Detect text in a Cloud Storage file

Perform text detection on a file stored in Cloud Storage.

Documentation pages that include this code sample

To view the code sample used in context, see the following documentation:

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.


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

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

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

	if len(annotations) == 0 {
		fmt.Fprintln(w, "No text found.")
	} else {
		fmt.Fprintln(w, "Text:")
		for _, annotation := range annotations {
			fmt.Fprintf(w, "%q\n", annotation.Description)
		}
	}

	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.


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.EntityAnnotation;
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 java.io.IOException;
import java.util.ArrayList;
import java.util.List;

public class DetectTextGcs {

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

  // Detects text in the specified remote image on Google Cloud Storage.
  public static void detectTextGcs(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.TEXT_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;
        }

        // For full list of available annotations, see http://g.co/cloud/vision/docs
        for (EntityAnnotation annotation : res.getTextAnnotationsList()) {
          System.out.format("Text: %s%n", annotation.getDescription());
          System.out.format("Position : %s%n", annotation.getBoundingPoly());
        }
      }
    }
  }
}

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.

// 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';

// Performs text detection on the gcs file
const [result] = await client.textDetection(`gs://${bucketName}/${fileName}`);
const detections = result.textAnnotations;
console.log('Text:');
detections.forEach(text => console.log(text));

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.

namespace Google\Cloud\Samples\Vision;

use Google\Cloud\Vision\V1\ImageAnnotatorClient;

// $path = 'gs://path/to/your/image.jpg'

function detect_text_gcs($path)
{
    $imageAnnotator = new ImageAnnotatorClient();

    # annotate the image
    $response = $imageAnnotator->textDetection($path);
    $texts = $response->getTextAnnotations();

    printf('%d texts found:' . PHP_EOL, count($texts));
    foreach ($texts as $text) {
        print($text->getDescription() . PHP_EOL);

        # get bounds
        $vertices = $text->getBoundingPoly()->getVertices();
        $bounds = [];
        foreach ($vertices as $vertex) {
            $bounds[] = sprintf('(%d,%d)', $vertex->getX(), $vertex->getY());
        }
        print('Bounds: ' . join(', ', $bounds) . PHP_EOL);
    }

    if ($error = $response->getError()) {
        print('API Error: ' . $error->getMessage() . 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.

def detect_text_uri(uri):
    """Detects text in the file located in Google Cloud Storage or on the Web.
    """
    from google.cloud import vision
    client = vision.ImageAnnotatorClient()
    image = vision.Image()
    image.source.image_uri = uri

    response = client.text_detection(image=image)
    texts = response.text_annotations
    print('Texts:')

    for text in texts:
        print('\n"{}"'.format(text.description))

        vertices = (['({},{})'.format(vertex.x, vertex.y)
                    for vertex in text.bounding_poly.vertices])

        print('bounds: {}'.format(','.join(vertices)))

    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