With face detection, you can get the information you need to perform tasks like embellishing selfies and portraits, or generating avatars from a user's photo. Because ML Kit can perform face detection in real time, you can use it in applications like video chat or games that respond to the player's expressions.
See the ML Kit quickstart sample on GitHub for an example of this API in use.
build.gradle
file, make sure to include Google's Maven repository in both your buildscript
and allprojects
sections.app/build.gradle
):dependencies { // ...implementation ‘com.google.firebase:firebase-ml-vision:23.0.0’
implementation ‘com.google.firebase:firebase-ml-vision-face-model:18.0.0’
}
apply plugin: ‘com.google.gms.google-services’
4- Optional but recommended: Configure your app to automatically download the ML model to the device after your app is installed from the Play Store.
To do so, add the following declaration to your app’s AndroidManifest.xml
file:
<application …>
…
<meta-data
android:name=“com.google.firebase.ml.vision.DEPENDENCIES”
android:value=“face” />
<!-- To use multiple models: android:value=“face,model2,model3” -->
</application>
If you do not enable install-time model downloads, the model will be downloaded the first time you run the detector. Requests you make before the download has completed will produce no results. Input image guidelines
For ML Kit to accurately detect faces, input images must contain faces that are represented by sufficient pixel data. In general, each face you want to detect in an image should be at least 100x100 pixels. If you want to detect the contours of faces, ML Kit requires higher resolution input: each face should be at least 200x200 pixels.
If you are detecting faces in a real-time application, you might also want to consider the overall dimensions of the input images. Smaller images can be processed faster, so to reduce latency, capture images at lower resolutions (keeping in mind the above accuracy requirements) and ensure that the subject’s face occupies as much of the image as possible. Also see Tips to improve real-time performance.
Poor image focus can hurt accuracy. If you aren’t getting acceptable results, try asking the user to recapture the image.
The orientation of a face relative to the camera can also affect what facial features ML Kit detects. See Face Detection Concepts.
Before you apply face detection to an image, if you want to change any of the face detector’s default settings, specify those settings with a FirebaseVisionFaceDetectorOptions
object. You can change the following settings:
For example:
Java Android
// High-accuracy landmark detection and face classification
FirebaseVisionFaceDetectorOptions highAccuracyOpts =
new FirebaseVisionFaceDetectorOptions.Builder()
.setPerformanceMode(FirebaseVisionFaceDetectorOptions.ACCURATE)
.setLandmarkMode(FirebaseVisionFaceDetectorOptions.ALL_LANDMARKS)
.setClassificationMode(FirebaseVisionFaceDetectorOptions.ALL_CLASSIFICATIONS)
.build();// Real-time contour detection of multiple faces
FirebaseVisionFaceDetectorOptions realTimeOpts =
new FirebaseVisionFaceDetectorOptions.Builder()
.setContourMode(FirebaseVisionFaceDetectorOptions.ALL_CONTOURS)
.build();
FaceDetectionActivity.java
Kotlin Android
// High-accuracy landmark detection and face classification
val highAccuracyOpts = FirebaseVisionFaceDetectorOptions.Builder()
.setPerformanceMode(FirebaseVisionFaceDetectorOptions.ACCURATE)
.setLandmarkMode(FirebaseVisionFaceDetectorOptions.ALL_LANDMARKS)
.setClassificationMode(FirebaseVisionFaceDetectorOptions.ALL_CLASSIFICATIONS)
.build()// Real-time contour detection of multiple faces
val realTimeOpts = FirebaseVisionFaceDetectorOptions.Builder()
.setContourMode(FirebaseVisionFaceDetectorOptions.ALL_CONTOURS)
.build()
FaceDetectionActivity.kt
To detect faces in an image, create a FirebaseVisionImage
object from either a Bitmap
, media.Image
, ByteBuffer
, byte array, or a file on the device. Then, pass the FirebaseVisionImage
object to the FirebaseVisionFaceDetector
's detectInImage
method.For face recognition, you should use an image with dimensions of at least 480x360 pixels. If you are recognizing faces in real time, capturing frames at this minimum resolution can help reduce latency.
FirebaseVisionImage
object from your image.FirebaseVisionImage
object from a media.Image
object, such as when capturing an image from a device’s camera, pass the media.Image
object and the image’s rotation to FirebaseVisionImage.fromMediaImage()
.OnImageCapturedListener
and ImageAnalysis.Analyzer
classes calculate the rotation value for you, so you just need to convert the rotation to one of ML Kit’s ROTATION_
constants before calling FirebaseVisionImage.fromMediaImage()
:Java Android
private class YourAnalyzer implements ImageAnalysis.Analyzer {private int degreesToFirebaseRotation(int degrees) {
switch (degrees) {
case 0:
return FirebaseVisionImageMetadata.ROTATION_0;
case 90:
return FirebaseVisionImageMetadata.ROTATION_90;
case 180:
return FirebaseVisionImageMetadata.ROTATION_180;
case 270:
return FirebaseVisionImageMetadata.ROTATION_270;
default:
throw new IllegalArgumentException(
“Rotation must be 0, 90, 180, or 270.”);
}
}@Override
public void analyze(ImageProxy imageProxy, int degrees) {
if (imageProxy == null || imageProxy.getImage() == null) {
return;
}
Image mediaImage = imageProxy.getImage();
int rotation = degreesToFirebaseRotation(degrees);
FirebaseVisionImage image =
FirebaseVisionImage.fromMediaImage(mediaImage, rotation);
// Pass image to an ML Kit Vision API
// …
}
}
Kotlin Android
private class YourImageAnalyzer : ImageAnalysis.Analyzer {
private fun degreesToFirebaseRotation(degrees: Int): Int = when(degrees) {
0 -> FirebaseVisionImageMetadata.ROTATION_0
90 -> FirebaseVisionImageMetadata.ROTATION_90
180 -> FirebaseVisionImageMetadata.ROTATION_180
270 -> FirebaseVisionImageMetadata.ROTATION_270
else -> throw Exception(“Rotation must be 0, 90, 180, or 270.”)
}override fun analyze(imageProxy: ImageProxy?, degrees: Int) {
val mediaImage = imageProxy?.image
val imageRotation = degreesToFirebaseRotation(degrees)
if (mediaImage != null) {
val image = FirebaseVisionImage.fromMediaImage(mediaImage, imageRotation)
// Pass image to an ML Kit Vision API
// …
}
}
}
If you don’t use a camera library that gives you the image’s rotation, you can calculate it from the device’s rotation and the orientation of camera sensor in the device:
Java Android
private static final SparseIntArray ORIENTATIONS = new SparseIntArray();
static {
ORIENTATIONS.append(Surface.ROTATION_0, 90);
ORIENTATIONS.append(Surface.ROTATION_90, 0);
ORIENTATIONS.append(Surface.ROTATION_180, 270);
ORIENTATIONS.append(Surface.ROTATION_270, 180);
}/**
* Get the angle by which an image must be rotated given the device’s current
* orientation.
*/
@RequiresApi(api = Build.VERSION_CODES.LOLLIPOP)
private int getRotationCompensation(String cameraId, Activity activity, Context context)
throws CameraAccessException {
// Get the device’s current rotation relative to its “native” orientation.
// Then, from the ORIENTATIONS table, look up the angle the image must be
// rotated to compensate for the device’s rotation.
int deviceRotation = activity.getWindowManager().getDefaultDisplay().getRotation();
int rotationCompensation = ORIENTATIONS.get(deviceRotation);// On most devices, the sensor orientation is 90 degrees, but for some
// devices it is 270 degrees. For devices with a sensor orientation of
// 270, rotate the image an additional 180 ((270 + 270) % 360) degrees.
CameraManager cameraManager = (CameraManager) context.getSystemService(CAMERA_SERVICE);
int sensorOrientation = cameraManager
.getCameraCharacteristics(cameraId)
.get(CameraCharacteristics.SENSOR_ORIENTATION);
rotationCompensation = (rotationCompensation + sensorOrientation + 270) % 360;// Return the corresponding FirebaseVisionImageMetadata rotation value.
int result;
switch (rotationCompensation) {
case 0:
result = FirebaseVisionImageMetadata.ROTATION_0;
break;
case 90:
result = FirebaseVisionImageMetadata.ROTATION_90;
break;
case 180:
result = FirebaseVisionImageMetadata.ROTATION_180;
break;
case 270:
result = FirebaseVisionImageMetadata.ROTATION_270;
break;
default:
result = FirebaseVisionImageMetadata.ROTATION_0;
Log.e(TAG, "Bad rotation value: " + rotationCompensation);
}
return result;
}
VisionImage.java
Kotlin Android
private val ORIENTATIONS = SparseIntArray()init {
ORIENTATIONS.append(Surface.ROTATION_0, 90)
ORIENTATIONS.append(Surface.ROTATION_90, 0)
ORIENTATIONS.append(Surface.ROTATION_180, 270)
ORIENTATIONS.append(Surface.ROTATION_270, 180)
}
/**
* Get the angle by which an image must be rotated given the device’s current
* orientation.
*/
@RequiresApi(api = Build.VERSION_CODES.LOLLIPOP)
@Throws(CameraAccessException::class)
private fun getRotationCompensation(cameraId: String, activity: Activity, context: Context): Int {
// Get the device’s current rotation relative to its “native” orientation.
// Then, from the ORIENTATIONS table, look up the angle the image must be
// rotated to compensate for the device’s rotation.
val deviceRotation = activity.windowManager.defaultDisplay.rotation
var rotationCompensation = ORIENTATIONS.get(deviceRotation)// On most devices, the sensor orientation is 90 degrees, but for some
// devices it is 270 degrees. For devices with a sensor orientation of
// 270, rotate the image an additional 180 ((270 + 270) % 360) degrees.
val cameraManager = context.getSystemService(CAMERA_SERVICE) as CameraManager
val sensorOrientation = cameraManager
.getCameraCharacteristics(cameraId)
.get(CameraCharacteristics.SENSOR_ORIENTATION)!!
rotationCompensation = (rotationCompensation + sensorOrientation + 270) % 360// Return the corresponding FirebaseVisionImageMetadata rotation value.
val result: Int
when (rotationCompensation) {
0 -> result = FirebaseVisionImageMetadata.ROTATION_0
90 -> result = FirebaseVisionImageMetadata.ROTATION_90
180 -> result = FirebaseVisionImageMetadata.ROTATION_180
270 -> result = FirebaseVisionImageMetadata.ROTATION_270
else -> {
result = FirebaseVisionImageMetadata.ROTATION_0
Log.e(TAG, “Bad rotation value: $rotationCompensation”)
}
}
return result
}
VisionImage.kt
Then, pass the media.Image
object and the rotation value to FirebaseVisionImage.fromMediaImage()
:
Java Android
FirebaseVisionImage image = FirebaseVisionImage.fromMediaImage(mediaImage, rotation);
VisionImage.java
Kotlin Android
val image = FirebaseVisionImage.fromMediaImage(mediaImage, rotation)
VisionImage.kt
FirebaseVisionImage
object from a file URI, pass the app context and file URI to FirebaseVisionImage.fromFilePath()
. This is useful when you use an ACTIONGETCONTENT
intent to prompt the user to select an image from their gallery app.Java Android
FirebaseVisionImage image;
try {
image = FirebaseVisionImage.fromFilePath(context, uri);
} catch (IOException e) {
e.printStackTrace();
}
VisionImage.java
Kotlin Android
val image: FirebaseVisionImage
try {
image = FirebaseVisionImage.fromFilePath(context, uri)
} catch (e: IOException) {
e.printStackTrace()
}
VisionImage.kt
FirebaseVisionImage
object from a ByteBuffer
or a byte array, first calculate the image rotation as described above for media.Image
input.Then, create a FirebaseVisionImageMetadata
object that contains the image’s height, width, color encoding format, and rotation:
Java Android
FirebaseVisionImageMetadata metadata = new FirebaseVisionImageMetadata.Builder()
.setWidth(480) // 480x360 is typically sufficient for
.setHeight(360) // image recognition
.setFormat(FirebaseVisionImageMetadata.IMAGE_FORMAT_NV21)
.setRotation(rotation)
.build();
VisionImage.java
Kotlin Android
val metadata = FirebaseVisionImageMetadata.Builder()
.setWidth(480) // 480x360 is typically sufficient for
.setHeight(360) // image recognition
.setFormat(FirebaseVisionImageMetadata.IMAGE_FORMAT_NV21)
.setRotation(rotation)
.build()
VisionImage.kt
FirebaseVisionImage
object:Java Android
FirebaseVisionImage image = FirebaseVisionImage.fromByteBuffer(buffer, metadata);
// Or: FirebaseVisionImage image = FirebaseVisionImage.fromByteArray(byteArray, metadata);
VisionImage.java
Kotlin Android
val image = FirebaseVisionImage.fromByteBuffer(buffer, metadata)
// Or: val image = FirebaseVisionImage.fromByteArray(byteArray, metadata)
VisionImage.kt
FirebaseVisionImage
object from a Bitmap
object:Java Android
FirebaseVisionImage image = FirebaseVisionImage.fromBitmap(bitmap);
VisionImage.java
Kotlin Android
val image = FirebaseVisionImage.fromBitmap(bitmap)
VisionImage.kt
The image represented by the Bitmap
object must be upright, with no additional rotation required.
2 - Get an instance of FirebaseVisionFaceDetector
:
Java Android
FirebaseVisionFaceDetector detector = FirebaseVision.getInstance()
.getVisionFaceDetector(options);
FaceDetectionActivity.java
Kotlin Android
val detector = FirebaseVision.getInstance()
.getVisionFaceDetector(options)
FaceDetectionActivity.kt
3 - Finally, pass the image to the detectInImage
method:
Java Android
Task<List<FirebaseVisionFace>> result =
detector.detectInImage(image)
.addOnSuccessListener(
new OnSuccessListener<List<FirebaseVisionFace>>() {
@Override
public void onSuccess(List<FirebaseVisionFace> faces) {
// Task completed successfully
// …
}
})
.addOnFailureListener(
new OnFailureListener() {
@Override
public void onFailure(@NonNull Exception e) {
// Task failed with an exception
// …
}
});
FaceDetectionActivity.java
Kotlin Android
val result = detector.detectInImage(image)
.addOnSuccessListener { faces ->
// Task completed successfully
// …
}
.addOnFailureListener(
object : OnFailureListener {
override fun onFailure(e: Exception) {
// Task failed with an exception
// …
}
})
FaceDetectionActivity.kt
If the face recognition operation succeeds, a list of FirebaseVisionFace
objects will be passed to the success listener. Each FirebaseVisionFace
object represents a face that was detected in the image. For each face, you can get its bounding coordinates in the input image, as well as any other information you configured the face detector to find. For example:
Java Android
for (FirebaseVisionFace face : faces) {
Rect bounds = face.getBoundingBox();
float rotY = face.getHeadEulerAngleY(); // Head is rotated to the right rotY degrees
float rotZ = face.getHeadEulerAngleZ(); // Head is tilted sideways rotZ degrees// If landmark detection was enabled (mouth, ears, eyes, cheeks, and
// nose available):
FirebaseVisionFaceLandmark leftEar = face.getLandmark(FirebaseVisionFaceLandmark.LEFT_EAR);
if (leftEar != null) {
FirebaseVisionPoint leftEarPos = leftEar.getPosition();
}// If contour detection was enabled:
List<FirebaseVisionPoint> leftEyeContour =
face.getContour(FirebaseVisionFaceContour.LEFT_EYE).getPoints();
List<FirebaseVisionPoint> upperLipBottomContour =
face.getContour(FirebaseVisionFaceContour.UPPER_LIP_BOTTOM).getPoints();// If classification was enabled:
if (face.getSmilingProbability() != FirebaseVisionFace.UNCOMPUTED_PROBABILITY) {
float smileProb = face.getSmilingProbability();
}
if (face.getRightEyeOpenProbability() != FirebaseVisionFace.UNCOMPUTED_PROBABILITY) {
float rightEyeOpenProb = face.getRightEyeOpenProbability();
}// If face tracking was enabled:
if (face.getTrackingId() != FirebaseVisionFace.INVALID_ID) {
int id = face.getTrackingId();
}
}
FaceDetectionActivity.java
Kotlin Android
for (face in faces) {
val bounds = face.boundingBox
val rotY = face.headEulerAngleY // Head is rotated to the right rotY degrees
val rotZ = face.headEulerAngleZ // Head is tilted sideways rotZ degrees// If landmark detection was enabled (mouth, ears, eyes, cheeks, and
// nose available):
val leftEar = face.getLandmark(FirebaseVisionFaceLandmark.LEFT_EAR)
leftEar?.let {
val leftEarPos = leftEar.position
}// If contour detection was enabled:
val leftEyeContour = face.getContour(FirebaseVisionFaceContour.LEFT_EYE).points
val upperLipBottomContour = face.getContour(FirebaseVisionFaceContour.UPPER_LIP_BOTTOM).points// If classification was enabled:
if (face.smilingProbability != FirebaseVisionFace.UNCOMPUTED_PROBABILITY) {
val smileProb = face.smilingProbability
}
if (face.rightEyeOpenProbability != FirebaseVisionFace.UNCOMPUTED_PROBABILITY) {
val rightEyeOpenProb = face.rightEyeOpenProbability
}// If face tracking was enabled:
if (face.trackingId != FirebaseVisionFace.INVALID_ID) {
val id = face.trackingId
}
}
FaceDetectionActivity.kt
When you have face contour detection enabled, you get a list of points for each facial feature that was detected. These points represent the shape of the feature. See the Face Detection Concepts Overview for details about how contours are represented.
The following image illustrates how these points map to a face (click the image to enlarge):
If you want to use face detection in a real-time application, follow these guidelines to achieve the best framerates:
FAST
mode (enabled by default).VisionProcessorBase
class in the quickstart sample app for an example.CameraSourcePreview
and GraphicOverlay
classes in the quickstart sample app for an example.ImageFormat.YUV_420_888
format.ImageFormat.NV21
format.#firebase #machine-learning #deep-learning #data-science #image