Face detection

The FaceDetector class detects human faces in still images.

Detection models

The face detector requires a machine learning model to be loaded into memory. The model should be selected according to the target platform and use-case.

Model

Size

Description

FaceDetector4A

8.29 MB

This model provides the best accuracy. It is recommended for 1-to-N applications or in an uncontrolled environment.

FaceDetector4B

1.25 MB

This model provides a good balance of accuracy, speed, and size. This model is less robust to variations of head pose than the 4A version and should therefore only be used in a controlled environment.

FaceDetector3A

57.66 MB

Obsolete. Provided for backward compatibility. Use model 4A whenever possible.

FaceDetector3B

0.98 MB

Obsolete. Provided for backward compatibility. Use model 4B whenever possible.

FaceDetector3C

0.22 MB

Ultra-light detector, dedicated to short-range real-time detection/tracking applications only.

Note

Call the FaceLibrary.loadModel Method to load the chosen model on application start.

Hint

On startup, call the FaceDetector.warmUp Method to prepare inference of the AI model.

Tolerance

The face detection tolerance depends on the AI model used. The following characteristics can be assumed:

Face angle tolerance

yaw < ±45°, pitch < ±30°, roll < 45°

Minimal interocular distance (IOD)

10 pixels

Warning

The algorithm searches for faces in the range [16px;512px]. If the image is too large to fit this range, one must resize it before the detection process.

Hint

For optimum facial recognition performance, a minimum distance of 100 pixels between eyes is recommended.

Detected face

The FaceDetector outputs a list of DetectedFace objects containing the following information:

Note

Only faces with a confidence score above the configured threshold are returned. See Parameters for details.

Face ID

The face ID is an auto-incremented value used to track faces.

Warning

The face ID is not linked to a user’s identity.

Confidence score

The confidence score ranges from 0 to 100. A high confidence score indicates that it is more likely that the face detected is really a face.

Face bounds

id3 Face SDK detects human faces and returns a rectangle around the detected faces, as shown in the figure below.

../_images/Multi-face-recognition.jpg

Portrait bounds

id3 Face SDK detects human faces and returns a rectangle for ISO/ICAO compliant portraits, as shown in the figure below.

../_images/face-portrait-rectangle.jpg

Parameters

The face detector is configured by default with the most common parameters. For specific applications, it may be useful to adjust certain parameters.

The following parameters are defined:

Name

Description

Confidence threshold
Value above which the detector considers the detected element to be a face.
Setting a high threshold reduces false detection but can increase the number of undetected faces.

Model

Detection models used to detect faces.

NMS IoU threshold
Non-maximum suppression (NMS) intersection-over-union (IoU) threshold.
Setting a high threshold allows to detect more overlapping faces which can be useful in a multi-face scenario. On the contrary, in a portrait scenario, a low NMS IoU threshold should be preferred.
../_images/iou.bmp

Thread count

Number of threads to use for face detection. Default is 1.

Example

The example below demonstrates how to detect faces in an image:

# create a new instance of the FaceDetector class.
face_detector = FaceDetector(
    confidence_threshold = 50,
    nms_iou_threshold = 40,
    thread_count = 4
)

# warm up the face detector
face_detector.warm_up(512, 512)

# downscale image
downscaled_image = image.clone()
scale = downscaled_image.downscale(512)

# detect faces on the image.
detected_face_list = face_detector.detect_faces(downscaled_image)

# enumerate detected faces.
for face in detected_face_list:
    bounds = face.bounds

# get the largest face
face = detected_face_list.get_largest_face()

# rescale detected face
face.rescale(1/scale)

# Dispose of all resources allocated to the FaceDetector.
del face_detector

See also