FaceConfig class

Configuration for face emotion detection.

Constructors

FaceConfig({bool detectEmotion = true, bool detectLandmarks = false, bool detectContours = false, double minFaceSize = 0.1, bool enableTracking = true, double minEmotionConfidence = 0.4, bool accurateMode = false})

const

Properties

accurateMode → bool

Use ML Kit's accurate detection mode instead of fast mode. Improves detection quality (fewer missed faces, better landmarks) at the cost of higher latency (~2-3x slower per frame).

final

detectContours → bool

Whether to detect face contours (face outline, eyes, lips, eyebrows, nose, cheeks — all 15 ML Kit contour types). Note: contour mode and face tracking cannot be used together in ML Kit. When enabled, tracking is automatically disabled.

final

detectEmotion → bool

Whether to run the TFLite emotion classifier (adds ~5-15ms latency).

final

detectLandmarks → bool

Whether to detect 10 face landmarks (eye centers, mouth corners, nose, ears, cheeks). Lighter than contours and works WITH face tracking.

final

enableTracking → bool

Assign stable tracking IDs to faces across frames.

final

hashCode → int

The hash code for this object.

no setter, inherited

minEmotionConfidence → double

Minimum confidence to accept an emotion classification 0.0, 1.0.

final

minFaceSize → double

Minimum face size as proportion of image width 0.0, 1.0.

final

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited