Распознавание текста на изображениях с помощью ML Kit на Android

// When using Latin script library
val recognizer = TextRecognition.getClient(TextRecognizerOptions.DEFAULT_OPTIONS)

// When using Chinese script library
val recognizer = TextRecognition.getClient(ChineseTextRecognizerOptions.Builder().build())

// When using Devanagari script library
val recognizer = TextRecognition.getClient(DevanagariTextRecognizerOptions.Builder().build())

// When using Japanese script library
val recognizer = TextRecognition.getClient(JapaneseTextRecognizerOptions.Builder().build())

// When using Korean script library
val recognizer = TextRecognition.getClient(KoreanTextRecognizerOptions.Builder().build())

// When using Latin script library
TextRecognizer recognizer =
  TextRecognition.getClient(TextRecognizerOptions.DEFAULT_OPTIONS);

// When using Chinese script library
TextRecognizer recognizer =
  TextRecognition.getClient(new ChineseTextRecognizerOptions.Builder().build());

// When using Devanagari script library
TextRecognizer recognizer =
  TextRecognition.getClient(new DevanagariTextRecognizerOptions.Builder().build());

// When using Japanese script library
TextRecognizer recognizer =
  TextRecognition.getClient(new JapaneseTextRecognizerOptions.Builder().build());

// When using Korean script library
TextRecognizer recognizer =
  TextRecognition.getClient(new KoreanTextRecognizerOptions.Builder().build());

private class YourImageAnalyzer : ImageAnalysis.Analyzer {

    override fun analyze(imageProxy: ImageProxy) {
        val mediaImage = imageProxy.image
        if (mediaImage != null) {
            val image = InputImage.fromMediaImage(mediaImage, imageProxy.imageInfo.rotationDegrees)
            // Pass image to an ML Kit Vision API
            // ...
        }
    }
}

private class YourAnalyzer implements ImageAnalysis.Analyzer {

    @Override
    public void analyze(ImageProxy imageProxy) {
        Image mediaImage = imageProxy.getImage();
        if (mediaImage != null) {
          InputImage image =
                InputImage.fromMediaImage(mediaImage, imageProxy.getImageInfo().getRotationDegrees());
          // Pass image to an ML Kit Vision API
          // ...
        }
    }
}

private val ORIENTATIONS = SparseIntArray()

init {
    ORIENTATIONS.append(Surface.ROTATION_0, 0)
    ORIENTATIONS.append(Surface.ROTATION_90, 90)
    ORIENTATIONS.append(Surface.ROTATION_180, 180)
    ORIENTATIONS.append(Surface.ROTATION_270, 270)
}

/**
 * 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, isFrontFacing: Boolean): 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)

    // Get the device's sensor orientation.
    val cameraManager = activity.getSystemService(CAMERA_SERVICE) as CameraManager
    val sensorOrientation = cameraManager
            .getCameraCharacteristics(cameraId)
            .get(CameraCharacteristics.SENSOR_ORIENTATION)!!

    if (isFrontFacing) {
        rotationCompensation = (sensorOrientation + rotationCompensation) % 360
    } else { // back-facing
        rotationCompensation = (sensorOrientation - rotationCompensation + 360) % 360
    }
    return rotationCompensation
}
MLKitVisionImage.kt

private static final SparseIntArray ORIENTATIONS = new SparseIntArray();
static {
    ORIENTATIONS.append(Surface.ROTATION_0, 0);
    ORIENTATIONS.append(Surface.ROTATION_90, 90);
    ORIENTATIONS.append(Surface.ROTATION_180, 180);
    ORIENTATIONS.append(Surface.ROTATION_270, 270);
}

/**
 * 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, boolean isFrontFacing)
        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);

    // Get the device's sensor orientation.
    CameraManager cameraManager = (CameraManager) activity.getSystemService(CAMERA_SERVICE);
    int sensorOrientation = cameraManager
            .getCameraCharacteristics(cameraId)
            .get(CameraCharacteristics.SENSOR_ORIENTATION);

    if (isFrontFacing) {
        rotationCompensation = (sensorOrientation + rotationCompensation) % 360;
    } else { // back-facing
        rotationCompensation = (sensorOrientation - rotationCompensation + 360) % 360;
    }
    return rotationCompensation;
}

val image = InputImage.fromMediaImage(mediaImage, rotation)
MLKitVisionImage.kt

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

val image = InputImage.fromByteBuffer(
        byteBuffer,
        /* image width */ 480,
        /* image height */ 360,
        rotationDegrees,
        InputImage.IMAGE_FORMAT_NV21 // or IMAGE_FORMAT_YV12
)
MLKitVisionImage.kt
// Or:
val image = InputImage.fromByteArray(
        byteArray,
        /* image width */ 480,
        /* image height */ 360,
        rotationDegrees,
        InputImage.IMAGE_FORMAT_NV21 // or IMAGE_FORMAT_YV12
)
MLKitVisionImage.kt

InputImage image = InputImage.fromByteBuffer(byteBuffer,
        /* image width */ 480,
        /* image height */ 360,
        rotationDegrees,
        InputImage.IMAGE_FORMAT_NV21 // or IMAGE_FORMAT_YV12
);
MLKitVisionImage.java
// Or:
InputImage image = InputImage.fromByteArray(
        byteArray,
        /* image width */480,
        /* image height */360,
        rotation,
        InputImage.IMAGE_FORMAT_NV21 // or IMAGE_FORMAT_YV12
);
MLKitVisionImage.java

val image = InputImage.fromBitmap(bitmap, 0)
MLKitVisionImage.kt

val result = recognizer.process(image)
        .addOnSuccessListener { visionText ->
            // Task completed successfully
            // ...
        }
        .addOnFailureListener { e ->
            // Task failed with an exception
            // ...
        }
TextRecognitionActivity.kt

Task<Text> result =
        recognizer.process(image)
                .addOnSuccessListener(new OnSuccessListener<Text>() {
                    @Override
                    public void onSuccess(Text visionText) {
                        // Task completed successfully
                        // ...
                    }
                })
                .addOnFailureListener(
                        new OnFailureListener() {
                            @Override
                            public void onFailure(@NonNull Exception e) {
                                // Task failed with an exception
                                // ...
                            }
                        });
TextRecognitionActivity.java

val resultText = result.text
for (block in result.textBlocks) {
    val blockText = block.text
    val blockCornerPoints = block.cornerPoints
    val blockFrame = block.boundingBox
    for (line in block.lines) {
        val lineText = line.text
        val lineCornerPoints = line.cornerPoints
        val lineFrame = line.boundingBox
        for (element in line.elements) {
            val elementText = element.text
            val elementCornerPoints = element.cornerPoints
            val elementFrame = element.boundingBox
        }
    }
}
TextRecognitionActivity.kt

String resultText = result.getText();
for (Text.TextBlock block : result.getTextBlocks()) {
    String blockText = block.getText();
    Point[] blockCornerPoints = block.getCornerPoints();
    Rect blockFrame = block.getBoundingBox();
    for (Text.Line line : block.getLines()) {
        String lineText = line.getText();
        Point[] lineCornerPoints = line.getCornerPoints();
        Rect lineFrame = line.getBoundingBox();
        for (Text.Element element : line.getElements()) {
            String elementText = element.getText();
            Point[] elementCornerPoints = element.getCornerPoints();
            Rect elementFrame = element.getBoundingBox();
            for (Text.Symbol symbol : element.getSymbols()) {
                String symbolText = symbol.getText();
                Point[] symbolCornerPoints = symbol.getCornerPoints();
                Rect symbolFrame = symbol.getBoundingBox();
            }
        }
    }
}
TextRecognitionActivity.java