FaceLandmarker

public final class FaceLandmarker

Performs face landmarks detection on images.

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

• Input image MPImage
  • The image that face landmarks detection runs on.
• Output FaceLandmarkerResult
  • A FaceLandmarkerResult containing face landmarks.

Nested Classes

class

FaceLandmarker.FaceLandmarkerOptions

Options for setting up an FaceLandmarker.

Fields

public static final Set<Connection>	FACE_LANDMARKS_CONNECTORS
public static final Set<Connection>	FACE_LANDMARKS_FACE_OVAL
public static final Set<Connection>	FACE_LANDMARKS_LEFT_EYE
public static final Set<Connection>	FACE_LANDMARKS_LEFT_EYE_BROW
public static final Set<Connection>	FACE_LANDMARKS_LEFT_IRIS
public static final Set<Connection>	FACE_LANDMARKS_LIPS
public static final Set<Connection>	FACE_LANDMARKS_RIGHT_EYE
public static final Set<Connection>	FACE_LANDMARKS_RIGHT_EYE_BROW
public static final Set<Connection>	FACE_LANDMARKS_RIGHT_IRIS
public static final Set<Connection>	FACE_LANDMARKS_TESSELATION

Public Methods

static FaceLandmarker	createFromBuffer(Context context, ByteBuffer modelAssetBuffer) Creates a FaceLandmarker instance from a model asset bundle buffer and the default FaceLandmarker.FaceLandmarkerOptions.
static FaceLandmarker	createFromFile(Context context, String modelAssetPath) Creates a FaceLandmarker instance from a model asset bundle path and the default FaceLandmarker.FaceLandmarkerOptions.
static FaceLandmarker	createFromFile(Context context, File modelAssetFile) Creates a FaceLandmarker instance from a model asset bundle file and the default FaceLandmarker.FaceLandmarkerOptions.
static FaceLandmarker	createFromOptions(Context context, FaceLandmarker.FaceLandmarkerOptions landmarkerOptions) Creates a FaceLandmarker instance from a FaceLandmarker.FaceLandmarkerOptions.
FaceLandmarkerResult	detect(MPImage image) Performs face landmarks detection on the provided single image with default image processing options, i.e.
FaceLandmarkerResult	detect(MPImage image, ImageProcessingOptions imageProcessingOptions) Performs face landmarks detection on the provided single image.
void	detectAsync(MPImage image, ImageProcessingOptions imageProcessingOptions, long timestampMs) Sends live image data to perform face landmarks detection, and the results will be available via the OutputHandler.ResultListener provided in the FaceLandmarker.FaceLandmarkerOptions.
void	detectAsync(MPImage image, long timestampMs) Sends live image data to perform face landmarks detection with default image processing options, i.e.
FaceLandmarkerResult	detectForVideo(MPImage image, ImageProcessingOptions imageProcessingOptions, long timestampMs) Performs face landmarks detection on the provided video frame.
FaceLandmarkerResult	detectForVideo(MPImage image, long timestampMs) Performs face landmarks detection on the provided video frame with default image processing options, i.e.

Inherited Methods

From class com.google.mediapipe.tasks.vision.core.BaseVisionTaskApi

void	close() Closes and cleans up the MediaPipe vision task.
static long	generateResultTimestampMs(RunningMode runningMode, Packet packet) Generates the timestamp of a vision task result object from the vision task running mode and the output packet.

From class java.lang.Object

boolean	equals(Object arg0)
final Class<?>	getClass()
int	hashCode()
final void	notify()
final void	notifyAll()
String	toString()
final void	wait(long arg0, int arg1)
final void	wait(long arg0)
final void	wait()

From interface java.lang.AutoCloseable

abstract void

close()

Fields

public static final Set<Connection> FACE_LANDMARKS_CONNECTORS

public static final Set<Connection> FACE_LANDMARKS_FACE_OVAL

public static final Set<Connection> FACE_LANDMARKS_LEFT_EYE

public static final Set<Connection> FACE_LANDMARKS_LEFT_EYE_BROW

public static final Set<Connection> FACE_LANDMARKS_LEFT_IRIS

public static final Set<Connection> FACE_LANDMARKS_LIPS

public static final Set<Connection> FACE_LANDMARKS_RIGHT_EYE

public static final Set<Connection> FACE_LANDMARKS_RIGHT_EYE_BROW

public static final Set<Connection> FACE_LANDMARKS_RIGHT_IRIS

public static final Set<Connection> FACE_LANDMARKS_TESSELATION

Public Methods

public static FaceLandmarker createFromBuffer (Context context, ByteBuffer modelAssetBuffer)

Creates a FaceLandmarker instance from a model asset bundle buffer and the default FaceLandmarker.FaceLandmarkerOptions.

Parameters

context	an Android ERROR(/Context).
modelAssetBuffer

Throws

	if there is an error during FaceLandmarker creation.

public static FaceLandmarker createFromFile (Context context, String modelAssetPath)

Creates a FaceLandmarker instance from a model asset bundle path and the default FaceLandmarker.FaceLandmarkerOptions.

Parameters

context	an Android ERROR(/Context).
modelAssetPath	path to the face landmarks model with metadata in the assets.

Throws

	if there is an error during FaceLandmarker creation.

public static FaceLandmarker createFromFile (Context context, File modelAssetFile)

Creates a FaceLandmarker instance from a model asset bundle file and the default FaceLandmarker.FaceLandmarkerOptions.

Parameters

context	an Android ERROR(/Context).
modelAssetFile	the face landmarks model File instance.

Throws

IOException	if an I/O error occurs when opening the tflite model file.
	if there is an error during FaceLandmarker creation.

public static FaceLandmarker createFromOptions (Context context, FaceLandmarker.FaceLandmarkerOptions landmarkerOptions)

Creates a FaceLandmarker instance from a FaceLandmarker.FaceLandmarkerOptions.

Parameters

context	an Android ERROR(/Context).
landmarkerOptions	a FaceLandmarker.FaceLandmarkerOptions instance.

Throws

	if there is an error during FaceLandmarker creation.

public FaceLandmarkerResult detect (MPImage image)

Performs face landmarks detection on the provided single image with default image processing options, i.e. without any rotation applied. Only use this method when the FaceLandmarker is created with ERROR(/RunningMode.IMAGE). TODO update java doc for input image format.

FaceLandmarker supports the following color space types:

• ERROR(/Bitmap.Config.ARGB_8888)

Parameters

image	a MediaPipe MPImage object for processing.

Throws

	if there is an internal error.

public FaceLandmarkerResult detect (MPImage image, ImageProcessingOptions imageProcessingOptions)

Performs face landmarks detection on the provided single image. Only use this method when the FaceLandmarker is created with ERROR(/RunningMode.IMAGE). TODO update java doc for input image format.

FaceLandmarker supports the following color space types:

• ERROR(/Bitmap.Config.ARGB_8888)

Parameters

image	a MediaPipe MPImage object for processing.
imageProcessingOptions	the ImageProcessingOptions specifying how to process the input image before running inference. Note that region-of-interest is not supported by this task: specifying ImageProcessingOptions.regionOfInterest() will result in this method throwing an IllegalArgumentException.

Throws

IllegalArgumentException	if the ImageProcessingOptions specify a region-of-interest.
	if there is an internal error.

public void detectAsync (MPImage image, ImageProcessingOptions imageProcessingOptions, long timestampMs)

Sends live image data to perform face landmarks detection, and the results will be available via the OutputHandler.ResultListener provided in the FaceLandmarker.FaceLandmarkerOptions. Only use this method when the FaceLandmarker is created with ERROR(/RunningMode.LIVE_STREAM).

It's required to provide a timestamp (in milliseconds) to indicate when the input image is sent to the face landmarker. The input timestamps must be monotonically increasing.

FaceLandmarker supports the following color space types:

• ERROR(/Bitmap.Config.ARGB_8888)

Parameters

image	a MediaPipe MPImage object for processing.
imageProcessingOptions	the ImageProcessingOptions specifying how to process the input image before running inference. Note that region-of-interest is not supported by this task: specifying ImageProcessingOptions.regionOfInterest() will result in this method throwing an IllegalArgumentException.
timestampMs	the input timestamp (in milliseconds).

Throws

IllegalArgumentException	if the ImageProcessingOptions specify a region-of-interest.
	if there is an internal error.

public void detectAsync (MPImage image, long timestampMs)

Sends live image data to perform face landmarks detection with default image processing options, i.e. without any rotation applied, and the results will be available via the OutputHandler.ResultListener provided in the FaceLandmarker.FaceLandmarkerOptions. Only use this method when the FaceLandmarker is created with ERROR(/RunningMode.LIVE_STREAM).

It's required to provide a timestamp (in milliseconds) to indicate when the input image is sent to the face landmarker. The input timestamps must be monotonically increasing.

FaceLandmarker supports the following color space types:

• ERROR(/Bitmap.Config.ARGB_8888)

Parameters

image	a MediaPipe MPImage object for processing.
timestampMs	the input timestamp (in milliseconds).

Throws

	if there is an internal error.

public FaceLandmarkerResult detectForVideo (MPImage image, ImageProcessingOptions imageProcessingOptions, long timestampMs)

Performs face landmarks detection on the provided video frame. Only use this method when the FaceLandmarker is created with ERROR(/RunningMode.VIDEO).

It's required to provide the video frame's timestamp (in milliseconds). The input timestamps must be monotonically increasing.

FaceLandmarker supports the following color space types:

• ERROR(/Bitmap.Config.ARGB_8888)

Parameters

image	a MediaPipe MPImage object for processing.
imageProcessingOptions	the ImageProcessingOptions specifying how to process the input image before running inference. Note that region-of-interest is not supported by this task: specifying ImageProcessingOptions.regionOfInterest() will result in this method throwing an IllegalArgumentException.
timestampMs	the input timestamp (in milliseconds).

Throws

IllegalArgumentException	if the ImageProcessingOptions specify a region-of-interest.
	if there is an internal error.

public FaceLandmarkerResult detectForVideo (MPImage image, long timestampMs)

Performs face landmarks detection on the provided video frame with default image processing options, i.e. without any rotation applied. Only use this method when the FaceLandmarker is created with ERROR(/RunningMode.VIDEO).

It's required to provide the video frame's timestamp (in milliseconds). The input timestamps must be monotonically increasing.

FaceLandmarker supports the following color space types:

• ERROR(/Bitmap.Config.ARGB_8888)

Parameters

image	a MediaPipe MPImage object for processing.
timestampMs	the input timestamp (in milliseconds).

Throws

	if there is an internal error.