FaceAI Android SDK v1.0

FaceAI Android SDK is a fast and lightweight SDK that allows you to add Facial Expression and Facial Emotion Recognition AI to Android app. It works on the App’s UI itself and does not send or store any of the biometric data to a server.

Download FaceAI Android SDK v1.1

Released: October 10, 2022

Table of Contents

How to use EnxFaceAIAndroid SDK?

Maven

A Maven version is available to integrate EnxFaceAIAndroid SDK into your application. Modify your App gradle to download the EnableX Android SDK.

  • Edit the build.gradle for your project and add the following code snippet to the allprojects.repositories section:
allprojects {
	repositories {
		maven  {
			url  "https://dl.bintray.com/enablex/maven" 
		}
	}
}
  • Modify build.gradle for your module and add the following code snippet to the dependencies section:
implementation 'XYZ'

Permissions

  • Define Permissions in AndroidManifest.xml
<uses-permission android:name="android.permission.CAMERA"/>
<uses-permission android:name="android.permission.CHANGE_NETWORK_STATE"/>
<uses-permission android:name="android.permission.RECORD_AUDIO"/>
<uses-permission android:name="android.permission.INTERNET" />
<uses-permission android:name="android.permission.ACCESS_WIFI_STATE"/>
<uses-permission android:name="android.permission.ACCESS_NETWORK_STATE"/>
<uses-permission android:name="android.permission.WRITE_EXTERNAL_STORAGE"/>
<uses-permission android:name="android.permission.READ_EXTERNAL_STORAGE"/>
<uses-permission android:name="android.permission.MODIFY_AUDIO_SETTINGS"/>
<uses-permission android:name="android.permission.BLUETOOTH"/>
<uses-permission android:name="android.permission.BLUETOOTH_ADMIN"/>

Features

  • Define Features in AndroidManifest.xml
<uses-feature android:name="android.hardware.camera"/>
<uses-feature android:name="android.hardware.camera.autofocus"/>
<uses-feature android:glEsVersion="0x00020000" android:required="false"/>

Initialise FaceAI

FaceAI analyses Video Streams within an ongoing EnableX video session. To get started with analysis, you must bind the FaceAI Object with the Room in which Video Session is on.

Clas: EnxFaceAI

Method: public void initFaceAI(Activity activity, JSONObject roomMeta, EnxRoom room, EnxStream stream, EnxFaceAIObserver enxFaceAIObserver) – To start analysis on given Stream

Parameters:

  • activity – Current class instance or activity instance
  • roomMeta – NSDictionary Object. It contains information of the connected Room.
  • room – Instance of the connected Room using EnxRTCAndroid native SDK
  • stream – The Local Stream Object which will be analyzed.
  • enxFaceAIObserver – EnxFaceAIObserver Observer is used to return callback

Example: 

/*
After successful room connecction, 
initiate EnxFaceAI on onRoomConnected Callback method
*/
			
EnxFaceAI enxFaceAI = new EnxFaceAI();   				
enxFaceAI.initFaceAI(this, roomMetaJsonObject, room, localStream, this);

Face Detector

This is to detect how many faces are there in a Video Stream. The Event Listener continuously receives data in JSON as the detector tries to detect faces in the changing video frame.

Class: EnxFaceAI

Method: public void enableFaceDetector(boolean enable) – To start/stop analysis

Parameters:

  • enable: Boolean. Set to true to enable/start Face Detector analysis. Set to false to disable/stop analysis

Callback Method:

  • onFaceDetectorData: Gets called repeatedly with Face Detection analysis report with JSON Object. JSON Object Reference appended below:
{
    faces: Array(n),
    rects: Array(n),
    status: string,
    fullFrameDetection: Boolean,
    totalFaces: Number,
    totalFacesChangedFrom: Number | undefined
}

JSON Object Explanation:

  • faces: Array. The detected faces in form of ImageData objects (zero or one; or multiple faces, if fullFrameDetection is true)
  • rects: Array of objects. Describes the bounding boxes (zero or one; or multiple rects, if fullFrameDetection is true)
    • x: Upper left point x coordinate
    • y: Upper left point y coordinate
    • width: Width of the bounding box
    • height: Height of the bounding box
  • status: String. Its status of the face tracker
    • INIT: Detector initializing; zero or many faces could be returned
    • TRACK_OK: Detector is correctly tracking one face; one face is returned
    • RECOVERING: Detector lost a face and attempting to recover and continue tracking; zero faces are returned
  • faces: Array. The detected faces in form of ImageData objects (zero or one; or multiple faces, if fullFrameDetection is true)
  • rects: Array of objects. Describes the bounding boxes (zero or one; or multiple rects, if fullFrameDetection is true)
    • x: Upper left point x coordinate
    • y: Upper left point y coordinate
    • width: Width of the bounding box
    • height: Height of the bounding box
  • status: String. Its status of the face tracker
    • INIT: Detector initializing; zero or many faces could be returned
    • TRACK_OK: Detector is correctly tracking one face; one face is returned
    • RECOVERING: Detector lost a face and attempting to recover and continue tracking; zero faces are returned
  • fullFrameDetection: Boolean. It is true when detection was full-frame and multiple faces can be returned, false otherwise.
  • totalFaces: Number. It represents the total number filtered of faces detected, smoothened over an interval of time. By default, one face is the maximum number. If multi-face is enabled, the maximum is 6. This output is not synchronized with faces and rects arrays, do not use it to count their lengths!
  • totalFacesChangedFrom: Number. Optional. When there is a significant change in the number of faces, it is defined and represents the previous number of faces. In case no change occurred, it is undefined. This output is not synchronized with faces and rects arrays.

Note: if you ever notice some false positives in the events, i.e. the face is detected as present even if there is no one, you can further filter the results by the confidence property of the elements contained in the rects array (e.g. rects[0].confidence > 10)

Example: 

enxFaceAI.enableFaceDetector(true);		// To start analysis 
enxFaceAI.enableFaceDetector(false);		// To stop analysis

// callback
@Override
public void onFaceDetectorData(String type, String value) {
}

Face Pose

This is to analyse face rotation and position in a Video Stream. The Event Listener continuously gets data in JSON as FaceAI detects face rotation in the video stream. Face Rotation angle data is represented in terms of radiants as Pitch, Roll and Yaw.

Class: EnxFaceAI

Method: public void onFacePoseData(String type, String value) – To start/stop analysis

Parameters:

  • enable: Boolean. Set to true to enable/start Face Pose analysis. Set to false to disable/stop analysis

Callback Method:

  • onFacePoseData : Called repeatedly with Face Rotation & Position analysis report with JSON Object. JSON Object Reference appended below:
{	output: {
		pose: {
			pitch: Number, 
			roll: Number, 
			yaw: Number
		}
	}
}

JSON Object Explanation:

  • output: Face Rotation & Position Report
    • pose: Filtered (smoothened) pose rotation angles expressed in radiants as pitch, roll and yaw.

Example: 

enxFaceAI.enableFacePose(true);		// To start analysis
enxFaceAI.enableFacePose(false);	// To stop analysis

// Callback
@Override
public void onFacePoseData(String type, String value) { 
}

Notes:

  • max and min ranges for rotation angles are currently limited to +- (Pi/2) in radians, corresponding to +- (90°) in degrees, for each of the 3 axes
  • the ZERO point is when a face looks straight at the camera

Face Age

This is to analyse and predict face age in a Video Stream. Face Age predicts within an age range. The Event Listener continuously gets data in JSON as FaceAI analyses face age. If the prediction quality is poor, the event is not fired.

Class: EnxFaceAI

Method: public void enableFaceAge(boolean enable) – To start/stop analysis

Parameters:

  • enable: Boolean. Set to true to enable/start Face Age analysis. Set to false to disable/stop analysis

Callback Method:

  • onFaceAgeData – Gets called repeatedly with Face Age analysis report with JSON Object. JSON Object Reference appended below:
{	output: {
		age: {
			-18: Number, 
			18-35: Number, 
			35-51: Number, 
			51-: Number
		}, 
		numericAge: Number
	}
}

JSON Object Explanation:

  • output: Face Age Analysis Report
    • age: Filtered (smoothened) age prediction:
      • -18: Probability Weightage suggesting less than 18 years old.
      • 18-35: Probability Weightage suggesting between 18 to 35 years old.
      • 35-51: Probability Weightage suggesting between 18 35 years old.
      • 51-: Probability Weightage suggesting equal or greater than 51 years old.
    • numericAge: Numeric. Estimated Age

Example: 

enxFaceAI.enableFaceAge(true);	// To start analysis
enxFaceAI.enableFaceAge(false);	// To stop analysis

// Callback
@Override
public void onFaceAgeData(String type, String value) { 
}

Note: in case of poor quality of the prediction, by default, the event is not fired (i.e. skipped for that frame).

Face Gender

This is to analyse face gender in a Video Stream. The Event Listener continuously gets data in JSON as FaceAI analyses face gender.

Class: EnxFaceAI

Method: public void enableFaceGender(boolean enable) – To start/stop analysis

Parameters:

  • enable: Boolean. Set to true to enable/start Face Gender analysis. Set to false to disable/stop analysis

Callback Method:

  • onFaceGenderData – Gets called repeatedly with Face Gender analysis report with JSON Object. JSON Object Reference appended below:
{	output: {
		gender: {
			Female: Number, 
			Male: Number
		}, 
		mostConfident: String
	}
}

JSON Object Explanation:

  • output: Face Gender Report
    • gender: Filtered (smoothened) probabilities of the gender prediction:
      • Female: Probability weightage for gender is female
      • Male: Probability weightage for gender is male
    • mostConfident: Gender name of the most likely result if its smoothened probability is above the threshold, otherwise it is undefined.

Example: 

enxFaceAI.enableFaceGender(true);	// To start analysis
enxFaceAI.enableFaceGender(false);	// To stop analysis

// Callback
@Override
public void onFaceGenderData(String type, String value) { 
}

Face Emotion

This is to analyse face emotions in Video Stream. It analyses basic 8 emotions in a human face, viz. Angry, Disgust, Fear, Happy, Sad, Surprise, Neutral. It also returns most dominate emotion on face. The Event Listener continuously getss data in JSON as FaceAI analyses face emotion.

Class:EnxFaceAI

Method: public void enableFaceEmotion(boolean enable) – To start/stop analysis

Parameters:

  • enable: Boolean. Set to true to enable/start Face Emotion analysis. Set to false to disable/stop analysis

Callback Method:

  • onFaceEmotionData – Called repeatedly with Face Gender analysis report with JSON Object. JSON Object Reference appended below:
{	output: {
		dominantEmotion: String,
		emotion: {
			Angry: Number, 
			Disgust: Number, 
			Fear: Number, 
			Happy: Number, 
			Neutral: Number, 
			Sad: Number, 
			Surprise: Number
		}
	}
}

JSON Object Explanation:

  • output: Face Emotion Report
    • dominantEmotion: Name of Dominant Emotion if present, otherwise it is undefined.
    • emotion: Filtered (smoothened) values of the probability distribution of emotions. The sum of all the probabilities is always 1, each probability in the distribution has a value between 0 and 1.
      • Angry: Probability for Angry.
      • Disgust: Probability for Disgust.
      • Fear: Probability for Fear.
      • Happy: Probability for Happy.
      • Sad: Probability for Sad.
      • Surprise: Probability for Surprise.
      • Neutral: Probability for Neutral.

Example: 

enxFaceAI.enableFaceEmotion(true);	// To start analysis
enxFaceAI.enableFaceEmotion(false);	// To stop analysis

// Callback
@Override
public void onFaceEmotionData(String type, String value) { 
}

Face Features

This is to analyse face features in a Video Stream. The Event Listener continuously gets data in JSON as FaceAI analyses face features.

Class:EnxFaceAI

Method: public void enableFaceFeatures(boolean enable) – To start/stop analysis

Parameters:

  • enable: Boolean. Set to true to enable/start Face Features analysis. Set to false to disable/stop analysis

Callback Method:

  • onFaceFeatureData – Gets called repeatedly with Face Features analysis report with JSON Object. JSON Object Reference appended below:
{	output: {
		features: {
			ArchedEyebrows: Number, 
			Attractive: Number,
			....
			....
		}
	}
}

JSON Object Explanation:

  • output: Face Features Report
    • features: Filtered (smoothened) probabilities of each face independent feature in range 0.0 – 1.0. The following features are evaluated:
      • Arched Eyebrows
      • Attractive
      • Bags Under Eyes
      • Bald
      • Bangs
      • Beard 5 O’Clock Shadow
      • Big Lips
      • Big Nose
      • Black Hair
      • Blond Hair
      • Brown Hair
      • Chubby
      • Double Chin
      • Earrings
      • Eyebrows Bushy
      • Eyeglasses
      • Goatee
      • Gray Hair
      • Hat
      • Heavy Makeup
      • High Cheekbones
      • Lipstick
      • Mouth Slightly Open
      • Mustache
      • Narrow Eyes
      • Necklace
      • Necktie
      • No Beard
      • Oval Face
      • Pale Skin
      • Pointy Nose
      • Receding Hairline
      • Rosy Cheeks
      • Sideburns
      • Straight Hair
      • Wavy Hair

Example: 

enxFaceAI.enableFaceFeatures(true);	// To start analysis
enxFaceAI.enableFaceFeatures(false);	// To stop analysis

// Callback
@Override
public void onFaceFeatureData(String type, String value) { 
}

Face Arousal Valence

This is to analyse face arousal valence in a Video Stream. The Event Listener continuously gets data in JSON as FaceAI analyses Face Arousal Valence.

Class:EnxFaceAI

Method: public void enableFaceArousalValence(boolean enable) – To start/stop analysis

Parameters:

  • enable: Boolean. Set to true to enable/start Face Arousal Valence analysis. Set to false to disable/stop analysis

Callback Method:

  • onFaceArousalValenceData – Gets called repeatedly with Face Arousal Valence analysis report with JSON Object. JSON Object Reference appended below:
{	output: {
		arousalvalence: {
			arousal: Number, 
			valence: Number,
			affects38 : { "Afraid": Number, "Amused": Number, .. },
			affects98 : { "Adventurous": Number, "Afraid": Number, .. },
			quadrant : String
		}
	}
}

JSON Object Explanation:

  • output: Face Arousal Valence Report
    • arousalvalence: Filtered (smoothened) values.
      • arousal: Range 1.0 to 1.0. It represents the degree of engagement (positive arousal), or disengagement (negative arousal).
      • valence: Range -1.0 to 1.0. It represents the degree of pleasantness (positive valence), or unpleasantness (negative valence).
  • output: Face Arousal Valence Report
    • arousalvalence: Filtered (smoothened) values.
      • arousal: Range 1.0 to 1.0. It represents the degree of engagement (positive arousal), or disengagement (negative arousal).
      • valence: Range -1.0 to 1.0. It represents the degree of pleasantness (positive valence), or unpleasantness (negative valence).
      • affects38: An object containing the smoothened probabilities of the 38 affects in range [0.00, 1.00]: Afraid, Amused, Angry, Annoyed, Uncomfortable, Anxious, Apathetic, Astonished, Bored, Worried, Calm, Conceited, Contemplative, Content, Convinced, Delighted, Depressed, Determined, Disappointed, Discontented, Distressed, Embarrassed, Enraged, Excited, Feel Well, Frustrated, Happy, Hopeful, Impressed, Melancholic, Peaceful, Pensive, Pleased, Relaxed, Sad, Satisfied, Sleepy, Tired
      • affects98: An object containing the smoothened probabilities of the 98 affects in range [0.00, 1.00]: Adventurous, Afraid, Alarmed, Ambitious, Amorous, Amused, Wavering, Angry, Annoyed, Anxious, Apathetic, Aroused, Ashamed, Worried, Astonished, At Ease, Attentive, Bellicose, Bitter, Bored, Calm, Compassionate, Conceited, Confident, Conscientious, Contemplative, Contemptuous, Content, Convinced, Courageous, Defient, Dejected, Delighted, Depressed, Desperate, Despondent, Determined, Disappointed, Discontented, Disgusted, Dissatisfied, Distressed, Distrustful, Doubtful, Droopy, Embarrassed, Enraged, Enthusiastic, Envious, Excited, Expectant, Feel Guilt, Feel Well, Feeling Superior, Friendly, Frustrated, Glad, Gloomy, Happy, Hateful, Hesitant, Hopeful, Hostile, Impatient, Impressed, Indignant, Insulted, Interested, Jealous, Joyous, Languid, Light Hearted, Loathing, Longing, Lusting, Melancholic, Miserable, Passionate, Peaceful, Pensive, Pleased, Polite, Relaxed, Reverent, Sad, Satisfied, Selfconfident, Serene, Serious, Sleepy, Solemn, Startled, Suspicious, Taken Aback, Tense, Tired, Triumphant, Uncomfortable
      • quadrant: A string representing one of the four quadrants in the cirumplex model of affect (“High Control”, “Obstructive”, “Low Control”, “Conductive”, or “Neutral”)

Example: 

enxFaceAI.enableFaceArousalValence(true);	// To start analysis
enxFaceAI.enableFaceArousalValence(false);	// To stop analysis

// Callback
@Override
public void onFaceArousalValenceData(String type, String value) { 
}

Face Attention

This is to analyse face attention in a Video Stream. The Event Listener continuously get data in JSON as FaceAI analyses face attention.

Class:EnxFaceAI

Method: public void enableFaceAttention(boolean enable) – To start/stop analysis

Parameters:

  • enable: Boolean. Set to true to enable/start Face Attention analysis. Set to false to disable/stop analysis

Callback Method:

  • onFaceAttentionData – Gets called repeatedly with Face Attention analysis report with JSON Object. JSON Object Reference appended below:
{	output: {
		attention: Number
	}
}

JSON Object Explanation:

  • output: Face Attention Report
    • attention: Filtered value (smoothened) in range [0.0, 1.0]. A value close to 1.0 represents attention, a value close to 0.0 represents distraction.

Example: 

enxFaceAI.enableFaceAttention(true);	// To start analysis
enxFaceAI.enableFaceAttention(false);	// To stop analysis

// Callback
@Override
public void onFaceAttentionData(String type, String value) { 
}

Face Wish

This is to analyze face wish in a Video Stream. The Event Listener keeps getting data in JSON as FaceAI keeps analyzing face wish.

Class: EnxFaceAI

Method: public void enableFaceWish(boolean enable) – To start/stop analysis

Parameters:

  • enable: Boolean. Set to true to enable/start Face Wish analysis. Set to false to disable/stop analysis

Callback Method:

  • onFaceWishData – Get called notifies repeatedly with Face Wish analysis report with JSON Object. JSON Object Reference appended below:
{	output: {
		wish: Number
	}
}

JSON Object Explanation:

  • output: Face Wish Report
    • wish: Filtered value (smoothened) in range [0, 1.0]. A value closer to 0 represents a lower wish, a value closer to 1.0 represents a higher wish.

Example: 

enxFaceAI.enableFaceWish(true);	// To start analysis
enxFaceAI.enableFaceWish(false);// To stop analysis

// Callback
@Override
public void onFaceWishData(String type, String value) { 
}