Mendeteksi Wajah dengan ML Kit di Android

Anda dapat menggunakan ML Kit untuk mendeteksi wajah dalam gambar dan video.

Sebelum memulai

1. Tambahkan Firebase ke project Android jika Anda belum melakukannya.
2. Tambahkan dependensi untuk library Android ML Kit ke file Gradle modul (level aplikasi), biasanya app/build.gradle:

   apply plugin: 'com.android.application'
   apply plugin: 'com.google.gms.google-services'
   
   dependencies {
     // ...
   
     implementation 'com.google.firebase:firebase-ml-vision:24.0.3'
     // If you want to detect face contours (landmark detection and classification
     // don't require this additional model):
     implementation 'com.google.firebase:firebase-ml-vision-face-model:20.0.1'
   }
   

3. Opsional tetapi direkomendasikan: Konfigurasi aplikasi agar mendownload model ML secara otomatis ke perangkat setelah aplikasi diinstal dari Play Store.

   Untuk melakukannya, tambahkan deklarasi berikut ke file AndroidManifest.xml aplikasi Anda:

   <application ...>
     ...
     <meta-data
         android:name="com.google.firebase.ml.vision.DEPENDENCIES"
         android:value="face" />
     <!-- To use multiple models: android:value="face,model2,model3" -->
   </application>
   

   Jika Anda tidak mengaktifkan download model waktu-instal, model ini akan didownload saat pertama kali Anda menjalankan detektor. Permintaan yang Anda buat sebelum download selesai tidak akan memberikan hasil apa pun.

Pedoman gambar input

Agar ML Kit dapat secara akurat mengenali wajah, gambar input harus berisi wajah yang diwakili oleh data piksel yang memadai. Secara umum, setiap wajah yang ingin dideteksi dalam suatu gambar harus berukuran minimal 100x100 piksel. Jika Anda ingin mendeteksi kontur wajah, ML Kit membutuhkan input resolusi yang lebih tinggi: setiap wajah harus berukuran minimal 200x200 piksel.

Jika ingin mendeteksi wajah dalam aplikasi real-time, Anda mungkin perlu mempertimbangkan dimensi gambar input secara keseluruhan. Gambar yang lebih kecil dapat diproses lebih cepat. Jadi, untuk mengurangi latensi, ambil gambar dengan resolusi yang lebih rendah (dengan tetap memperhatikan persyaratan akurasi di atas), dan pastikan bahwa wajah subjek menempati gambar seluas mungkin. Baca juga Tips untuk meningkatkan performa real-time.

Fokus gambar yang buruk dapat mengurangi akurasi. Jika tidak memperoleh hasil yang dapat diterima, coba minta pengguna untuk mengambil ulang gambar.

Orientasi wajah terhadap arah kamera juga dapat memengaruhi fitur wajah yang terdeteksi oleh ML Kit. Baca Konsep Deteksi Wajah.

1. Mengonfigurasi detektor wajah

Contoh:

// 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();

// 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()

2. Menjalankan detektor wajah

Untuk pengenalan wajah, Anda harus menggunakan gambar dengan dimensi yang berukuran minimal 480x360 piksel. Jika Anda mengenali wajah secara real-time, pengambilan frame pada resolusi minimum ini dapat membantu mengurangi latensi.

1. Buat objek FirebaseVisionImage dari gambar Anda.

   • Untuk membuat objek FirebaseVisionImage dari objek media.Image, seperti saat mengambil gambar dari kamera perangkat, teruskan objek media.Image dan nilai rotasi gambar ke FirebaseVisionImage.fromMediaImage().

     Jika Anda menggunakan library CameraX, class OnImageCapturedListener dan ImageAnalysis.Analyzer menghitung nilai rotasi, sehingga Anda hanya perlu mengonversi rotasi ke salah satu konstanta ROTATION_ ML Kit sebelum memanggil FirebaseVisionImage.fromMediaImage():

     Java

     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+KTX

     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
                 // ...
             }
         }
     }
     

     Jika tidak menggunakan library kamera yang memberikan nilai rotasi gambar, Anda dapat menghitungnya dari rotasi perangkat dan orientasi sensor kamera pada perangkat:

     Java

     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+KTX

     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

     Lalu, teruskan objek media.Image dan nilai rotasi ke FirebaseVisionImage.fromMediaImage():

     Java

     FirebaseVisionImage image = FirebaseVisionImage.fromMediaImage(mediaImage, rotation);
     VisionImage.java

     Kotlin+KTX

     val image = FirebaseVisionImage.fromMediaImage(mediaImage, rotation)
     VisionImage.kt

   • Untuk membuat objek FirebaseVisionImage dari URI file, teruskan konteks aplikasi dan URI file ke FirebaseVisionImage.fromFilePath(). Hal ini berguna saat Anda menggunakan intent ACTION_GET_CONTENT untuk meminta pengguna memilih gambar dari aplikasi galeri mereka.

     Java

     FirebaseVisionImage image;
     try {
         image = FirebaseVisionImage.fromFilePath(context, uri);
     } catch (IOException e) {
         e.printStackTrace();
     }
     VisionImage.java

     Kotlin+KTX

     val image: FirebaseVisionImage
     try {
         image = FirebaseVisionImage.fromFilePath(context, uri)
     } catch (e: IOException) {
         e.printStackTrace()
     }
     VisionImage.kt

   • Untuk membuat objek FirebaseVisionImage dari ByteBuffer atau array byte, pertama-tama hitung rotasi gambar seperti yang dijelaskan di atas untuk input media.Image.

     Lalu, buat objek FirebaseVisionImageMetadata yang berisi tinggi, lebar, format encoding warna, dan rotasi gambar:

     Java

     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+KTX

     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

     Gunakan buffering atau array, dan objek metadata, untuk membuat objek FirebaseVisionImage:

     Java

     FirebaseVisionImage image = FirebaseVisionImage.fromByteBuffer(buffer, metadata);
     // Or: FirebaseVisionImage image = FirebaseVisionImage.fromByteArray(byteArray, metadata);
     VisionImage.java

     Kotlin+KTX

     val image = FirebaseVisionImage.fromByteBuffer(buffer, metadata)
     // Or: val image = FirebaseVisionImage.fromByteArray(byteArray, metadata)
     VisionImage.kt

   • Untuk membuat objek FirebaseVisionImage dari objek Bitmap:

     Java

     FirebaseVisionImage image = FirebaseVisionImage.fromBitmap(bitmap);
     VisionImage.java

     Kotlin+KTX

     val image = FirebaseVisionImage.fromBitmap(bitmap)
     VisionImage.kt

     Gambar yang diwakili oleh objek Bitmap harus berposisi tegak, tanpa perlu rotasi tambahan.

2. Dapatkan instance FirebaseVisionFaceDetector:

   Java

   FirebaseVisionFaceDetector detector = FirebaseVision.getInstance()
           .getVisionFaceDetector(options);

   Kotlin+KTX

   val detector = FirebaseVision.getInstance()
           .getVisionFaceDetector(options)

3. Terakhir, teruskan gambar ke metode detectInImage:

   Java

   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
                                   // ...
                               }
                           });

   Kotlin+KTX

   val result = detector.detectInImage(image)
           .addOnSuccessListener { faces ->
               // Task completed successfully
               // ...
           }
           .addOnFailureListener { e ->
               // Task failed with an exception
               // ...
           }

3. Mendapatkan informasi tentang wajah yang terdeteksi

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();
    }
}

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
    }
}

Contoh kontur wajah

Ketika mengaktifkan deteksi kontur wajah, Anda juga akan melihat sekumpulan titik untuk setiap fitur wajah yang terdeteksi Titik-titik ini mengikuti bentuk fitur wajah. Baca Ringkasan Konsep Deteksi Wajah untuk mengetahui informasi detail tentang cara kontur direpresentasikan.

Gambar berikut mengilustrasikan bagaimana titik-titik ini dipetakan ke wajah (klik gambar untuk memperbesar):