FaceAnalyser class

Provides methods for analysing the characteristics of portrait image.

Implemented types

Constructors

FaceAnalyser()
Creates a new instance of the FaceAnalyser class.
FaceAnalyser.fromHandle(Pointer<id3FaceAnalyser> handle)
Creates a new instance of the FaceAnalyser class.

Properties

expressionSensibility ↔ int
Sensibility of the expression classifier. The higher the value, the more sensitive the algorithm will be, meaning that it will be less likely to estimate neutral expression out of the detected face. Hint: Default value is 60.
getter/setter pair
handle → Pointer<id3FaceAnalyser>
Gets the native handle. return The native handle.
no setter
hashCode → int
The hash code for this object.
no setterinherited
overExposureSensibility ↔ int
Sensibility of the over-exposure classifier, from 0 to 255. The lower the value, the more sensitive the algorithm will be, meaning that it will be more likely to estimate over-exposed face images. Hint: Default value is 188.
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 face analysis. Hint: Default value is 1. Allocating more than one thread can increase the speed of the process.
getter/setter pair
underExposureSensibility ↔ int
Sensibility of the under-exposure classifier, from 0 to 255. The higher the value, the more sensitive the algorithm will be, meaning that it will be more likely to estimate under-exposed face images. Hint: Default value is 66.
getter/setter pair

Methods

applyAlphaMask(Image image, Image mask) → Image
Applies an alpha mask to suppress the background and returns a 32-bit BGRA image.
applyMask(Image image, Image mask, int red, int green, int blue) → Image
Applies a mask to replace the background with the specified color and returns a 24-bit BGR image.
checkColorizedImage(Image image) → bool
Verifies if an image is colorized or grayscale.
computeAge(Image image, DetectedFace detectedFace) → int
Computes the age of a detected face. Important: Loading the FaceAgeEstimator model is required to use this function.
computeAttributes(Image image, DetectedFace detectedFace) → FaceAttributes
Computes the attributes of a detected face. Important: Loading the model FaceAttributesClassifier is required to use this function.
computeBackgroundUniformity(Image image, DetectedFace detectedFace) → BackgroundUniformity
Computes the background uniformity behind a detected face. This function must be used for a portrait image with only one face in it. A high uniformity score means that the background is uniform. Important: Loading the model FaceBackgroundUniformity is required to use this function.
computeExpression(Image image, DetectedFace detectedFace) → FaceExpression
Computes the expression of a detected face. Important: Loading the FaceExpressionClassifier model is required to use this function.
computeEyeGaze(Image image, DetectedFace detectedFace, PointList landmarks) → EyeGaze
Computes the eye gaze of a detected face. Important: Loading the EyeGazeEstimator model is required to use this function.
computeEyeOpenness(Image image, DetectedFace detectedFace, PointList landmarks) → List<int>
Computes the eye openness of a detected face. The minimum recommanded value for is 90. Important: Loading the EyeOpennessDetector model is required to use this function.
computeEyeRedness(Image image, DetectedFace detectedFace, PointList landmarks) → List<int>
Computes the eye redness of a detected face. The maximum recommanded value for an ICAO-compliant portrait is 10. Important: Loading the EyeRednessDetector model is required to use this function.
computeGeometricAttributes(Image image, DetectedFace detectedFace, PointList landmarks) → GeometricAttributes
Computes the geometric attributes of a detected face. This function must be used for a portrait image with only one face in it.
computeGlassesAttributes(Image image, DetectedFace detectedFace, PointList landmarks) → GlassesAttributes
Computes the glasses attributes of a detected face. This function must be used for a portrait image with only one face in it.
computeLandmarks(Image image, DetectedFace detectedFace) → PointList
Computes 68 landmarks of a detected face. Important: Loading the FaceLandmarksEstimator model is required to use this function.
computeNoise(Image image) → int
Measures the image noise.
computePhotographicAttributes(Image image, DetectedFace detectedFace, PointList landmarks) → PhotographicAttributes
Computes the photographic attributes of a detected face. This function must be used for a portrait image with only one face in it.
computePose(DetectedFace detectedFace) → FacePose
Computes the pose of a detected face. Important: Loading the FacePoseEstimator model is required to use this function.
computePoseWithLandmarks(DetectedFace detectedFace, PointList landmarks) → FacePose
Computes the pose of a detected face using the specified 68-point landmarks. Loading the model FacePoseEstimator1A is required to use this function.
detectFaceMask(Image image, DetectedFace detectedFace) → int
Detects the presence of a face mask on a detected face. A high score means that there is a high chance that the person is wearing a mask. The minimum recommended threshold is 15. Important: Loading the FaceMaskClassifier, model is required to use this function.
detectOcclusions(Image image, DetectedFace detectedFace) → FaceOcclusionScores
Detects occlusions on the subject's face. Important: This function requires the FaceOcclusionDetector model to be loaded.
dispose() → void
Releases all resources used by this FaceAnalyser.
getExpressionSensibility() → int
Gets the sensibility of the expression classifier. The higher the value, the more sensitive the algorithm will be, meaning that it will be less likely to estimate neutral expression out of the detected face. Hint: Default value is 60.
getOverExposureSensibility() → int
Gets the sensibility of the over-exposure classifier, from 0 to 255. The lower the value, the more sensitive the algorithm will be, meaning that it will be more likely to estimate over-exposed face images. Hint: Default value is 188.
getThreadCount() → int
Gets the number of threads to be used for face analysis. Hint: Default value is 1. Allocating more than one thread can increase the speed of the process.
getUnderExposureSensibility() → int
Gets the sensibility of the under-exposure classifier, from 0 to 255. The higher the value, the more sensitive the algorithm will be, meaning that it will be more likely to estimate under-exposed face images. Hint: Default value is 66.
noSuchMethod(Invocation invocation) → dynamic
Invoked when a nonexistent method or property is accessed.
inherited
removeCompressionArtifacts(Image image) → Image
Upscale and enhance the image of a face. Important: This methods requires the CompressionArtifactRemover model to be loaded.
segmentBackground(Image image) → Image
Computes face segmentation mask for background removal. Important: This methods requires the FaceBackgroundSegmenter model to be loaded.
segmentFace(Image image) → Image
Computes a segmentation map of a face. Important: This methods requires the FaceSegmenter model to be loaded.
setExpressionSensibility(int expressionSensibility) → void
Sets the sensibility of the expression classifier. The higher the value, the more sensitive the algorithm will be, meaning that it will be less likely to estimate neutral expression out of the detected face. Hint: Default value is 60.
setOverExposureSensibility(int overExposureSensibility) → void
Sets the sensibility of the over-exposure classifier, from 0 to 255. The lower the value, the more sensitive the algorithm will be, meaning that it will be more likely to estimate over-exposed face images. Hint: Default value is 188.
setThreadCount(int threadCount) → void
Sets the number of threads to be used for face analysis. Hint: Default value is 1. Allocating more than one thread can increase the speed of the process.
setUnderExposureSensibility(int underExposureSensibility) → void
Sets the sensibility of the under-exposure classifier, from 0 to 255. The higher the value, the more sensitive the algorithm will be, meaning that it will be more likely to estimate under-exposed face images. Hint: Default value is 66.
toString() → String
A string representation of this object.
inherited

Operators

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