain the same key, this Robot’s value takes precedence. Assembly Variables are supported, for example `{ "internal_file_id": "${file.id}" }`.

* `result`: Whether the results of this Step should be present in the Assembly Status JSON

* `queue`: Setting the queue to 'batch', manually downgrades the priority of jobs for this step to avoid consuming Priority job slots for jobs that don't need zero queue waiting times

* `force_accept`: Force a Robot to accept a file type it would have ignored.

  By default, Robots ignore files they are not familiar with.
  [🤖/video/encode](/docs/robots/video-encode.md), for
  example, will happily ignore input images.

  With the `force_accept` parameter set to `true`, you can force Robots to accept all files thrown at them.
  This will typically lead to errors and should only be used for debugging or combatting edge cases.

* `ignore_errors`: Ignore errors during specific phases of processing.

  Setting this to `["meta"]` will cause the Robot to ignore errors during metadata extraction.

  Setting this to `["execute"]` will cause the Robot to ignore errors during the main execution phase.

  Setting this to `true` is equivalent to `["meta", "execute"]` and will ignore errors in both phases.

* `use`: Specifies which Step(s) to use as input.

  * You can pick any names for Steps except `":original"` (reserved for user uploads handled by Transloadit)
  * You can provide several Steps as input with arrays:
    ```json
    {
      "use": [
        ":original",
        "encoded",
        "resized"
      ]
    }
    ```
  * You can also tag input Steps with `as` to pass semantic intent to robots:
    ```json
    {
      "use": [
        {
          "name": ":original",
          "as": "image"
        },
        {
          "name": ":original",
          "as": "mask"
        }
      ]
    }
    ```

  > [!Tip]
  > That's likely all you need to know about `use`, but you can view [Advanced use cases](/docs/topics/use-parameter.md).

* `provider`: Chooses the best provider based on your request.

  Set this to `"aws"` or `"gcp"` to force a specific provider.

* `crop`: Determine if the detected faces should be extracted. If this option is set to `false`, then the <dfn>Robot</dfn> returns the input image again, but with the coordinates of all detected faces attached to `file.meta.faces` in the result JSON. If this parameter is set to `true`, the <dfn>Robot</dfn> will output all detected faces as images.

* `crop_padding`: Specifies how much padding is added to the extracted face images if `crop` is set to `true`. Values can be in `px` (pixels) or `%` (percentage of the width and height of the particular face image).

* `format`: Determines the output format of the extracted face images if `crop` is set to `true`.

  The default value `"preserve"` means that the input image format is re-used.

* `min_confidence`: Specifies the minimum confidence that a detected face must have. Only faces which have a higher confidence value than this threshold will be included in the result.

* `faces`: Determines which of the detected faces should be returned. Valid values are:

  * `"each"` — each face is returned individually.
  * `"max-confidence"` — only the face with the highest confidence value is returned.
  * `"max-size"` — only the face with the largest area is returned.
  * `"group"` — all detected faces are grouped together into one rectangle that contains all faces.
  * any integer — the faces are sorted by their top-left corner and the integer determines the index of the returned face. Be aware the values are zero-indexed, meaning that `faces: 0` will return the first face. If no face for a given index exists, no output is produced.

  For the following examples, the input image is:

  ![](/assets/images/abbas-malek-hosseini-22NnY93qaOk-unsplash.jpg)

  <br>

  `faces: "each"` applied:

  ![](/assets/images/abbas-malek-hosseini-22NnY93qaOk-face-0.jpg)
  ![](/assets/images/abbas-malek-hosseini-22NnY93qaOk-face-1.jpg)

  <br>

  `faces: "max-confidence"` applied:

  ![](/assets/images/abbas-malek-hosseini-22NnY93qaOk-face-1.jpg)

  <br>

  `faces: "max-size"` applied:

  ![](/assets/images/abbas-malek-hosseini-22NnY93qaOk-face-1.jpg)

  <br>

  `faces: "group"` applied:

  ![](/assets/images/abbas-malek-hosseini-22NnY93qaOk-face-group.jpg)

  <br>

  `faces: 0` applied:

  ![](/assets/images/abbas-malek-hosseini-22NnY93qaOk-face-0.jpg)