使用机器学习套件识别图片中的文本 (Android)

您可以使用机器学习套件识别图片中的文本。机器学习套件中既包含可用于识别图片中的文本(例如街道标志的文本)的通用 API,也包含针对识别文档文本而优化的 API。通用 API 同时具有设备端模型和云端模型。 文档文本识别只能以云端模型的形式提供。如需查看云端模型和设备端模型的对比结果,请参阅概览

准备工作

  1. 将 Firebase 添加到您的 Android 项目(如果尚未添加)。
  2. 将 Android 版机器学习套件库的依赖项添加到您的模块(应用级层)Gradle 文件(通常为 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'
    }
    
  3. (可选但建议执行)如果您使用设备端 API,请将您的应用配置为当用户从 Play 商店安装您的应用后,应用自动将机器学习模型下载到设备。

    为此,请将以下声明添加到您的应用的 AndroidManifest.xml 文件:

    <application ...>
      ...
      <meta-data
          android:name="com.google.firebase.ml.vision.DEPENDENCIES"
          android:value="ocr" />
      <!-- To use multiple models: android:value="ocr,model2,model3" -->
    </application>
    
    如果您未启用在安装时下载模型的选项,模型将在您首次运行检测器时下载。您在下载完毕之前提出的请求不会产生任何结果。
  4. 如果您想使用云端模型,但尚未为项目启用基于 Cloud 的 API,此时请执行以下操作来启用该 API:

    1. 打开 Firebase 控制台的机器学习套件 API 页面
    2. 如果您尚未将项目升级到 Blaze 定价方案,请点击升级以执行此操作。(只有在您的项目未采用 Blaze 方案时,系统才会提示您进行升级。)

      只有 Blaze 级项目才能使用基于 Cloud 的 API。

    3. 如果尚未启用基于 Cloud 的 API,请点击启用基于 Cloud 的 API

    如果您只想使用设备端模型,可以跳过此步骤。

现在,您可以开始识别图片中的文本了。

输入图片指南

  • 要使机器学习套件准确识别文本,输入图片中包含的文本必须由足够大的像素表示。理想情况下,对于拉丁文本,每个字符应至少为 16x16 像素。对于中文、日语和韩语文本(只有在基于 Cloud 的 API 的支持下),每个字符应为 24x24 像素。对于所有语言,字符像素大于 24x24 通常不会增加准确性。

    例如,640x480 像素的图片可能非常适合用于扫描占据图片整个宽度的名片。如需扫描打印在信纸大小纸张上的文档,可能需要 720x1280 像素的图片。

  • 图片聚焦不佳会影响文本识别的准确性。如果您无法获得满意的结果,请尝试让用户重新捕获图片。

  • 如果您是在实时应用中识别文本,则可能还需要考虑输入图片的整体尺寸。较小图片的处理速度相对较快,因此,为了减少延迟时间,请以较低的分辨率捕获图片(但请牢记上述准确性要求),并确保文本在图片中占据尽可能大的画面。另请参阅提高实时性能的相关提示


识别图片中的文本

如需使用设备端模型或云端模型来识别图片中的文本,请按照以下说明运行文本识别器。

1. 运行文本识别器

如需识别图片中的文本,请基于设备上的以下资源创建一个 FirebaseVisionImage 对象:Bitmapmedia.ImageByteBuffer、字节数组或文件。然后,将 FirebaseVisionImage 对象传递给 FirebaseVisionTextRecognizerprocessImage 方法。

  1. 基于图片创建 FirebaseVisionImage 对象。

    • 如需基于 media.Image 对象创建 FirebaseVisionImage 对象(例如从设备的相机捕获图片时),请将 media.Image 对象和图片的旋转角度传递给 FirebaseVisionImage.fromMediaImage()

      如果您使用 CameraX 库,OnImageCapturedListenerImageAnalysis.Analyzer 类会为您计算旋转角度值,因此您只需在调用 FirebaseVisionImage.fromMediaImage() 之前将旋转角度转换为机器学习套件的 ROTATION_ 常量之一:

      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
                  // ...
              }
          }
      }
      

      如果您没有使用可提供图片旋转角度的相机库,可以根据设备的旋转角度和设备中相机传感器的朝向来计算旋转角度:

      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;
      }

      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
      }

      然后,将 media.Image 对象及旋转角度值传递给 FirebaseVisionImage.fromMediaImage()

      Java

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

      Kotlin+KTX

      val image = FirebaseVisionImage.fromMediaImage(mediaImage, rotation)
    • 如需基于文件 URI 创建 FirebaseVisionImage 对象,请将应用上下文和文件 URI 传递给 FirebaseVisionImage.fromFilePath()。如果您使用 ACTION_GET_CONTENT Intent 提示用户从图库应用中选择图片,这一操作会非常有用。

      Java

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

      Kotlin+KTX

      val image: FirebaseVisionImage
      try {
          image = FirebaseVisionImage.fromFilePath(context, uri)
      } catch (e: IOException) {
          e.printStackTrace()
      }
    • 如需基于 ByteBuffer 或字节数组创建 FirebaseVisionImage 对象,请先按上述 media.Image 输入的说明计算图片旋转角度。

      然后,创建一个包含图片的高度、宽度、颜色编码格式和旋转角度的 FirebaseVisionImageMetadata 对象:

      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();

      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()

      使用缓冲区或数组以及元数据对象来创建 FirebaseVisionImage 对象:

      Java

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

      Kotlin+KTX

      val image = FirebaseVisionImage.fromByteBuffer(buffer, metadata)
      // Or: val image = FirebaseVisionImage.fromByteArray(byteArray, metadata)
    • 如需基于 Bitmap 对象创建 FirebaseVisionImage 对象,请运行以下代码:

      Java

      FirebaseVisionImage image = FirebaseVisionImage.fromBitmap(bitmap);

      Kotlin+KTX

      val image = FirebaseVisionImage.fromBitmap(bitmap)
      Bitmap 对象表示的图片必须保持竖直,不需要额外的旋转。

  2. 获取 FirebaseVisionTextRecognizer 的一个实例。

    如需使用设备端模型,请运行以下代码:

    Java

    FirebaseVisionTextRecognizer detector = FirebaseVision.getInstance()
            .getOnDeviceTextRecognizer();

    Kotlin+KTX

    val detector = FirebaseVision.getInstance()
            .onDeviceTextRecognizer

    如需使用云端模型,请运行以下代码:

    Java

    FirebaseVisionTextRecognizer detector = FirebaseVision.getInstance()
            .getCloudTextRecognizer();
    // Or, to change the default settings:
    //   FirebaseVisionTextRecognizer detector = FirebaseVision.getInstance()
    //          .getCloudTextRecognizer(options);
    // Or, to provide language hints to assist with language detection:
    // See https://cloud.google.com/vision/docs/languages for supported languages
    FirebaseVisionCloudTextRecognizerOptions options = new FirebaseVisionCloudTextRecognizerOptions.Builder()
            .setLanguageHints(Arrays.asList("en", "hi"))
            .build();
    

    Kotlin+KTX

    val detector = FirebaseVision.getInstance().cloudTextRecognizer
    // Or, to change the default settings:
    // val detector = FirebaseVision.getInstance().getCloudTextRecognizer(options)
    // Or, to provide language hints to assist with language detection:
    // See https://cloud.google.com/vision/docs/languages for supported languages
    val options = FirebaseVisionCloudTextRecognizerOptions.Builder()
            .setLanguageHints(listOf("en", "hi"))
            .build()
    
  3. 最后,将图片传递给 processImage 方法:

    Java

    Task<FirebaseVisionText> result =
            detector.processImage(image)
                    .addOnSuccessListener(new OnSuccessListener<FirebaseVisionText>() {
                        @Override
                        public void onSuccess(FirebaseVisionText firebaseVisionText) {
                            // Task completed successfully
                            // ...
                        }
                    })
                    .addOnFailureListener(
                            new OnFailureListener() {
                                @Override
                                public void onFailure(@NonNull Exception e) {
                                    // Task failed with an exception
                                    // ...
                                }
                            });

    Kotlin+KTX

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

2. 从识别出的文本块中提取文本

如果文本识别操作成功完成,系统会向成功监听器传递一个 FirebaseVisionText 对象。FirebaseVisionText 对象包含图片中识别到的完整文本以及零个或零个以上的 TextBlock 对象。

每个 TextBlock 表示一个矩形文本块,其中包含零个或零个以上的 Line 对象。每个 Line 对象包含零个或零个以上的 Element 对象,这些对象表示字词和类似字词的实体(日期、数字等)。

对于每个 TextBlockLineElement 对象,您可以获取区域中识别出的文本以及该区域的边界坐标。

例如:

Java

String resultText = result.getText();
for (FirebaseVisionText.TextBlock block: result.getTextBlocks()) {
    String blockText = block.getText();
    Float blockConfidence = block.getConfidence();
    List<RecognizedLanguage> blockLanguages = block.getRecognizedLanguages();
    Point[] blockCornerPoints = block.getCornerPoints();
    Rect blockFrame = block.getBoundingBox();
    for (FirebaseVisionText.Line line: block.getLines()) {
        String lineText = line.getText();
        Float lineConfidence = line.getConfidence();
        List<RecognizedLanguage> lineLanguages = line.getRecognizedLanguages();
        Point[] lineCornerPoints = line.getCornerPoints();
        Rect lineFrame = line.getBoundingBox();
        for (FirebaseVisionText.Element element: line.getElements()) {
            String elementText = element.getText();
            Float elementConfidence = element.getConfidence();
            List<RecognizedLanguage> elementLanguages = element.getRecognizedLanguages();
            Point[] elementCornerPoints = element.getCornerPoints();
            Rect elementFrame = element.getBoundingBox();
        }
    }
}

Kotlin+KTX

val resultText = result.text
for (block in result.textBlocks) {
    val blockText = block.text
    val blockConfidence = block.confidence
    val blockLanguages = block.recognizedLanguages
    val blockCornerPoints = block.cornerPoints
    val blockFrame = block.boundingBox
    for (line in block.lines) {
        val lineText = line.text
        val lineConfidence = line.confidence
        val lineLanguages = line.recognizedLanguages
        val lineCornerPoints = line.cornerPoints
        val lineFrame = line.boundingBox
        for (element in line.elements) {
            val elementText = element.text
            val elementConfidence = element.confidence
            val elementLanguages = element.recognizedLanguages
            val elementCornerPoints = element.cornerPoints
            val elementFrame = element.boundingBox
        }
    }
}

提高实时性能的相关提示

如果要在实时应用中使用设备端模型识别文本,请遵循以下准则以实现最佳帧速率:

  • 限制文本识别器的调用次数。如果在文本识别器运行时有新视频帧可用,请丢弃该帧。
  • 如果要将文本识别器的输出作为图形叠加在输入图片上,请先从机器学习套件获取结果,然后在一个步骤中完成图片的呈现和叠加。采用这一方法,每个输入帧只需在显示表面呈现一次。
  • 如果您使用 Camera2 API,请以 ImageFormat.YUV_420_888 格式捕获图片。

    如果您使用旧版 Camera API,请以 ImageFormat.NV21 格式捕获图片。

  • 建议以较低分辨率捕获图片,但是,请注意此 API 的图片尺寸要求。

后续步骤


识别文档图片中的文本

如需识别文档的文本,请按照以下说明配置并运行云端文档文本识别器。

下文所述的文档文本识别 API 提供了一个旨在更方便地处理文档图片的接口。如果您希望使用 FirebaseVisionTextRecognizer API 提供的接口,可以将云端文本识别器配置为使用密集文本模型,以改用该接口来扫描文档。

如需使用文档文本识别 API,请执行以下操作:

1. 运行文本识别器

如需识别图片中的文本,请从设备上的以下资源创建一个 FirebaseVisionImage 对象:Bitmapmedia.ImageByteBuffer、字节数组或文件。然后,将 FirebaseVisionImage 对象传递给 FirebaseVisionDocumentTextRecognizerprocessImage 方法。

  1. 基于图片创建 FirebaseVisionImage 对象。

    • 如需基于 media.Image 对象创建 FirebaseVisionImage 对象(例如从设备的相机捕获图片时),请将 media.Image 对象和图片的旋转角度传递给 FirebaseVisionImage.fromMediaImage()

      如果您使用 CameraX 库,OnImageCapturedListenerImageAnalysis.Analyzer 类会为您计算旋转角度值,因此您只需在调用 FirebaseVisionImage.fromMediaImage() 之前将旋转角度转换为机器学习套件的 ROTATION_ 常量之一:

      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
                  // ...
              }
          }
      }
      

      如果您没有使用可提供图片旋转角度的相机库,可以根据设备的旋转角度和设备中相机传感器的朝向来计算旋转角度:

      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;
      }

      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
      }

      然后,将 media.Image 对象及旋转角度值传递给 FirebaseVisionImage.fromMediaImage()

      Java

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

      Kotlin+KTX

      val image = FirebaseVisionImage.fromMediaImage(mediaImage, rotation)
    • 如需基于文件 URI 创建 FirebaseVisionImage 对象,请将应用上下文和文件 URI 传递给 FirebaseVisionImage.fromFilePath()。如果您使用 ACTION_GET_CONTENT Intent 提示用户从图库应用中选择图片,这一操作会非常有用。

      Java

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

      Kotlin+KTX

      val image: FirebaseVisionImage
      try {
          image = FirebaseVisionImage.fromFilePath(context, uri)
      } catch (e: IOException) {
          e.printStackTrace()
      }
    • 如需基于 ByteBuffer 或字节数组创建 FirebaseVisionImage 对象,请先按上述 media.Image 输入的说明计算图片旋转角度。

      然后,创建一个包含图片的高度、宽度、颜色编码格式和旋转角度的 FirebaseVisionImageMetadata 对象:

      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();

      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()

      使用缓冲区或数组以及元数据对象来创建 FirebaseVisionImage 对象:

      Java

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

      Kotlin+KTX

      val image = FirebaseVisionImage.fromByteBuffer(buffer, metadata)
      // Or: val image = FirebaseVisionImage.fromByteArray(byteArray, metadata)
    • 如需基于 Bitmap 对象创建 FirebaseVisionImage 对象,请运行以下代码:

      Java

      FirebaseVisionImage image = FirebaseVisionImage.fromBitmap(bitmap);

      Kotlin+KTX

      val image = FirebaseVisionImage.fromBitmap(bitmap)
      Bitmap 对象表示的图片必须保持竖直,不需要额外的旋转。

  2. 获取 FirebaseVisionDocumentTextRecognizer 实例:

    Java

    FirebaseVisionDocumentTextRecognizer detector = FirebaseVision.getInstance()
            .getCloudDocumentTextRecognizer();
    // Or, to provide language hints to assist with language detection:
    // See https://cloud.google.com/vision/docs/languages for supported languages
    FirebaseVisionCloudDocumentRecognizerOptions options =
            new FirebaseVisionCloudDocumentRecognizerOptions.Builder()
                    .setLanguageHints(Arrays.asList("en", "hi"))
                    .build();
    FirebaseVisionDocumentTextRecognizer detector = FirebaseVision.getInstance()
            .getCloudDocumentTextRecognizer(options);

    Kotlin+KTX

    val detector = FirebaseVision.getInstance()
            .cloudDocumentTextRecognizer
    // Or, to provide language hints to assist with language detection:
    // See https://cloud.google.com/vision/docs/languages for supported languages
    val options = FirebaseVisionCloudDocumentRecognizerOptions.Builder()
            .setLanguageHints(listOf("en", "hi"))
            .build()
    val detector = FirebaseVision.getInstance()
            .getCloudDocumentTextRecognizer(options)

  3. 最后,将图片传递给 processImage 方法:

    Java

    detector.processImage(myImage)
            .addOnSuccessListener(new OnSuccessListener<FirebaseVisionDocumentText>() {
                @Override
                public void onSuccess(FirebaseVisionDocumentText result) {
                    // Task completed successfully
                    // ...
                }
            })
            .addOnFailureListener(new OnFailureListener() {
                @Override
                public void onFailure(@NonNull Exception e) {
                    // Task failed with an exception
                    // ...
                }
            });

    Kotlin+KTX

    detector.processImage(myImage)
            .addOnSuccessListener { firebaseVisionDocumentText ->
                // Task completed successfully
                // ...
            }
            .addOnFailureListener { e ->
                // Task failed with an exception
                // ...
            }

2. 从识别出的文本块中提取文本

如果文本识别操作成功完成,它将返回一个 FirebaseVisionDocumentText 对象。FirebaseVisionDocumentText 对象包含图片中识别到的完整文本以及反映所识别的文档结构的对象层次结构:

对于每个 BlockParagraphWordSymbol 对象,您可以获取区域中识别出的文本以及该区域的边界坐标。

例如:

Java

String resultText = result.getText();
for (FirebaseVisionDocumentText.Block block: result.getBlocks()) {
    String blockText = block.getText();
    Float blockConfidence = block.getConfidence();
    List<RecognizedLanguage> blockRecognizedLanguages = block.getRecognizedLanguages();
    Rect blockFrame = block.getBoundingBox();
    for (FirebaseVisionDocumentText.Paragraph paragraph: block.getParagraphs()) {
        String paragraphText = paragraph.getText();
        Float paragraphConfidence = paragraph.getConfidence();
        List<RecognizedLanguage> paragraphRecognizedLanguages = paragraph.getRecognizedLanguages();
        Rect paragraphFrame = paragraph.getBoundingBox();
        for (FirebaseVisionDocumentText.Word word: paragraph.getWords()) {
            String wordText = word.getText();
            Float wordConfidence = word.getConfidence();
            List<RecognizedLanguage> wordRecognizedLanguages = word.getRecognizedLanguages();
            Rect wordFrame = word.getBoundingBox();
            for (FirebaseVisionDocumentText.Symbol symbol: word.getSymbols()) {
                String symbolText = symbol.getText();
                Float symbolConfidence = symbol.getConfidence();
                List<RecognizedLanguage> symbolRecognizedLanguages = symbol.getRecognizedLanguages();
                Rect symbolFrame = symbol.getBoundingBox();
            }
        }
    }
}

Kotlin+KTX

val resultText = result.text
for (block in result.blocks) {
    val blockText = block.text
    val blockConfidence = block.confidence
    val blockRecognizedLanguages = block.recognizedLanguages
    val blockFrame = block.boundingBox
    for (paragraph in block.paragraphs) {
        val paragraphText = paragraph.text
        val paragraphConfidence = paragraph.confidence
        val paragraphRecognizedLanguages = paragraph.recognizedLanguages
        val paragraphFrame = paragraph.boundingBox
        for (word in paragraph.words) {
            val wordText = word.text
            val wordConfidence = word.confidence
            val wordRecognizedLanguages = word.recognizedLanguages
            val wordFrame = word.boundingBox
            for (symbol in word.symbols) {
                val symbolText = symbol.text
                val symbolConfidence = symbol.confidence
                val symbolRecognizedLanguages = symbol.recognizedLanguages
                val symbolFrame = symbol.boundingBox
            }
        }
    }
}

后续步骤