FaceEncoder class

Extracts facial features and encodes face templates.

Implemented types

Constructors

FaceEncoder()
Creates a new instance of the FaceEncoder class.
FaceEncoder.fromHandle(Pointer<id3FaceEncoder> handle)
Creates a new instance of the FaceEncoder class.

Properties

handle → Pointer<id3FaceEncoder>
Gets the native handle. return The native handle.
no setter
hashCode → int
The hash code for this object.
no setterinherited
minimalIod ↔ int
Minimal interocular distance (IOD) in pixels required to perform a face encoding. Hint: Default value is 30 pixels. It is not recommended to change this value. Warning: Reducing the minimal required IOD to encode smaller face images may create unreliable face templates and significantly degrade recognition performances.
getter/setter pair
model ↔ FaceModel
Model used to create templates. Hint: Default value is FaceEncoder9A which is the best available algorithm in this SDK in terms of accuracy. Some better accuracy/speed balances can be found by choosing another model.
getter/setter pair
processingUnit ↔ ProcessingUnit
Processing unit where to run the encoding process. Hint: Default value is CPU.
getter/setter pair
runtimeType → Type
A representation of the runtime type of the object.
no setterinherited
threadCount ↔ int
Number of threads to be used for template encoding. Hint: Default value is 1. Allocating more than one thread can increase the speed of the process.
getter/setter pair

Methods

computeQuality(Image image, DetectedFace detectedFace) → int
Computes the quality of a detected face. Here, quality expresses the match capability of an image: a high quality image will generate less match errors (false acceptance or false rejection) than a low quality one. Warning: A minimum interocular distance (IOD) of 30 pixels for the detected face is required for this function, below this value it will output an error. Important: Loading the FaceEncodingQualityEstimator model is required to use this function.
createTemplate(Image image, DetectedFace detectedFace) → FaceTemplate
Extracts the unique features of a detected face and store them in a FaceTemplate. Warning: A minimum interocular distance (IOD) of 30 pixels for the detected face is required for this function, below this value it will output an error. Important: Loading a FaceEncoder model is required to use this function.
dispose() → void
Releases all resources used by this FaceEncoder.
getMinimalIod() → int
Gets the minimal interocular distance (IOD) in pixels required to perform a face encoding. Hint: Default value is 30 pixels. It is not recommended to change this value. Warning: Reducing the minimal required IOD to encode smaller face images may create unreliable face templates and significantly degrade recognition performances.
getModel() → FaceModel
Gets the model used to create templates. Hint: Default value is FaceEncoder9A which is the best available algorithm in this SDK in terms of accuracy. Some better accuracy/speed balances can be found by choosing another model.
getProcessingUnit() → ProcessingUnit
Gets the processing unit where to run the encoding process. Hint: Default value is CPU.
getThreadCount() → int
Gets the number of threads to be used for template encoding. Hint: Default value is 1. Allocating more than one thread can increase the speed of the process.
noSuchMethod(Invocation invocation) → dynamic
Invoked when a nonexistent method or property is accessed.
inherited
setMinimalIod(int minimalIod) → void
Sets the minimal interocular distance (IOD) in pixels required to perform a face encoding. Hint: Default value is 30 pixels. It is not recommended to change this value. Warning: Reducing the minimal required IOD to encode smaller face images may create unreliable face templates and significantly degrade recognition performances.
setModel(FaceModel model) → void
Sets the model used to create templates. Hint: Default value is FaceEncoder9A which is the best available algorithm in this SDK in terms of accuracy. Some better accuracy/speed balances can be found by choosing another model.
setProcessingUnit(ProcessingUnit processingUnit) → void
Sets the processing unit where to run the encoding process. Hint: Default value is CPU.
setThreadCount(int threadCount) → void
Sets the number of threads to be used for template encoding. Hint: Default value is 1. Allocating more than one thread can increase the speed of the process.
toString() → String
A string representation of this object.
inherited
warmUp() → void
Gets the face encoder module ready to work by initializing all its internal memory layout. This function can be called after setting all the parameters of the face encoder module. Calling this function is not mandatory as the internal memory layout is automatically initialized in the first call to createTemplate() if missing. Important: Loading a FaceEncoder is required to use this function.

Operators

operator ==(Object other) → bool
The equality operator.
inherited