Detect handwritten text in a local file (beta)

Perform handwritten text detection on a local file (for beta launch).

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.

/**
 * Performs handwritten text detection on a local image file.
 *
 * @param filePath The path to the local file to detect handwritten text on.
 * @param out A {@link PrintStream} to write the results to.
 * @throws Exception on errors while closing the client.
 * @throws IOException on Input/Output errors.
 */
public static void detectHandwrittenOcr(String filePath, PrintStream out) throws Exception {
  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.DOCUMENT_TEXT_DETECTION).build();
  // Set the Language Hint codes for handwritten OCR
  ImageContext imageContext =
      ImageContext.newBuilder().addLanguageHints("en-t-i0-handwrit").build();

  AnnotateImageRequest request =
      AnnotateImageRequest.newBuilder()
          .addFeatures(feat)
          .setImage(img)
          .setImageContext(imageContext)
          .build();
  requests.add(request);

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

    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
      TextAnnotation annotation = res.getFullTextAnnotation();
      for (Page page : annotation.getPagesList()) {
        String pageText = "";
        for (Block block : page.getBlocksList()) {
          String blockText = "";
          for (Paragraph para : block.getParagraphsList()) {
            String paraText = "";
            for (Word word : para.getWordsList()) {
              String wordText = "";
              for (Symbol symbol : word.getSymbolsList()) {
                wordText = wordText + symbol.getText();
                out.format(
                    "Symbol text: %s (confidence: %f)\n",
                    symbol.getText(), symbol.getConfidence());
              }
              out.format("Word text: %s (confidence: %f)\n\n", wordText, word.getConfidence());
              paraText = String.format("%s %s", paraText, wordText);
            }
            // Output Example using Paragraph:
            out.println("\nParagraph: \n" + paraText);
            out.format("Paragraph Confidence: %f\n", para.getConfidence());
            blockText = blockText + paraText;
          }
          pageText = pageText + blockText;
        }
      }
      out.println("\nComplete annotation:");
      out.println(annotation.getText());
    }
  }
}

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').v1p3beta1;
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),
  },
  feature: {
    languageHints: ['en-t-i0-handwrit'],
  },
};

const [result] = await client.documentTextDetection(request);
const fullTextAnnotation = result.fullTextAnnotation;
console.log(`Full text: ${fullTextAnnotation.text}`);

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_handwritten_ocr(path):
    """Detects handwritten characters in a local image.

    Args:
    path: The path to the local file.
    """
    from google.cloud import vision_v1p3beta1 as vision
    client = vision.ImageAnnotatorClient()

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

    image = vision.Image(content=content)

    # Language hint codes for handwritten OCR:
    # en-t-i0-handwrit, mul-Latn-t-i0-handwrit
    # Note: Use only one language hint code per request for handwritten OCR.
    image_context = vision.ImageContext(
        language_hints=['en-t-i0-handwrit'])

    response = client.document_text_detection(image=image,
                                              image_context=image_context)

    print('Full Text: {}'.format(response.full_text_annotation.text))
    for page in response.full_text_annotation.pages:
        for block in page.blocks:
            print('\nBlock confidence: {}\n'.format(block.confidence))

            for paragraph in block.paragraphs:
                print('Paragraph confidence: {}'.format(
                    paragraph.confidence))

                for word in paragraph.words:
                    word_text = ''.join([
                        symbol.text for symbol in word.symbols
                    ])
                    print('Word text: {} (confidence: {})'.format(
                        word_text, word.confidence))

                    for symbol in word.symbols:
                        print('\tSymbol: {} (confidence: {})'.format(
                            symbol.text, symbol.confidence))

    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.