mp.tasks.vision.GestureRecognizer

Class that performs gesture recognition on images.

mp.tasks.vision.GestureRecognizer(
    lib: mp.tasks.vision.drawing_styles.face_landmarker.serial_dispatcher.SerialDispatcher,
    handle: ctypes.c_void_p,
    dispatcher: mp.tasks.vision.drawing_styles.face_landmarker.async_result_dispatcher.AsyncResultDispatcher,
    async_callback: _C_TYPES_RESULT_CALLBACK
)

lib The dispatch library to use for the gesture recognizer.
handle The C pointer to the gesture recognizer.
dispatcher The async result handler for the gesture recognizer.
async_callback The c callback for the gesture recognizer.

Methods

close

View source

close()

Closes GestureRecognizer.

create_from_model_path

View source

@classmethod
create_from_model_path(
    model_path: str
) -> 'GestureRecognizer'

Creates an GestureRecognizer object from a TensorFlow Lite model and the default GestureRecognizerOptions.

Note that the created GestureRecognizer instance is in image mode, for recognizing hand gestures on single image inputs.

Args
model_path Path to the model.

Returns
GestureRecognizer object that's created from the model file and the default GestureRecognizerOptions.

Raises
ValueError If failed to create GestureRecognizer object from the provided file such as invalid file path.
RuntimeError If other types of error occurred.

create_from_options

View source

@classmethod
create_from_options(
    options: mp.tasks.vision.GestureRecognizerOptions
) -> 'GestureRecognizer'

Creates the GestureRecognizer object from gesture recognizer options.

Args
options Options for the gesture recognizer task.

Returns
GestureRecognizer object that's created from options.

Raises
ValueError If failed to create GestureRecognizer object from GestureRecognizerOptions such as missing the model.
RuntimeError If other types of error occurred.

recognize

View source

recognize(
    image: mp.Image,
    image_processing_options: Optional[mp.tasks.vision.ImageProcessingOptions] = None
) -> mp.tasks.vision.GestureRecognizerResult

Performs hand gesture recognition on the given image.

Only use this method when the GestureRecognizer is created with the image running mode.

The image can be of any size with format RGB or RGBA.

support is implemented.

Args
image MediaPipe Image.
image_processing_options Options for image processing.

Returns
The hand gesture recognition results.

Raises
ValueError If any of the input arguments is invalid.
RuntimeError If gesture recognition failed to run.

recognize_async

View source

recognize_async(
    image: mp.Image,
    timestamp_ms: int,
    image_processing_options: Optional[mp.tasks.vision.ImageProcessingOptions] = None
) -> None

Sends live image data to perform gesture recognition.

The results will be available via the "result_callback" provided in the GestureRecognizerOptions. Only use this method when the GestureRecognizer is created with the live stream running mode.

Only use this method when the GestureRecognizer is created with the live stream running mode. The input timestamps should be monotonically increasing for adjacent calls of this method. This method will return immediately after the input image is accepted. The results will be available via the result_callback provided in the GestureRecognizerOptions. The recognize_async method is designed to process live stream data such as camera input. To lower the overall latency, gesture recognizer may drop the input images if needed. In other words, it's not guaranteed to have output per input image.

The result_callback provides:

  • The hand gesture recognition results.
  • The input image that the gesture recognizer runs on.
  • The input timestamp in milliseconds.

Args
image MediaPipe Image.
timestamp_ms The timestamp of the input image in milliseconds.
image_processing_options Options for image processing.

Raises
ValueError If the current input timestamp is smaller than what the gesture recognizer has already processed.

recognize_for_video

View source

recognize_for_video(
    image: mp.Image,
    timestamp_ms: int,
    image_processing_options: Optional[mp.tasks.vision.ImageProcessingOptions] = None
) -> mp.tasks.vision.GestureRecognizerResult

Performs gesture recognition on the provided video frame.

Only use this method when the GestureRecognizer is created with the video running mode.

Only use this method when the GestureRecognizer is created with the video running mode. It's required to provide the video frame's timestamp (in milliseconds) along with the video frame. The input timestamps should be monotonically increasing for adjacent calls of this method.

Args
image MediaPipe Image.
timestamp_ms The timestamp of the input video frame in milliseconds.
image_processing_options Options for image processing.

Returns
The hand gesture recognition results.

Raises
ValueError If any of the input arguments is invalid.
RuntimeError If gesture recognition failed to run.

__enter__

View source

__enter__()

Returns self upon entering the runtime context.

__exit__

View source

__exit__(
    exc_type, exc_value, traceback
)

Closes GestureRecognizers and exits the context manager.

Args
exc_type The exception type that caused the context manager to exit.
exc_value The exception value that caused the context manager to exit.
traceback The exception traceback that caused the context manager to exit.

Raises
RuntimeError If the MediaPipe Gesture Recognizer task failed to close.