Detect multiple objects in a local file

Perform object detection for multiple objects in an image on a local file.

Explore further

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

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.


// localizeObjects gets objects and bounding boxes from the Vision API for an image at the given file path.
func localizeObjects(w io.Writer, file string) error {
	ctx := context.Background()

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

	f, err := os.Open(file)
	if err != nil {
		return err
	}
	defer f.Close()

	image, err := vision.NewImageFromReader(f)
	if err != nil {
		return err
	}
	annotations, err := client.LocalizeObjects(ctx, image, nil)
	if err != nil {
		return err
	}

	if len(annotations) == 0 {
		fmt.Fprintln(w, "No objects found.")
		return nil
	}

	fmt.Fprintln(w, "Objects:")
	for _, annotation := range annotations {
		fmt.Fprintln(w, annotation.Name)
		fmt.Fprintln(w, annotation.Score)

		for _, v := range annotation.BoundingPoly.NormalizedVertices {
			fmt.Fprintf(w, "(%f,%f)\n", v.X, v.Y)
		}
	}

	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.

/**
 * Detects localized objects in the specified local image.
 *
 * @param filePath The path to the file to perform localized object detection on.
 * @throws Exception on errors while closing the client.
 * @throws IOException on Input/Output errors.
 */
public static void detectLocalizedObjects(String filePath) throws IOException {
  List<AnnotateImageRequest> requests = new ArrayList<>();

  ByteString imgBytes = ByteString.readFrom(new FileInputStream(filePath));

  Image img = Image.newBuilder().setContent(imgBytes).build();
  AnnotateImageRequest request =
      AnnotateImageRequest.newBuilder()
          .addFeatures(Feature.newBuilder().setType(Type.OBJECT_LOCALIZATION))
          .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()) {
    // Perform the request
    BatchAnnotateImagesResponse response = client.batchAnnotateImages(requests);
    List<AnnotateImageResponse> responses = response.getResponsesList();

    // Display the results
    for (AnnotateImageResponse res : responses) {
      for (LocalizedObjectAnnotation entity : res.getLocalizedObjectAnnotationsList()) {
        System.out.format("Object name: %s%n", entity.getName());
        System.out.format("Confidence: %s%n", entity.getScore());
        System.out.format("Normalized Vertices:%n");
        entity
            .getBoundingPoly()
            .getNormalizedVerticesList()
            .forEach(vertex -> System.out.format("- (%s, %s)%n", vertex.getX(), vertex.getY()));
      }
    }
  }
}

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');
const fs = require('fs');

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

/**
 * TODO(developer): Uncomment the following line before running the sample.
 */
// const fileName = `/path/to/localImage.png`;
const request = {
  image: {content: fs.readFileSync(fileName)},
};

const [result] = await client.objectLocalization(request);
const objects = result.localizedObjectAnnotations;
objects.forEach(object => {
  console.log(`Name: ${object.name}`);
  console.log(`Confidence: ${object.score}`);
  const vertices = object.boundingPoly.normalizedVertices;
  vertices.forEach(v => console.log(`x: ${v.x}, y:${v.y}`));
});

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 Path to the image, e.g. "path/to/your/image.jpg"
 */
function detect_object(string $path)
{
    $imageAnnotator = new ImageAnnotatorClient();

    # annotate the image
    $image = file_get_contents($path);
    $response = $imageAnnotator->objectLocalization($image);
    $objects = $response->getLocalizedObjectAnnotations();

    foreach ($objects as $object) {
        $name = $object->getName();
        $score = $object->getScore();
        $vertices = $object->getBoundingPoly()->getNormalizedVertices();

        printf('%s (confidence %f)):' . PHP_EOL, $name, $score);
        print('normalized bounding polygon vertices: ');
        foreach ($vertices as $vertex) {
            printf(' (%f, %f)', $vertex->getX(), $vertex->getY());
        }
        print(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 localize_objects(path):
    """Localize objects in the local image.

    Args:
    path: The path to the local file.
    """
    from google.cloud import vision

    client = vision.ImageAnnotatorClient()

    with open(path, "rb") as image_file:
        content = image_file.read()
    image = vision.Image(content=content)

    objects = client.object_localization(image=image).localized_object_annotations

    print(f"Number of objects found: {len(objects)}")
    for object_ in objects:
        print(f"\n{object_.name} (confidence: {object_.score})")
        print("Normalized bounding polygon vertices: ")
        for vertex in object_.bounding_poly.normalized_vertices:
            print(f" - ({vertex.x}, {vertex.y})")

What's next

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