Detect web annotations in a Cloud Storage file

Perform web annotation detection on a file stored in Cloud Storage.

Explore further

For detailed documentation that includes this code sample, see the following:

Detect Web entities and pages

Code sample

Go

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

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


// detectWeb gets image properties from the Vision API for an image at the given file path.
func detectWebURI(w io.Writer, file string) error {
	ctx := context.Background()

	client, err := vision.NewImageAnnotatorClient(ctx)
	if err != nil {
		return err
	}

	image := vision.NewImageFromURI(file)
	web, err := client.DetectWeb(ctx, image, nil)
	if err != nil {
		return err
	}

	fmt.Fprintln(w, "Web properties:")
	if len(web.FullMatchingImages) != 0 {
		fmt.Fprintln(w, "\tFull image matches:")
		for _, full := range web.FullMatchingImages {
			fmt.Fprintf(w, "\t\t%s\n", full.Url)
		}
	}
	if len(web.PagesWithMatchingImages) != 0 {
		fmt.Fprintln(w, "\tPages with this image:")
		for _, page := range web.PagesWithMatchingImages {
			fmt.Fprintf(w, "\t\t%s\n", page.Url)
		}
	}
	if len(web.WebEntities) != 0 {
		fmt.Fprintln(w, "\tEntities:")
		fmt.Fprintln(w, "\t\tEntity\t\tScore\tDescription")
		for _, entity := range web.WebEntities {
			fmt.Fprintf(w, "\t\t%-14s\t%-2.4f\t%s\n", entity.EntityId, entity.Score, entity.Description)
		}
	}
	if len(web.BestGuessLabels) != 0 {
		fmt.Fprintln(w, "\tBest guess labels:")
		for _, label := range web.BestGuessLabels {
			fmt.Fprintf(w, "\t\t%s\n", label.Label)
		}
	}

	return nil
}

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.cloud.vision.v1.AnnotateImageRequest;
import com.google.cloud.vision.v1.AnnotateImageResponse;
import com.google.cloud.vision.v1.BatchAnnotateImagesResponse;
import com.google.cloud.vision.v1.Feature;
import com.google.cloud.vision.v1.Image;
import com.google.cloud.vision.v1.ImageAnnotatorClient;
import com.google.cloud.vision.v1.ImageSource;
import com.google.cloud.vision.v1.WebDetection;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

public class DetectWebDetectionsGcs {

  public static void detectWebDetectionsGcs() throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String filePath = "gs://your-gcs-bucket/path/to/image/file.jpg";
    detectWebDetectionsGcs(filePath);
  }

  // Detects whether the remote image on Google Cloud Storage has features you would want to
  // moderate.
  public static void detectWebDetectionsGcs(String gcsPath) throws IOException {
    List<AnnotateImageRequest> requests = new ArrayList<>();

    ImageSource imgSource = ImageSource.newBuilder().setGcsImageUri(gcsPath).build();
    Image img = Image.newBuilder().setSource(imgSource).build();
    Feature feat = Feature.newBuilder().setType(Feature.Type.WEB_DETECTION).build();
    AnnotateImageRequest request =
        AnnotateImageRequest.newBuilder().addFeatures(feat).setImage(img).build();
    requests.add(request);

    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (ImageAnnotatorClient client = ImageAnnotatorClient.create()) {
      BatchAnnotateImagesResponse response = client.batchAnnotateImages(requests);
      List<AnnotateImageResponse> responses = response.getResponsesList();

      for (AnnotateImageResponse res : responses) {
        if (res.hasError()) {
          System.out.format("Error: %s%n", res.getError().getMessage());
          return;
        }

        // Search the web for usages of the image. You could use these signals later
        // for user input moderation or linking external references.
        // For a full list of available annotations, see http://g.co/cloud/vision/docs
        WebDetection annotation = res.getWebDetection();
        System.out.println("Entity:Id:Score");
        System.out.println("===============");
        for (WebDetection.WebEntity entity : annotation.getWebEntitiesList()) {
          System.out.println(
              entity.getDescription() + " : " + entity.getEntityId() + " : " + entity.getScore());
        }
        for (WebDetection.WebLabel label : annotation.getBestGuessLabelsList()) {
          System.out.format("%nBest guess label: %s", label.getLabel());
        }
        System.out.println("%nPages with matching images: Score%n==");
        for (WebDetection.WebPage page : annotation.getPagesWithMatchingImagesList()) {
          System.out.println(page.getUrl() + " : " + page.getScore());
        }
        System.out.println("%nPages with partially matching images: Score%n==");
        for (WebDetection.WebImage image : annotation.getPartialMatchingImagesList()) {
          System.out.println(image.getUrl() + " : " + image.getScore());
        }
        System.out.println("%nPages with fully matching images: Score%n==");
        for (WebDetection.WebImage image : annotation.getFullMatchingImagesList()) {
          System.out.println(image.getUrl() + " : " + image.getScore());
        }
        System.out.println("%nPages with visually similar images: Score%n==");
        for (WebDetection.WebImage image : annotation.getVisuallySimilarImagesList()) {
          System.out.println(image.getUrl() + " : " + image.getScore());
        }
      }
    }
  }
}

Node.js

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

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


// Imports the Google Cloud client libraries
const vision = require('@google-cloud/vision');

// Creates a client
const client = new vision.ImageAnnotatorClient();

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const bucketName = 'Bucket where the file resides, e.g. my-bucket';
// const fileName = 'Path to file within bucket, e.g. path/to/image.png';

// Detect similar images on the web to a remote file
const [result] = await client.webDetection(`gs://${bucketName}/${fileName}`);
const webDetection = result.webDetection;
if (webDetection.fullMatchingImages.length) {
  console.log(
    `Full matches found: ${webDetection.fullMatchingImages.length}`
  );
  webDetection.fullMatchingImages.forEach(image => {
    console.log(`  URL: ${image.url}`);
    console.log(`  Score: ${image.score}`);
  });
}

if (webDetection.partialMatchingImages.length) {
  console.log(
    `Partial matches found: ${webDetection.partialMatchingImages.length}`
  );
  webDetection.partialMatchingImages.forEach(image => {
    console.log(`  URL: ${image.url}`);
    console.log(`  Score: ${image.score}`);
  });
}

if (webDetection.webEntities.length) {
  console.log(`Web entities found: ${webDetection.webEntities.length}`);
  webDetection.webEntities.forEach(webEntity => {
    console.log(`  Description: ${webEntity.description}`);
    console.log(`  Score: ${webEntity.score}`);
  });
}

if (webDetection.bestGuessLabels.length) {
  console.log(
    `Best guess labels found: ${webDetection.bestGuessLabels.length}`
  );
  webDetection.bestGuessLabels.forEach(label => {
    console.log(`  Label: ${label.label}`);
  });
}

PHP

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

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

namespace Google\Cloud\Samples\Vision;

use Google\Cloud\Vision\V1\ImageAnnotatorClient;

/**
 * @param string $path GCS path to the image, e.g. "gs://path/to/your/image.jpg"
 */
function detect_web_gcs(string $path)
{
    $imageAnnotator = new ImageAnnotatorClient();

    # annotate the image
    $response = $imageAnnotator->webDetection($path);
    $web = $response->getWebDetection();

    if ($web) {
        printf('%d best guess labels found' . PHP_EOL,
            count($web->getPagesWithMatchingImages()));
        foreach ($web->getBestGuessLabels() as $label) {
            printf('Best guess label: %s' . PHP_EOL, $label->getLabel());
        }
        print(PHP_EOL);

        // Print pages with matching images
        printf('%d pages with matching images found' . PHP_EOL,
            count($web->getPagesWithMatchingImages()));
        foreach ($web->getPagesWithMatchingImages() as $page) {
            printf('URL: %s' . PHP_EOL, $page->getUrl());
        }
        print(PHP_EOL);

        // Print full matching images
        printf('%d full matching images found' . PHP_EOL,
            count($web->getFullMatchingImages()));
        foreach ($web->getFullMatchingImages() as $fullMatchingImage) {
            printf('URL: %s' . PHP_EOL, $fullMatchingImage->getUrl());
        }
        print(PHP_EOL);

        // Print partial matching images
        printf('%d partial matching images found' . PHP_EOL,
            count($web->getPartialMatchingImages()));
        foreach ($web->getPartialMatchingImages() as $partialMatchingImage) {
            printf('URL: %s' . PHP_EOL, $partialMatchingImage->getUrl());
        }
        print(PHP_EOL);

        // Print visually similar images
        printf('%d visually similar images found' . PHP_EOL,
            count($web->getVisuallySimilarImages()));
        foreach ($web->getVisuallySimilarImages() as $visuallySimilarImage) {
            printf('URL: %s' . PHP_EOL, $visuallySimilarImage->getUrl());
        }
        print(PHP_EOL);

        // Print web entities
        printf('%d web entities found' . PHP_EOL,
            count($web->getWebEntities()));
        foreach ($web->getWebEntities() as $entity) {
            printf('Description: %s, Score: %f' . PHP_EOL,
                $entity->getDescription(),
                $entity->getScore());
        }
    } else {
        print('No Results.' . PHP_EOL);
    }

    $imageAnnotator->close();
}

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 detect_web_uri(uri):
    """Detects web annotations in the file located in Google Cloud Storage."""
    from google.cloud import vision

    client = vision.ImageAnnotatorClient()
    image = vision.Image()
    image.source.image_uri = uri

    response = client.web_detection(image=image)
    annotations = response.web_detection

    if annotations.best_guess_labels:
        for label in annotations.best_guess_labels:
            print(f"\nBest guess label: {label.label}")

    if annotations.pages_with_matching_images:
        print(
            "\n{} Pages with matching images found:".format(
                len(annotations.pages_with_matching_images)
            )
        )

        for page in annotations.pages_with_matching_images:
            print(f"\n\tPage url   : {page.url}")

            if page.full_matching_images:
                print(
                    "\t{} Full Matches found: ".format(len(page.full_matching_images))
                )

                for image in page.full_matching_images:
                    print(f"\t\tImage url  : {image.url}")

            if page.partial_matching_images:
                print(
                    "\t{} Partial Matches found: ".format(
                        len(page.partial_matching_images)
                    )
                )

                for image in page.partial_matching_images:
                    print(f"\t\tImage url  : {image.url}")

    if annotations.web_entities:
        print("\n{} Web entities found: ".format(len(annotations.web_entities)))

        for entity in annotations.web_entities:
            print(f"\n\tScore      : {entity.score}")
            print(f"\tDescription: {entity.description}")

    if annotations.visually_similar_images:
        print(
            "\n{} visually similar images found:\n".format(
                len(annotations.visually_similar_images)
            )
        )

        for image in annotations.visually_similar_images:
            print(f"\tImage url    : {image.url}")

    if response.error.message:
        raise Exception(
            "{}\nFor more info on error messages, check: "
            "https://cloud.google.com/apis/design/errors".format(response.error.message)
        )

What's next

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

Detect web annotations in a Cloud Storage file Stay organized with collections Save and categorize content based on your preferences.

Explore further

Code sample

Go

Java

Node.js

PHP

Python

What's next

Detect web annotations in a Cloud Storage file