画像内の手書き文字を検出する

// detectDocumentText gets the full document text from the Vision API for an image at the given file path.
func detectDocumentText(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
	}
	annotation, err := client.DetectDocumentText(ctx, image, nil)
	if err != nil {
		return err
	}

	if annotation == nil {
		fmt.Fprintln(w, "No text found.")
	} else {
		fmt.Fprintln(w, "Document Text:")
		fmt.Fprintf(w, "%q\n", annotation.Text)

		fmt.Fprintln(w, "Pages:")
		for _, page := range annotation.Pages {
			fmt.Fprintf(w, "\tConfidence: %f, Width: %d, Height: %d\n", page.Confidence, page.Width, page.Height)
			fmt.Fprintln(w, "\tBlocks:")
			for _, block := range page.Blocks {
				fmt.Fprintf(w, "\t\tConfidence: %f, Block type: %v\n", block.Confidence, block.BlockType)
				fmt.Fprintln(w, "\t\tParagraphs:")
				for _, paragraph := range block.Paragraphs {
					fmt.Fprintf(w, "\t\t\tConfidence: %f", paragraph.Confidence)
					fmt.Fprintln(w, "\t\t\tWords:")
					for _, word := range paragraph.Words {
						symbols := make([]string, len(word.Symbols))
						for i, s := range word.Symbols {
							symbols[i] = s.Text
						}
						wordText := strings.Join(symbols, "")
						fmt.Fprintf(w, "\t\t\t\tConfidence: %f, Symbols: %s\n", word.Confidence, wordText)
					}
				}
			}
		}
	}

	return nil
}

public static void detectDocumentText(String filePath) 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.DOCUMENT_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();
    client.close();

    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
      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();
                System.out.format(
                    "Symbol text: %s (confidence: %f)%n",
                    symbol.getText(), symbol.getConfidence());
              }
              System.out.format(
                  "Word text: %s (confidence: %f)%n%n", wordText, word.getConfidence());
              paraText = String.format("%s %s", paraText, wordText);
            }
            // Output Example using Paragraph:
            System.out.println("%nParagraph: %n" + paraText);
            System.out.format("Paragraph Confidence: %f%n", para.getConfidence());
            blockText = blockText + paraText;
          }
          pageText = pageText + blockText;
        }
      }
      System.out.println("%nComplete annotation:");
      System.out.println(annotation.getText());
    }
  }
}

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

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

/**
 * TODO(developer): Uncomment the following line before running the sample.
 */
// const fileName = 'Local image file, e.g. /path/to/image.png';

// Read a local image as a text document
const [result] = await client.documentTextDetection(fileName);
const fullTextAnnotation = result.fullTextAnnotation;
console.log(`Full text: ${fullTextAnnotation.text}`);
fullTextAnnotation.pages.forEach(page => {
  page.blocks.forEach(block => {
    console.log(`Block confidence: ${block.confidence}`);
    block.paragraphs.forEach(paragraph => {
      console.log(`Paragraph confidence: ${paragraph.confidence}`);
      paragraph.words.forEach(word => {
        const wordText = word.symbols.map(s => s.text).join('');
        console.log(`Word text: ${wordText}`);
        console.log(`Word confidence: ${word.confidence}`);
        word.symbols.forEach(symbol => {
          console.log(`Symbol text: ${symbol.text}`);
          console.log(`Symbol confidence: ${symbol.confidence}`);
        });
      });
    });
  });
});

def detect_document(path):
    """Detects document features in an image."""
    from google.cloud import vision

    client = vision.ImageAnnotatorClient()

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

    image = vision.Image(content=content)

    response = client.document_text_detection(image=image)

    for page in response.full_text_annotation.pages:
        for block in page.blocks:
            print(f"\nBlock confidence: {block.confidence}\n")

            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)
        )

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

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

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

	if annotation == nil {
		fmt.Fprintln(w, "No text found.")
	} else {
		fmt.Fprintln(w, "Document Text:")
		fmt.Fprintf(w, "%q\n", annotation.Text)

		fmt.Fprintln(w, "Pages:")
		for _, page := range annotation.Pages {
			fmt.Fprintf(w, "\tConfidence: %f, Width: %d, Height: %d\n", page.Confidence, page.Width, page.Height)
			fmt.Fprintln(w, "\tBlocks:")
			for _, block := range page.Blocks {
				fmt.Fprintf(w, "\t\tConfidence: %f, Block type: %v\n", block.Confidence, block.BlockType)
				fmt.Fprintln(w, "\t\tParagraphs:")
				for _, paragraph := range block.Paragraphs {
					fmt.Fprintf(w, "\t\t\tConfidence: %f", paragraph.Confidence)
					fmt.Fprintln(w, "\t\t\tWords:")
					for _, word := range paragraph.Words {
						symbols := make([]string, len(word.Symbols))
						for i, s := range word.Symbols {
							symbols[i] = s.Text
						}
						wordText := strings.Join(symbols, "")
						fmt.Fprintf(w, "\t\t\t\tConfidence: %f, Symbols: %s\n", word.Confidence, wordText)
					}
				}
			}
		}
	}

	return nil
}

public static void detectDocumentTextGcs(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(Type.DOCUMENT_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();
    client.close();

    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
      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();
                System.out.format(
                    "Symbol text: %s (confidence: %f)%n",
                    symbol.getText(), symbol.getConfidence());
              }
              System.out.format(
                  "Word text: %s (confidence: %f)%n%n", wordText, word.getConfidence());
              paraText = String.format("%s %s", paraText, wordText);
            }
            // Output Example using Paragraph:
            System.out.println("%nParagraph: %n" + paraText);
            System.out.format("Paragraph Confidence: %f%n", para.getConfidence());
            blockText = blockText + paraText;
          }
          pageText = pageText + blockText;
        }
      }
      System.out.println("%nComplete annotation:");
      System.out.println(annotation.getText());
    }
  }
}

// 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';

// Read a remote image as a text document
const [result] = await client.documentTextDetection(
  `gs://${bucketName}/${fileName}`
);
const fullTextAnnotation = result.fullTextAnnotation;
console.log(fullTextAnnotation.text);

def detect_document_uri(uri):
    """Detects document features 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.document_text_detection(image=image)

    for page in response.full_text_annotation.pages:
        for block in page.blocks:
            print(f"\nBlock confidence: {block.confidence}\n")

            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)
        )

import (
	"context"
	"fmt"

	vision "cloud.google.com/go/vision/apiv1"
	"google.golang.org/api/option"
)

// setEndpoint changes your endpoint.
func setEndpoint(endpoint string) error {
	// endpoint := "eu-vision.googleapis.com:443"

	ctx := context.Background()
	client, err := vision.NewImageAnnotatorClient(ctx, option.WithEndpoint(endpoint))
	if err != nil {
		return fmt.Errorf("NewImageAnnotatorClient: %w", err)
	}
	defer client.Close()

	return nil
}

ImageAnnotatorSettings settings =
    ImageAnnotatorSettings.newBuilder().setEndpoint("eu-vision.googleapis.com:443").build();

// 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.
ImageAnnotatorClient client = ImageAnnotatorClient.create(settings);

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

async function setEndpoint() {
  // Specifies the location of the api endpoint
  const clientOptions = {apiEndpoint: 'eu-vision.googleapis.com'};

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

  // Performs text detection on the image file
  const [result] = await client.textDetection('./resources/wakeupcat.jpg');
  const labels = result.textAnnotations;
  console.log('Text:');
  labels.forEach(label => console.log(label.description));
}
setEndpoint();

from google.cloud import vision

client_options = {"api_endpoint": "eu-vision.googleapis.com"}

client = vision.ImageAnnotatorClient(client_options=client_options)