Introducing LiteRT: Google's high-performance runtime for on-device AI, formerly known as TensorFlow Lite. Learn more

FaceLandmarker class

Performs face landmarks detection on images.

This API expects a pre-trained face landmarker model asset bundle.

Signature:

export declare class FaceLandmarker extends VisionTaskRunner

Extends: VisionTaskRunner

Properties

Property	Modifiers	Type	Description
FACE_LANDMARKS_CONTOURS	`static`	Connection[]	Landmark connections to draw the face's contour.
FACE_LANDMARKS_FACE_OVAL	`static`	Connection[]	Landmark connections to draw the face's oval.
FACE_LANDMARKS_LEFT_EYE	`static`	Connection[]	Landmark connections to draw the connection between a face's left eye.
FACE_LANDMARKS_LEFT_EYEBROW	`static`	Connection[]	Landmark connections to draw the connection between a face's left eyebrow.
FACE_LANDMARKS_LEFT_IRIS	`static`	Connection[]	Landmark connections to draw the connection between a face's left iris.
FACE_LANDMARKS_LIPS	`static`	Connection[]	Landmark connections to draw the connection between a face's lips.
FACE_LANDMARKS_RIGHT_EYE	`static`	Connection[]	Landmark connections to draw the connection between a face's right eye.
FACE_LANDMARKS_RIGHT_EYEBROW	`static`	Connection[]	Landmark connections to draw the connection between a face's right eyebrow.
FACE_LANDMARKS_RIGHT_IRIS	`static`	Connection[]	Landmark connections to draw the connection between a face's right iris.
FACE_LANDMARKS_TESSELATION	`static`	Connection[]	Landmark connections to draw the face's tesselation.

Methods

Method	Modifiers	Description
createFromModelBuffer(wasmFileset, modelAssetBuffer)	`static`	Initializes the Wasm runtime and creates a new `FaceLandmarker` based on the provided model asset buffer.
createFromModelPath(wasmFileset, modelAssetPath)	`static`	Initializes the Wasm runtime and creates a new `FaceLandmarker` based on the path to the model asset.
createFromOptions(wasmFileset, faceLandmarkerOptions)	`static`	Initializes the Wasm runtime and creates a new `FaceLandmarker` from the provided options.
detect(image, imageProcessingOptions)		Performs face landmarks detection on the provided single image and waits synchronously for the response. Only use this method when the FaceLandmarker is created with running mode `image`.
detectForVideo(videoFrame, timestamp, imageProcessingOptions)		Performs face landmarks detection on the provided video frame and waits synchronously for the response. Only use this method when the FaceLandmarker is created with running mode `video`.
setOptions(options)		Sets new options for this `FaceLandmarker`.Calling `setOptions()` with a subset of options only affects those options. You can reset an option back to its default value by explicitly setting it to `undefined`.

FaceLandmarker.FACE_LANDMARKS_CONTOURS

Landmark connections to draw the face's contour.

Signature:

static FACE_LANDMARKS_CONTOURS: Connection[];

FaceLandmarker.FACE_LANDMARKS_FACE_OVAL

Landmark connections to draw the face's oval.

Signature:

static FACE_LANDMARKS_FACE_OVAL: Connection[];

FaceLandmarker.FACE_LANDMARKS_LEFT_EYE

Landmark connections to draw the connection between a face's left eye.

Signature:

static FACE_LANDMARKS_LEFT_EYE: Connection[];

FaceLandmarker.FACE_LANDMARKS_LEFT_EYEBROW

Landmark connections to draw the connection between a face's left eyebrow.

Signature:

static FACE_LANDMARKS_LEFT_EYEBROW: Connection[];

FaceLandmarker.FACE_LANDMARKS_LEFT_IRIS

Landmark connections to draw the connection between a face's left iris.

Signature:

static FACE_LANDMARKS_LEFT_IRIS: Connection[];

FaceLandmarker.FACE_LANDMARKS_LIPS

Landmark connections to draw the connection between a face's lips.

Signature:

static FACE_LANDMARKS_LIPS: Connection[];

FaceLandmarker.FACE_LANDMARKS_RIGHT_EYE

Landmark connections to draw the connection between a face's right eye.

Signature:

static FACE_LANDMARKS_RIGHT_EYE: Connection[];

FaceLandmarker.FACE_LANDMARKS_RIGHT_EYEBROW

Landmark connections to draw the connection between a face's right eyebrow.

Signature:

static FACE_LANDMARKS_RIGHT_EYEBROW: Connection[];

FaceLandmarker.FACE_LANDMARKS_RIGHT_IRIS

Landmark connections to draw the connection between a face's right iris.

Signature:

static FACE_LANDMARKS_RIGHT_IRIS: Connection[];

FaceLandmarker.FACE_LANDMARKS_TESSELATION

Landmark connections to draw the face's tesselation.

Signature:

static FACE_LANDMARKS_TESSELATION: Connection[];

FaceLandmarker.createFromModelBuffer()

Initializes the Wasm runtime and creates a new FaceLandmarker based on the provided model asset buffer.

Signature:

static createFromModelBuffer(wasmFileset: WasmFileset, modelAssetBuffer: Uint8Array): Promise<FaceLandmarker>;

Parameters

Parameter	Type	Description
wasmFileset	WasmFileset	A configuration object that provides the location of the Wasm binary and its loader.
modelAssetBuffer	Uint8Array	A binary representation of the model.

Returns:

Promise<FaceLandmarker>

FaceLandmarker.createFromModelPath()

Initializes the Wasm runtime and creates a new FaceLandmarker based on the path to the model asset.

Signature:

static createFromModelPath(wasmFileset: WasmFileset, modelAssetPath: string): Promise<FaceLandmarker>;

Parameters

Parameter	Type	Description
wasmFileset	WasmFileset	A configuration object that provides the location of the Wasm binary and its loader.
modelAssetPath	string	The path to the model asset.

Returns:

Promise<FaceLandmarker>

FaceLandmarker.createFromOptions()

Initializes the Wasm runtime and creates a new FaceLandmarker from the provided options.

Signature:

static createFromOptions(wasmFileset: WasmFileset, faceLandmarkerOptions: FaceLandmarkerOptions): Promise<FaceLandmarker>;

Parameters

Parameter	Type	Description
wasmFileset	WasmFileset	A configuration object that provides the location of the Wasm binary and its loader.
faceLandmarkerOptions	FaceLandmarkerOptions	The options for the FaceLandmarker. Note that either a path to the model asset or a model buffer needs to be provided (via `baseOptions`).

Returns:

Promise<FaceLandmarker>

FaceLandmarker.detect()

Performs face landmarks detection on the provided single image and waits synchronously for the response. Only use this method when the FaceLandmarker is created with running mode image.

Signature:

detect(image: ImageSource, imageProcessingOptions?: ImageProcessingOptions): FaceLandmarkerResult;

Parameters

Parameter	Type	Description
image	ImageSource	An image to process.
imageProcessingOptions	ImageProcessingOptions	the `ImageProcessingOptions` specifying how to process the input image before running inference. The detected face landmarks.

Returns:

FaceLandmarkerResult

FaceLandmarker.detectForVideo()

Performs face landmarks detection on the provided video frame and waits synchronously for the response. Only use this method when the FaceLandmarker is created with running mode video.

Signature:

detectForVideo(videoFrame: ImageSource, timestamp: number, imageProcessingOptions?: ImageProcessingOptions): FaceLandmarkerResult;

Parameters

Parameter	Type	Description
videoFrame	ImageSource	A video frame to process.
timestamp	number	The timestamp of the current frame, in ms.
imageProcessingOptions	ImageProcessingOptions	the `ImageProcessingOptions` specifying how to process the input image before running inference. The detected face landmarks.

Returns:

FaceLandmarkerResult

FaceLandmarker.setOptions()

Sets new options for this FaceLandmarker.

Calling setOptions() with a subset of options only affects those options. You can reset an option back to its default value by explicitly setting it to undefined.

Signature:

setOptions(options: FaceLandmarkerOptions): Promise<void>;

Parameters

Parameter	Type	Description
options	FaceLandmarkerOptions	The options for the face landmarker.

Returns:

Promise<void>