# Face Utils

{% hint style="info" %}
This API Reference is based on DeGirum Face version 1.4.1.
{% endhint %}

## Functions <a href="#functions" id="functions"></a>

#### face\_align\_and\_crop(img, ...) <a href="#face_align_and_crop" id="face_align_and_crop"></a>

`face_align_and_crop(img, landmarks, image_size)`

Align and crop the face from the image based on the given landmarks.

Parameters:

| Name         | Type            | Description                                                                                                                          | Default    |
| ------------ | --------------- | ------------------------------------------------------------------------------------------------------------------------------------ | ---------- |
| `img`        | `ndarray`       | The full image (not the cropped bounding box).                                                                                       | *required* |
| `landmarks`  | `List[ndarray]` | List of 5 keypoints (landmarks) as (x, y) coordinates in the following order: \[left eye, right eye, nose, left mouth, right mouth]. | *required* |
| `image_size` | `int`           | The size to which the image should be resized.                                                                                       | *required* |

Returns:

| Type      | Description                        |
| --------- | ---------------------------------- |
| `ndarray` | np.ndarray: the aligned face image |

#### face\_is\_frontal(landmarks) <a href="#face_is_frontal" id="face_is_frontal"></a>

`face_is_frontal(landmarks)`

Check if the face is frontal based on the landmarks.

Parameters:

| Name        | Type            | Description                                                                                                                          | Default    |
| ----------- | --------------- | ------------------------------------------------------------------------------------------------------------------------------------ | ---------- |
| `landmarks` | `List[ndarray]` | List of 5 keypoints (landmarks) as (x, y) coordinates in the following order: \[left eye, right eye, nose, left mouth, right mouth]. | *required* |

Returns:

| Name   | Type   | Description                                   |
| ------ | ------ | --------------------------------------------- |
| `bool` | `bool` | True if the face is frontal, False otherwise. |

#### face\_is\_shifted(bbox, ...) <a href="#face_is_shifted" id="face_is_shifted"></a>

`face_is_shifted(bbox, landmarks)`

Check if the face is shifted based on the landmarks.

Parameters:

| Name        | Type            | Description                                         | Default    |
| ----------- | --------------- | --------------------------------------------------- | ---------- |
| `bbox`      | `List[float]`   | Bounding box of the face as \[x1, y1, x2, y2].      | *required* |
| `landmarks` | `List[ndarray]` | List of keypoints (landmarks) as (x, y) coordinates | *required* |

Returns:

| Name   | Type   | Description                                                     |
| ------ | ------ | --------------------------------------------------------------- |
| `bool` | `bool` | True if the face is shifted to a side of bbox, False otherwise. |


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.degirum.com/face-recognition/complete-api-reference/face_utils.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.