Detecting Landmarks

Landmark Detection detects popular natural and man-made structures within an image.

Detecting Landmarks in a local image

Protocol

Refer to the images:annotate API endpoint for complete details.

To perform Landmarks Detection, make a POST request and provide the appropriate request body:

POST https://vision.googleapis.com/v1/images:annotate?key=YOUR_API_KEY
{
  "requests": [
    {
      "images": {
        "content": "/9j/7QBEUGhvdG9zaG9...base64-encoded-image-content...fXNWzvDEeYxxxzj/Coa6Bax//Z"
      },
      "features": [
        {
          "type": "LANDMARK_DETECTION"
        }
      ]
    }
  ]
}

See the AnnotateImageRequest reference documentation for more information on configuring the request body.

If the request is successful, the server returns a 200 OK HTTP status code and the response in JSON format:

{
  "responses": [
    {
      "landmarkAnnotations": [
        {
          "mid": "/g/1hg4vfsw1",
          "description": "Palace of Fine Arts",
          "score": 0.47093904,
          "boundingPoly": {
            "vertices": [
              {
                "x": 259,
                "y": 129
              },
              {
                "x": 523,
                "y": 129
              },
              {
                "x": 523,
                "y": 282
              },
              {
                "x": 259,
                "y": 282
              }
            ]
          },
          "locations": [
            {
              "latLng": {
                "latitude": 37.802900859931917,
                "longitude": -122.447777
              }
            }
          ]
        }
      ]
    }
  ]
}

C#

For more on installing and creating a Cloud Vision API client, refer to Cloud Vision API Client Libraries.

private static object DetectLandmarks(string filePath)
{
    var client = ImageAnnotatorClient.Create();
    var image = Image.FromFile(filePath);
    var response = client.DetectLandmarks(image);
    foreach (var annotation in response)
    {
        if (annotation.Description != null)
            Console.WriteLine(annotation.Description);
    }
    return 0;
}

Go

For more on installing and creating a Cloud Vision API client, refer to Cloud Vision API Client Libraries.

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

	client, err := vision.NewClient(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.DetectLandmarks(ctx, image, 10)
	if err != nil {
		return err
	}

	if len(annotations) == 0 {
		fmt.Fprintln(w, "No landmarks found.")
	} else {
		fmt.Fprintln(w, "Landmarks:")
		for _, annotation := range annotations {
			fmt.Fprintln(w, annotation.Description)
		}
	}

	return nil
}

Java

For more on installing and creating a Cloud Vision API client, refer to Cloud Vision API Client Libraries.

public static void detectLandmarks(String filePath, PrintStream out) throws IOException {
  List<AnnotateImageRequest> requests = new ArrayList<>();
  ByteString imgBytes = ByteString.readFrom(new FileInputStream(filePath));

  Image img = Image.newBuilder().setContent(imgBytes).build();
  Feature feat = Feature.newBuilder().setType(Type.LANDMARK_DETECTION).build();
  AnnotateImageRequest request =
      AnnotateImageRequest.newBuilder().addFeatures(feat).setImage(img).build();
  requests.add(request);

  BatchAnnotateImagesResponse response =
      ImageAnnotatorClient.create().batchAnnotateImages(requests);
  List<AnnotateImageResponse> responses = response.getResponsesList();

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

    // For full list of available annotations, see http://g.co/cloud/vision/docs
    for (EntityAnnotation annotation : res.getLandmarkAnnotationsList()) {
      LocationInfo info = annotation.getLocationsList().listIterator().next();
      out.printf("Landmark: %s\n %s\n", annotation.getDescription(), info.getLatLng());
    }
  }
}

Node.js

For more on installing and creating a Cloud Vision API client, refer to Cloud Vision API Client Libraries.

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

// Instantiates a client
const vision = Vision();

// The path to the local image file, e.g. "/path/to/image.png"
// const fileName = '/path/to/image.png';

// Performs landmark detection on the local file
vision.detectLandmarks(fileName)
  .then((results) => {
    const landmarks = results[0];

    console.log('Landmarks:');
    landmarks.forEach((landmark) => console.log(landmark));
  });

PHP

For more on installing and creating a Cloud Vision API client, refer to Cloud Vision API Client Libraries.

use Google\Cloud\Vision\VisionClient;

// $projectId = 'YOUR_PROJECT_ID';
// $path = 'path/to/your/image.jpg'

$vision = new VisionClient([
    'projectId' => $projectId,
]);
$image = $vision->image(file_get_contents($path), ['LANDMARK_DETECTION']);
$result = $vision->annotate($image);
print("Landmarks:\n");
foreach ((array) $result->landmarks() as $landmark) {
    print($landmark->description() . PHP_EOL);
}

Python

For more on installing and creating a Cloud Vision API client, refer to Cloud Vision API Client Libraries.

def detect_landmarks(path):
    """Detects landmarks in the file."""
    vision_client = vision.Client()

    with io.open(path, 'rb') as image_file:
        content = image_file.read()

    image = vision_client.image(content=content)

    landmarks = image.detect_landmarks()
    print('Landmarks:')

    for landmark in landmarks:
        print(landmark.description)

Detecting Landmarks in a remote image

For your convenience, the Cloud Vision API can perform Landmark Detection directly on an image file located in Google Cloud Storage or on the Web without the need to send the contents of the image file in the body of your request.

Protocol

Refer to the images:annotate API endpoint for complete details.

To perform Landmark Detection, make a POST request and provide the appropriate request body:

POST https://vision.googleapis.com/v1/images:annotate?key=YOUR_API_KEY
{
  "requests": [
    {
      "images": {
        "source": {
          "gcsImageUri": "gs://YOUR_BUCKET_NAME/YOUR_FILE_NAME"
        }
      },
      "features": [
        {
          "type": "LANDMARK_DETECTION"
        }
      ]
    }
  ]
}

See the AnnotateImageRequest reference documentation for more information on configuring the request body.

If the request is successful, the server returns a 200 OK HTTP status code and the response in JSON format:

{
  "responses": [
    {
      "landmarkAnnotations": [
        {
          "mid": "/g/1hg4vfsw1",
          "description": "Palace of Fine Arts",
          "score": 0.47093904,
          "boundingPoly": {
            "vertices": [
              {
                "x": 259,
                "y": 129
              },
              {
                "x": 523,
                "y": 129
              },
              {
                "x": 523,
                "y": 282
              },
              {
                "x": 259,
                "y": 282
              }
            ]
          },
          "locations": [
            {
              "latLng": {
                "latitude": 37.802900859931917,
                "longitude": -122.447777
              }
            }
          ]
        }
      ]
    }
  ]
}

C#

For more on installing and creating a Cloud Vision API client, refer to Cloud Vision API Client Libraries.

private static object DetectLandmarks(string bucketName, string objectName)
{
    var client = ImageAnnotatorClient.Create();
    var image = Image.FromUri($"gs://{bucketName}/{objectName}");
    var response = client.DetectLandmarks(image);
    foreach (var annotation in response)
    {
        if (annotation.Description != null)
            Console.WriteLine(annotation.Description);
    }
    return 0;
}

Go

For more on installing and creating a Cloud Vision API client, refer to Cloud Vision API Client Libraries.

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

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

	image := vision.NewImageFromURI(file)
	annotations, err := client.DetectLandmarks(ctx, image, 10)
	if err != nil {
		return err
	}

	if len(annotations) == 0 {
		fmt.Fprintln(w, "No landmarks found.")
	} else {
		fmt.Fprintln(w, "Landmarks:")
		for _, annotation := range annotations {
			fmt.Fprintln(w, annotation.Description)
		}
	}

	return nil
}

Java

For more on installing and creating a Cloud Vision API client, refer to Cloud Vision API Client Libraries.

public static void detectLandmarksGcs(String gcsPath, PrintStream out) 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(Type.LANDMARK_DETECTION).build();
  AnnotateImageRequest request =
      AnnotateImageRequest.newBuilder().addFeatures(feat).setImage(img).build();
  requests.add(request);

  BatchAnnotateImagesResponse response =
      ImageAnnotatorClient.create().batchAnnotateImages(requests);
  List<AnnotateImageResponse> responses = response.getResponsesList();

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

    // For full list of available annotations, see http://g.co/cloud/vision/docs
    for (EntityAnnotation annotation : res.getLandmarkAnnotationsList()) {
      LocationInfo info = annotation.getLocationsList().listIterator().next();
      out.printf("Landmark: %s\n %s\n", annotation.getDescription(), info.getLatLng());
    }
  }
}

Node.js

For more on installing and creating a Cloud Vision API client, refer to Cloud Vision API Client Libraries.

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

// Instantiates clients
const storage = Storage();
const vision = Vision();

// The name of the bucket where the file resides, e.g. "my-bucket"
// const bucketName = 'my-bucket';

// The path to the file within the bucket, e.g. "path/to/image.png"
// const fileName = 'path/to/image.png';

// Performs landmark detection on the remote file
vision.detectLandmarks(storage.bucket(bucketName).file(fileName))
  .then((results) => {
    const landmarks = results[0];

    console.log('Landmarks:');
    landmarks.forEach((landmark) => console.log(landmark));
  });

PHP

For more on installing and creating a Cloud Vision API client, refer to Cloud Vision API Client Libraries.

use Google\Cloud\ServiceBuilder;

// $projectId = 'YOUR_PROJECT_ID';
// $bucketName = 'your-bucket-name'
// $objectName = 'your-object-name'

$builder = new ServiceBuilder([
    'projectId' => $projectId,
]);
$vision = $builder->vision();
$storage = $builder->storage();

// fetch the storage object and annotate the image
$object = $storage->bucket($bucketName)->object($objectName);
$image = $vision->image($object, ['LANDMARK_DETECTION']);
$result = $vision->annotate($image);

// print the response
print("Landmarks:\n");
foreach ((array) $result->landmarks() as $landmark) {
    print($landmark->description() . PHP_EOL);
}

Python

For more on installing and creating a Cloud Vision API client, refer to Cloud Vision API Client Libraries.

def detect_landmarks_uri(uri):
    """Detects landmarks in the file located in Google Cloud Storage or on the
    Web."""
    vision_client = vision.Client()
    image = vision_client.image(source_uri=uri)

    landmarks = image.detect_landmarks()
    print('Landmarks:')

    for landmark in landmarks:
        print(landmark.description)

Send feedback about...

Google Cloud Vision API Documentation