Options to configure the MediaPipe HolisticLandmarker Task
Signature:
export declare interface HolisticLandmarkerOptions extends VisionTaskOptions
Extends: VisionTaskOptions
Properties
| Property | Type | Description |
|---|---|---|
| minFaceDetectionConfidence | number | undefined | The minimum confidence score for the face detection to be considered successful. Defaults to 0.5. |
| minFacePresenceConfidence | number | undefined | The minimum confidence score of face presence score in the face landmarks detection. Defaults to 0.5. |
| minFaceSuppressionThreshold | number | undefined | The minimum non-maximum-suppression threshold for face detection to be considered overlapped. Defaults to 0.3. |
| minHandLandmarksConfidence | number | undefined | The minimum confidence score of hand presence score in the hand landmarks detection. Defaults to 0.5. |
| minPoseDetectionConfidence | number | undefined | The minimum confidence score for the pose detection to be considered successful. Defaults to 0.5. |
| minPosePresenceConfidence | number | undefined | The minimum confidence score of pose presence score in the pose landmarks detection. Defaults to 0.5. |
| minPoseSuppressionThreshold | number | undefined | The minimum non-maximum-suppression threshold for pose detection to be considered overlapped. Defaults to 0.3. |
| outputFaceBlendshapes | boolean | undefined | Whether FaceLandmarker outputs face blendshapes classification. Face blendshapes are used for rendering the 3D face model. |
| outputPoseSegmentationMasks | boolean | undefined | Whether to output segmentation masks. Defaults to false. |
HolisticLandmarkerOptions.minFaceDetectionConfidence
The minimum confidence score for the face detection to be considered successful. Defaults to 0.5.
Signature:
minFaceDetectionConfidence?: number | undefined;
HolisticLandmarkerOptions.minFacePresenceConfidence
The minimum confidence score of face presence score in the face landmarks detection. Defaults to 0.5.
Signature:
minFacePresenceConfidence?: number | undefined;
HolisticLandmarkerOptions.minFaceSuppressionThreshold
The minimum non-maximum-suppression threshold for face detection to be considered overlapped. Defaults to 0.3.
Signature:
minFaceSuppressionThreshold?: number | undefined;
HolisticLandmarkerOptions.minHandLandmarksConfidence
The minimum confidence score of hand presence score in the hand landmarks detection. Defaults to 0.5.
Signature:
minHandLandmarksConfidence?: number | undefined;
HolisticLandmarkerOptions.minPoseDetectionConfidence
The minimum confidence score for the pose detection to be considered successful. Defaults to 0.5.
Signature:
minPoseDetectionConfidence?: number | undefined;
HolisticLandmarkerOptions.minPosePresenceConfidence
The minimum confidence score of pose presence score in the pose landmarks detection. Defaults to 0.5.
Signature:
minPosePresenceConfidence?: number | undefined;
HolisticLandmarkerOptions.minPoseSuppressionThreshold
The minimum non-maximum-suppression threshold for pose detection to be considered overlapped. Defaults to 0.3.
Signature:
minPoseSuppressionThreshold?: number | undefined;
HolisticLandmarkerOptions.outputFaceBlendshapes
Whether FaceLandmarker outputs face blendshapes classification. Face blendshapes are used for rendering the 3D face model.
Signature:
outputFaceBlendshapes?: boolean | undefined;
HolisticLandmarkerOptions.outputPoseSegmentationMasks
Whether to output segmentation masks. Defaults to false.
Signature:
outputPoseSegmentationMasks?: boolean | undefined;