FingerPatternSynthesizer class
Converts a high-level Finger → FingerState map into synthetic HandLandmarks that are geometrically consistent with the existing rule-based classifier and KNN trainer.
This lets sign-language presets ship as readable finger patterns while still
feeding the landmark-based CustomGestureTrainer used elsewhere in the
package. The synthesized hand is an idealized, upright right hand; small
deterministic variant offsets shift the whole hand so multiple distinct
training samples can be generated from one pattern.
Properties
- hashCode → int
-
The hash code for this object.
no setterinherited
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
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
Static Methods
-
synthesize(
Map< Finger, FingerState> pattern, {int variant = 0}) → HandLandmarks -
Build a synthetic HandLandmarks for
pattern.