Interface HandResult

Each result has:

• id: hand id number
• score: detection confidence score as value
• box: bounding box: x, y, width, height normalized to input image resolution
• boxRaw: bounding box: x, y, width, height normalized to 0..1
• keypoints: keypoints as array of [x, y, z] points of hand, normalized to image resolution
• annotations: annotated landmarks for each hand part with keypoints
• landmarks: annotated landmarks for eachb hand part with logical curl and direction strings