Face Detection

class tfsdk.TFFacechip

TFFacechip.save_image(self: tfsdk.TFFacechip, filepath: str) → None

Save the face chip to disk.

Parameters

filepath - the filepath where the face chip should be saved, including the image extension.

TFFacechip.load_image(self: tfsdk.TFFacechip, filepath: str, gpu_memory: bool, gpu_index: int) → tfsdk.ERRORCODE

Load the face chip from disk.

Parameters

filepath - the filepath of the facechip to load. gpu_memory - read the image into GPU memory. This should be set to true when running GPU inference. gpu_index - the GPU index.

TFFacechip.get_height(self: tfsdk.TFFacechip) → int

Get the face chip height in pixels.

Returns

Returns the face chip height in pixels.

TFFacechip.get_width(self: tfsdk.TFFacechip) → int

Get the face chip width in pixels.

Returns

Returns the face chip width in pixels.

SDK.detect_faces(self: tfsdk.SDK, tf_image: tfsdk.TFImage) → List[tfsdk.FaceBoxAndLandmarks]

Detect all the faces in the image and return the bounding boxes and facial landmarks. This method has a small false positive rate. To reduce the false positive rate to near zero, filter out faces with score lower than 0.90. Alternatively, you can use the FACEDETECTIONFILTER configuration option to filter the detected faces. The face detector has a detection scale range of about 5 octaves. tfsdk.ConfigurationOptions.smallest_face_height determines the lower of the detection scale range. E.g., setting tfsdk.ConfigurationOptions.smallest_face_height to 40 pixels yields the detection scale range of ~40 pixels to 1280 (=40x2^5) pixels.

Parameters

tf_image – the input tfsdk.TFImage, returned by tfsdk.SDK.preprocess_image().

Returns

A list of FaceBoxAndLandmarks representing each of the detected faces. If no faces are found, the list will be empty. The detected faces are sorted in order of descending face score.

The recall and precision of the face detection algorithm on the WIDER FACE dataset:

The effect of face height on similarity score:

SDK.detect_largest_face(self: tfsdk.SDK, tf_image: tfsdk.TFImage) → Tuple[bool, tfsdk.FaceBoxAndLandmarks]

Detect the largest face in the image. This method has a small false positive rate. To reduce the false positive rate to near zero, filter out faces with score lower than 0.90. Alternatively, you can use the FACEDETECTIONFILTER configuration option to filter the detected faces. See tfsdk.SDK.detect_faces() for detection range.

Parameters

tf_image – the input tfsdk.TFImage, returned by tfsdk.SDK.preprocess_image().

Returns

A bool indicating if a face was detected and the corresponding tfsdk.FaceBoxAndLandmarks, in that order.

SDK.get_face_landmarks(self: tfsdk.SDK, tf_image: tfsdk.TFImage, face_box_and_landmarks: tfsdk.FaceBoxAndLandmarks) → Tuple[tfsdk.ERRORCODE, List[tfsdk.Point[106]]]

Obtain the 106 face landmarks.

Parameters

• tf_image - the input tfsdk.TFImage, returned by tfsdk.SDK.preprocess_image().

• face_box_and_landmarks - tfsdk.FaceBoxAndLandmarks returned by tfsdk.SDK.detect_faces() or tfsdk.SDK.detect_largest_face().

Returns

The tfsdk.ERRORCODE and list of the 106 face landmark points, returned in that order.

Obtain the 106 face landmarks.

The order of the face landmarks:

SDK.extract_aligned_face(self: tfsdk.SDK, tf_image: tfsdk.TFImage, face_box_and_landmarks: tfsdk.FaceBoxAndLandmarks, margin_left: int = 0, margin_top: int = 0, margin_right: int = 0, margin_bottom: int = 0, scale: float = 1.0) → tfsdk.TFFacechip

Extract the aligned face chip. Changing the margins and scale will change the face chip size. If using the face chip with Trueface algorithms (ex face recognition), do not change the default margin and scale values.

Parameters

• tf_image - the input tfsdk.TFImage, returned by tfsdk.SDK.preprocess_image().

• face_box_and_landmarks - the tfsdk.FaceBoxAndLandmarks returned by tfsdk.SDK.detect_largest_face() or tfsdk.SDK.detect_faces().

• margin_left - adds a margin to the left side of the face chip (default = 0).

• margin_top - adds a margin to the top side of the face chip (default = 0).

• margin_right - adds a margin to the right side of the face chip (default = 0).

• margin_bottom - adds a margin to the bottom side of the face chip (default = 0).

• scale - changes the scale of the face chip (default = 1).

Returns

Returns tfsdk.TFFacechip.

SDK.estimate_head_orientation(self: tfsdk.SDK, tf_image: tfsdk.TFImage, face_box_and_landmarks: tfsdk.FaceBoxAndLandmarks) → Tuple[tfsdk.ERRORCODE, float, float, float]

Estimate the head orientation using the detected facial landmarks. Only works with images where the face is at least 100 pixels in height, otherwise returns ERRORCODE.FACE_TOO_SMALL

Parameters

• tf_image - the input tfsdk.TFImage, returned by tfsdk.SDK.preprocess_image().

• face_box_and_landmarks - the tfsdk.FaceBoxAndLandmarks returned by tfsdk.SDK.detect_largest_face() or tfsdk.SDK.detect_faces().

Returns

The ERRORCODE, yaw, pitch, roll, in that order. Angles are in radians.

The accuracy of this method is estimated using 1920x1080 pixel test images. A test image:

The accuracy of the head orientation estimation:

The effect of the face yaw angle on match similarity can be seen in the following figure:

The effect of the face pitch angle on match similarity can be seen in the following figure:

class tfsdk.Point

to_dict(self: tfsdk.Point) → dict

property x

Coordinate along the horizontal axis, or pixel column.

property y

Coordinate along the vertical axis, or pixel row.

class tfsdk.FaceBoxAndLandmarks

property bottom_right

The bottom-right corner Point of the bounding box.

property landmarks

The list of facial landmark points (Point) in this order: subject right eye, subject left eye, nose, subject right mouth corner, subject left mouth corner.

property score

Likelihood of this being a true positive; a value lower than 0.85 indicates a high chance of being a false positive.

to_dict(self: tfsdk.FaceBoxAndLandmarks) → dict

property top_left

The top-left corner Point of the bounding box.

The order of the face landmarks: