利用机器学习套件,您可以使用设备端模型或云端模型来为图片中识别出的对象加标签。如需了解每种方法的优势,请参阅概览。
准备工作
- 将 Firebase 添加到您的 Android 项目(如果尚未添加)。
- 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' implementation 'com.google.firebase:firebase-ml-vision-image-label-model:20.0.1' }
-
(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="label" /> <!-- To use multiple models: android:value="label,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。 -
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:
- 打开 Firebase 控制台的机器学习套件 API 页面。
-
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。
- 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,您就可以使用设备端模型或云端模型为图片加标签了。
1. 准备输入图片
基于图片创建FirebaseVisionImage
对象。使用 Bitmap
或 JPEG 格式的 media.Image
(如果您使用 Camera2 API)时,图片标记器的运行速度最快;建议您尽量使用这两种格式的图片。
-
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,
OnImageCapturedListener
和ImageAnalysis.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. 配置并运行图片标记器
如需给图片中的对象加标签,请将FirebaseVisionImage
对象传递给 FirebaseVisionImageLabeler
的 processImage
方法。
首先,获取
FirebaseVisionImageLabeler
的一个实例。如果您想要使用设备端图片标记器,请运行以下代码:
Java
FirebaseVisionImageLabeler labeler = FirebaseVision.getInstance() .getOnDeviceImageLabeler(); // Or, to set the minimum confidence required: // FirebaseVisionOnDeviceImageLabelerOptions options = // new FirebaseVisionOnDeviceImageLabelerOptions.Builder() // .setConfidenceThreshold(0.7f) // .build(); // FirebaseVisionImageLabeler labeler = FirebaseVision.getInstance() // .getOnDeviceImageLabeler(options);
Kotlin+KTX
val labeler = FirebaseVision.getInstance().getOnDeviceImageLabeler() // Or, to set the minimum confidence required: // val options = FirebaseVisionOnDeviceImageLabelerOptions.Builder() // .setConfidenceThreshold(0.7f) // .build() // val labeler = FirebaseVision.getInstance().getOnDeviceImageLabeler(options)
如果您想要使用云端图片标记器,请运行以下代码:
Java
FirebaseVisionImageLabeler labeler = FirebaseVision.getInstance() .getCloudImageLabeler(); // Or, to set the minimum confidence required: // FirebaseVisionCloudImageLabelerOptions options = // new FirebaseVisionCloudImageLabelerOptions.Builder() // .setConfidenceThreshold(0.7f) // .build(); // FirebaseVisionImageLabeler labeler = FirebaseVision.getInstance() // .getCloudImageLabeler(options);
Kotlin+KTX
val labeler = FirebaseVision.getInstance().getCloudImageLabeler() // Or, to set the minimum confidence required: // val options = FirebaseVisionCloudImageLabelerOptions.Builder() // .setConfidenceThreshold(0.7f) // .build() // val labeler = FirebaseVision.getInstance().getCloudImageLabeler(options)
然后,将图片传递给
processImage()
方法:Java
labeler.processImage(image) .addOnSuccessListener(new OnSuccessListener<List<FirebaseVisionImageLabel>>() { @Override public void onSuccess(List<FirebaseVisionImageLabel> labels) { // Task completed successfully // ... } }) .addOnFailureListener(new OnFailureListener() { @Override public void onFailure(@NonNull Exception e) { // Task failed with an exception // ... } });
Kotlin+KTX
labeler.processImage(image) .addOnSuccessListener { labels -> // Task completed successfully // ... } .addOnFailureListener { e -> // Task failed with an exception // ... }
3. 获取已加标签的对象的相关信息
如果为图片添加标签的操作成功完成,系统会向成功监听器传递一组FirebaseVisionImageLabel
对象。每个 FirebaseVisionImageLabel
对象代表图片中加了标签的某个事物。对于每个标签,您可以获取标签的文本说明、其知识图谱实体 ID(如果有)以及匹配的置信度分数。例如:
Java
for (FirebaseVisionImageLabel label: labels) {
String text = label.getText();
String entityId = label.getEntityId();
float confidence = label.getConfidence();
}
Kotlin+KTX
for (label in labels) {
val text = label.text
val entityId = label.entityId
val confidence = label.confidence
}
提高实时性能的相关提示
如果要在实时应用中为图片加标签,请遵循以下准则以实现最佳帧速率:
- 限制图片标记器的调用次数。如果在图片标记器运行时有新的视频帧可用,请丢弃该帧。
- 如果要将图片标记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。
后续步骤
- 在向生产环境中部署使用 Cloud API 的应用之前,您应该执行一些额外的步骤来防止未经授权的 API 访问并减轻这些访问造成的影响。