SeetaPsych Attributes

Face and body based psychology analysis

SeetaPsych Lib is a Python library for face- and body-based psychology analysis. It provides a modular Pipeline/Runner runtime and an optional Streamlit WebUI.

This project is used to manage the specifications for various attribute outputs, providing a unified standard so that different algorithm implementations can produce interchangeable and reusable module outputs.

Catalog

• face/detection Obtain the face detection results, represented as rectangular bounding boxes.
• face/landmarks Get facial landmarks for basic alignment, including the centers of the left and right eyes, the nose tip, and the positions of the left and right mouth corners.
• face/selection Indicates the result of face selection. It will update the properties of face/detection and face/landmarks.
• face/action_units Indicate the confidence level of each Action Unit. Not all Action Units' results may be output.
• face/expression Indicate the confidence level of each expression.

face/detection

Properties

• face_detection (array, required)
  • Items: Refer to #/$defs/BBox.

Definitions

• BBox (object)
  • xyxy (array, required): Length must be equal to 4.
    • Items (number)
  • score (number, required)

Examples

{
    "face_detection": [
        {
            "score": 0.5,
            "xyxy": [
                100,
                200,
                300,
                400
            ]
        }
    ]
}

face/landmarks

Properties

• face_landmarks (array, required)
  • Items: Refer to #/$defs/Landmarks.

Definitions

• Landmarks (object)
  • landmarks (array, required): Length must be equal to 10.
    • Items (number)

Examples

{
    "face_landmarks": [
        {
            "landmarks": [
                100,
                100,
                200,
                200,
                300,
                300,
                400,
                400,
                500,
                500
            ]
        }
    ]
}

face/selection

Properties

• face_selection (array, required)
  • Items: Refer to #/$defs/Selection.

Definitions

• Selection (object)
  • pid (integer, required): PID of selected face detection. It will automatically update starting from 1.

Examples

{
    "face_detection": [
        {
            "score": 0.5,
            "xyxy": [
                100,
                200,
                300,
                400
            ]
        }
    ],
    "face_selection": {
        "pid": 1
    }
}

face/action_units

Properties

• action_units (required): Refer to #/$defs/ActionUnits.

Definitions

• ActionUnits (object)
  • AU1 (number): [0, 1]. Inner Brow Raiser. Default: null.
  • AU2 (number): [0, 1]. Outer Brow Raiser. Default: null.
  • AU4 (number): [0, 1]. Brow Lowerer. Default: null.
  • AU5 (number): [0, 1]. Upper Lid Raiser. Default: null.
  • AU6 (number): [0, 1]. Cheek Raiser. Default: null.
  • AU7 (number): [0, 1]. Lid Tightener. Default: null.
  • AU9 (number): [0, 1]. Nose Wrinkler. Default: null.
  • AU10 (number): [0, 1]. Upper Lip Raiser. Default: null.
  • AU12 (number): [0, 1]. Lip Corner Puller. Default: null.
  • AU15 (number): [0, 1]. Lip Corner Depressor. Default: null.
  • AU17 (number): [0, 1]. Chin Raiser. Default: null.
  • AU20 (number): [0, 1]. Lip Stretcher. Default: null.
  • AU23 (number): [0, 1]. Lip Tightener. Default: null.
  • AU24 (number): [0, 1]. Lip Pressor. Default: null.
  • AU25 (number): [0, 1]. Lips Part. Default: null.
  • AU26 (number): [0, 1]. Jaw Drop. Default: null.

Examples

{
    "face_action_units": {
        "AU1": 0.5,
        "AU10": 0.5,
        "AU12": 0.5,
        "AU15": 0.5,
        "AU17": 0.5,
        "AU2": 0.5,
        "AU20": 0.5,
        "AU23": 0.5,
        "AU24": 0.5,
        "AU25": 0.5,
        "AU26": 0.5,
        "AU4": 0.5,
        "AU5": 0.5,
        "AU6": 0.5,
        "AU7": 0.5,
        "AU9": 0.5
    }
}

face/expression

Properties

• expression (required): Refer to #/$defs/Expression.

Definitions

• Expression (object)
  • neutral (number): Confidence in [0, 1]. Default: null.
  • anger (number): Confidence in [0, 1]. Default: null.
  • disgust (number): Confidence in [0, 1]. Default: null.
  • fear (number): Confidence in [0, 1]. Default: null.
  • happy (number): Confidence in [0, 1]. Default: null.
  • sad (number): Confidence in [0, 1]. Default: null.
  • surprise (number): Confidence in [0, 1]. Default: null.

Examples

{
    "face_expression": {
        "anger": 0.01,
        "disgust": 0.01,
        "fear": 0.01,
        "happy": 0.94,
        "neutral": 0.01,
        "sad": 0.01,
        "surprise": 0.01
    }
}