Base options for the hand gesture recognizer task.
running_mode
The running mode of the task. Default to the image mode.
Gesture recognizer task has three running modes: 1) The image mode for
recognizing hand gestures on single image inputs. 2) The video mode for
recognizing hand gestures on the decoded frames of a video. 3) The live
stream mode for recognizing hand gestures on a live stream of input data,
such as from camera.
num_hands
The maximum number of hands can be detected by the recognizer.
min_hand_detection_confidence
The minimum confidence score for the hand
detection to be considered successful.
min_hand_presence_confidence
The minimum confidence score of hand presence
score in the hand landmark detection.
min_tracking_confidence
The minimum confidence score for the hand tracking
to be considered successful.
canned_gesture_classifier_options
Options for configuring the canned
gestures classifier, such as score threshold, allow list and deny list of
gestures. The categories for canned gesture classifiers are: ["None",
"Closed_Fist", "Open_Palm", "Pointing_Up", "Thumb_Down", "Thumb_Up",
"Victory", "ILoveYou"]. Note this option is subject to change.
custom_gesture_classifier_options
Options for configuring the custom
gestures classifier, such as score threshold, allow list and deny list of
gestures. Note this option is subject to change.
result_callback
The user-defined result callback for processing live stream
data. The result callback should only be specified when the running mode
is set to the live stream mode.