Annotate a batch of images asynchronously (beta)

Annotate a batch of image files in Cloud Storage while off-line.

Code sample

Java

Before trying this sample, follow the Java setup instructions in the Vision quickstart using client libraries. For more information, see the Vision Java API reference documentation.

To authenticate to Vision, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import com.google.api.gax.longrunning.OperationFuture;
import com.google.api.gax.paging.Page;
import com.google.cloud.storage.Blob;
import com.google.cloud.storage.Bucket;
import com.google.cloud.storage.Storage;
import com.google.cloud.storage.Storage.BlobListOption;
import com.google.cloud.storage.StorageOptions;
import com.google.cloud.vision.v1p4beta1.AnnotateImageRequest;
import com.google.cloud.vision.v1p4beta1.AsyncBatchAnnotateImagesRequest;
import com.google.cloud.vision.v1p4beta1.AsyncBatchAnnotateImagesResponse;
import com.google.cloud.vision.v1p4beta1.BatchAnnotateImagesResponse;
import com.google.cloud.vision.v1p4beta1.BatchAnnotateImagesResponse.Builder;
import com.google.cloud.vision.v1p4beta1.Feature;
import com.google.cloud.vision.v1p4beta1.Feature.Type;
import com.google.cloud.vision.v1p4beta1.GcsDestination;
import com.google.cloud.vision.v1p4beta1.Image;
import com.google.cloud.vision.v1p4beta1.ImageAnnotatorClient;
import com.google.cloud.vision.v1p4beta1.ImageSource;
import com.google.cloud.vision.v1p4beta1.OperationMetadata;
import com.google.cloud.vision.v1p4beta1.OutputConfig;
import com.google.protobuf.util.JsonFormat;
import java.util.ArrayList;
import java.util.List;
import java.util.concurrent.TimeUnit;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class AsyncBatchAnnotateImagesGcs {

  // Performs asynchronous batch annotation of images on Google Cloud Storage
  public static void asyncBatchAnnotateImagesGcs(String gcsSourcePath, String gcsDestinationPath)
      throws Exception {
    // String gcsSourcePath = "gs://YOUR_BUCKET_ID/path_to_your_data";
    // String gcsDestinationPath = "gs://YOUR_BUCKET_ID/path_to_store_annotation";
    try (ImageAnnotatorClient client = ImageAnnotatorClient.create()) {
      List<AnnotateImageRequest> requests = new ArrayList<>();

      ImageSource imgSource = ImageSource.newBuilder().setImageUri(gcsSourcePath).build();

      Image image = Image.newBuilder().setSource(imgSource).build();

      // Set the GCS destination path for where to save the results.
      GcsDestination gcsDestination =
          GcsDestination.newBuilder().setUri(gcsDestinationPath).build();

      // Create the configuration for the output with the batch size.
      // The batch size sets how many pages should be grouped into each json output file.
      OutputConfig outputConfig =
          OutputConfig.newBuilder().setGcsDestination(gcsDestination).setBatchSize(2).build();

      // Select the Features required by the vision API
      Feature features =
          Feature.newBuilder()
              .setType(Type.LABEL_DETECTION)
              .setType(Type.TEXT_DETECTION)
              .setType(Type.IMAGE_PROPERTIES)
              .build();

      // Build the request
      AnnotateImageRequest annotateImageRequest =
          AnnotateImageRequest.newBuilder().setImage(image).addFeatures(features).build();

      requests.add(annotateImageRequest);
      AsyncBatchAnnotateImagesRequest request =
          AsyncBatchAnnotateImagesRequest.newBuilder()
              .addAllRequests(requests)
              .setOutputConfig(outputConfig)
              .build();

      OperationFuture<AsyncBatchAnnotateImagesResponse, OperationMetadata> response =
          client.asyncBatchAnnotateImagesAsync(request);
      System.out.println("Waiting for the operation to finish.");

      // we're not processing the response, since we'll be reading the output from GCS.
      response.get(180, TimeUnit.SECONDS);

      // Once the request has completed and the output has been
      // written to GCS, we can list all the output files.
      Storage storage = StorageOptions.getDefaultInstance().getService();

      // Get the destination location from the gcsDestinationPath
      Pattern pattern = Pattern.compile("gs://([^/]+)/(.+)");
      Matcher matcher = pattern.matcher(gcsDestinationPath);

      if (matcher.find()) {
        String bucketName = matcher.group(1);
        String prefix = matcher.group(2);

        // Get the list of objects with the given prefix from the GCS bucket
        Bucket bucket = storage.get(bucketName);
        Page<Blob> pageList = bucket.list(BlobListOption.prefix(prefix));

        Blob firstOutputFile = null;

        // List objects with the given prefix.
        System.out.println("Output files:");
        for (Blob blob : pageList.iterateAll()) {
          System.out.println(blob.getName());

          // Process the first output file from GCS.
          // Since we specified batch size = 2, the first response contains
          // the first two image requests
          if (firstOutputFile == null) {
            firstOutputFile = blob;
          }
        }

        // Get the contents of the file and convert the JSON contents to an
        // BatchAnnotateImagesResponse
        // object. If the Blob is small read all its content in one request
        // (Note: the file is a .json file)
        // Storage guide: https://cloud.google.com/storage/docs/downloading-objects
        String jsonContents = new String(firstOutputFile.getContent());
        Builder builder = BatchAnnotateImagesResponse.newBuilder();
        JsonFormat.parser().merge(jsonContents, builder);

        // Build the AnnotateFileResponse object
        BatchAnnotateImagesResponse batchAnnotateImagesResponse = builder.build();

        // Here we print the response for the first image
        // The response contains more information:
        // annotation/pages/blocks/paragraphs/words/symbols/colors
        // including confidence score and bounding boxes
        System.out.format("\nResponse: %s\n", batchAnnotateImagesResponse.getResponses(0));

      } else {
        System.out.println("No MATCH");
      }
    } catch (Exception e) {
      System.out.println("Error during asyncBatchAnnotateImagesGcs: \n" + e.toString());
    }
  }
}

Python

Before trying this sample, follow the Python setup instructions in the Vision quickstart using client libraries. For more information, see the Vision Python API reference documentation.

To authenticate to Vision, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

def async_batch_annotate_images_uri(input_image_uri, output_uri):
    """Batch annotation of images on Google Cloud Storage asynchronously.

    Args:
    input_image_uri: The path to the image in Google Cloud Storage (gs://...)
    output_uri: The path to the output path in Google Cloud Storage (gs://...)
    """
    import re

    from google.cloud import storage

    from google.cloud import vision_v1p4beta1 as vision

    client = vision.ImageAnnotatorClient()

    # Construct the request for the image(s) to be annotated:
    image_source = vision.ImageSource(image_uri=input_image_uri)
    image = vision.Image(source=image_source)
    features = [
        vision.Feature(type_=vision.Feature.Type.LABEL_DETECTION),
        vision.Feature(type_=vision.Feature.Type.TEXT_DETECTION),
        vision.Feature(type_=vision.Feature.Type.IMAGE_PROPERTIES),
    ]
    requests = [
        vision.AnnotateImageRequest(image=image, features=features),
    ]

    gcs_destination = vision.GcsDestination(uri=output_uri)
    output_config = vision.OutputConfig(gcs_destination=gcs_destination, batch_size=2)

    operation = client.async_batch_annotate_images(
        requests=requests, output_config=output_config
    )

    print("Waiting for the operation to finish.")
    operation.result(timeout=10000)

    # Once the request has completed and the output has been
    # written to Google Cloud Storage, we can list all the output files.
    storage_client = storage.Client()

    match = re.match(r"gs://([^/]+)/(.+)", output_uri)
    bucket_name = match.group(1)
    prefix = match.group(2)

    bucket = storage_client.get_bucket(bucket_name)

    # Lists objects with the given prefix.
    blob_list = list(bucket.list_blobs(prefix=prefix))
    print("Output files:")
    for blob in blob_list:
        print(blob.name)

    # Processes the first output file from Google Cloud Storage.
    # Since we specified batch_size=2, the first response contains
    # annotations for the first two annotate image requests.
    output = blob_list[0]

    json_string = output.download_as_bytes().decode("utf-8")
    response = vision.BatchAnnotateImagesResponse.from_json(json_string)

    # Prints the actual response for the first annotate image request.
    print(
        "The annotation response for the first request: {}".format(
            response.responses[0]
        )
    )

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.