Interface FaceResult

Each result has:

• id: face id number
• score: overal detection confidence score value
• boxScore: face box detection confidence score value
• faceScore: face keypoints detection confidence score value
• box: face bounding box as array of [x, y, width, height], normalized to image resolution
• boxRaw: face bounding box as array of [x, y, width, height], normalized to range 0..1
• mesh: face keypoints as array of [x, y, z] points of face mesh, normalized to image resolution
• meshRaw: face keypoints as array of [x, y, z] points of face mesh, normalized to range 0..1
• annotations: annotated face keypoints as array of annotated face mesh points
• age: age as value
• gender: gender as value
• genderScore: gender detection confidence score as value
• emotion: emotions as array of possible emotions with their individual scores
• embedding: facial descriptor as array of numerical elements
• iris: iris distance from current viewpoint as distance value in centimeters for a typical camera field of view of 88 degrees. value should be adjusted manually as needed
• real: anti-spoofing analysis to determine if face is real of fake
• rotation: face rotiation that contains both angles and matrix used for 3d transformations
• angle: face angle as object with values for roll, yaw and pitch angles
• matrix: 3d transofrmation matrix as array of numeric values
• gaze: gaze direction as object with values for bearing in radians and relative strength
• tensor: face tensor as Tensor object which contains detected face