Detect handwriting in images

// detectDocumentText gets the full document text from the Vision API for an image at the given file path.
funcdetectDocumentText(wio.Writer,filestring)error{
ctx:=context.Background()
client,err:=vision.NewImageAnnotatorClient(ctx)
iferr!=nil{
returnerr
}
f,err:=os.Open(file)
iferr!=nil{
returnerr
}
deferf.Close()
image,err:=vision.NewImageFromReader(f)
iferr!=nil{
returnerr
}
annotation,err:=client.DetectDocumentText(ctx,image,nil)
iferr!=nil{
returnerr
}
ifannotation==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:=rangeannotation.Pages{
fmt.Fprintf(w,"\tConfidence: %f, Width: %d, Height: %d\n",page.Confidence,page.Width,page.Height)
fmt.Fprintln(w,"\tBlocks:")
for_,block:=rangepage.Blocks{
fmt.Fprintf(w,"\t\tConfidence: %f, Block type: %v\n",block.Confidence,block.BlockType)
fmt.Fprintln(w,"\t\tParagraphs:")
for_,paragraph:=rangeblock.Paragraphs{
fmt.Fprintf(w,"\t\t\tConfidence: %f",paragraph.Confidence)
fmt.Fprintln(w,"\t\t\tWords:")
for_,word:=rangeparagraph.Words{
symbols:=make([]string,len(word.Symbols))
fori,s:=rangeword.Symbols{
symbols[i]=s.Text
}
wordText:=strings.Join(symbols,"")
fmt.Fprintf(w,"\t\t\t\tConfidence: %f, Symbols: %s\n",word.Confidence,wordText)
}
}
}
}
}
returnnil
}

publicstaticvoiddetectDocumentText(StringfilePath)throwsIOException{
List<AnnotateImageRequest>requests=newArrayList<>();
ByteStringimgBytes=ByteString.readFrom(newFileInputStream(filePath));
Imageimg=Image.newBuilder().setContent(imgBytes).build();
Featurefeat=Feature.newBuilder().setType(Type.DOCUMENT_TEXT_DETECTION).build();
AnnotateImageRequestrequest=
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(ImageAnnotatorClientclient=ImageAnnotatorClient.create()){
BatchAnnotateImagesResponseresponse=client.batchAnnotateImages(requests)<;
ListAnnotateIma>geResponseresponses=response.getResponsesList();
client.close();
for(AnnotateImageResponseres: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
TextAnnotationannotation=res.getFullTextAnnotation();
for(Pagepage:annotation.getPagesList()){
StringpageText="";
for(Blockblock:page.getBlocksList()){
StringblockText="";
for(Paragraphpara:block.getParagraphsList()){
StringparaText="";
for(Wordword:para.getWordsList()){
StringwordText="";
for(Symbolsymbol: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
constvision=require('@google-cloud/vision');
// Creates a client
constclient=newvision.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]=awaitclient.documentTextDetection(fileName);
constfullTextAnnotation=result.fullTextAnnotation;
console.log(`Full text: ${fullTextAnnotation.text}`);
fullTextAnnotation.page>s.forEach(page={
page.blocks>.forEach(block={
console.log(`Block confidence: ${block.confidence}`);
block.paragraphs.for>Each(paragraph={
console.log(`Paragraph confidence: ${paragraph.confidence}`);
paragraph.word>s.forEach(word={
constwordText=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}`);
});
  });
});
});
});

defdetect_document(path):
"""Detects document features in an image."""
 fromgoogle.cloudimport 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.
funcdetectDocumentTextURI(wio.Writer,filestring)error{
ctx:=context.Background()
client,err:=vision.NewImageAnnotatorClient(ctx)
iferr!=nil{
returnerr
}
image:=vision.NewImageFromURI(file)
annotation,err:=client.DetectDocumentText(ctx,image,nil)
iferr!=nil{
returnerr
}
ifannotation==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:=rangeannotation.Pages{
fmt.Fprintf(w,"\tConfidence: %f, Width: %d, Height: %d\n",page.Confidence,page.Width,page.Height)
fmt.Fprintln(w,"\tBlocks:")
for_,block:=rangepage.Blocks{
fmt.Fprintf(w,"\t\tConfidence: %f, Block type: %v\n",block.Confidence,block.BlockType)
fmt.Fprintln(w,"\t\tParagraphs:")
for_,paragraph:=rangeblock.Paragraphs{
fmt.Fprintf(w,"\t\t\tConfidence: %f",paragraph.Confidence)
fmt.Fprintln(w,"\t\t\tWords:")
for_,word:=rangeparagraph.Words{
symbols:=make([]string,len(word.Symbols))
fori,s:=rangeword.Symbols{
symbols[i]=s.Text
}
wordText:=strings.Join(symbols,"")
fmt.Fprintf(w,"\t\t\t\tConfidence: %f, Symbols: %s\n",word.Confidence,wordText)
}
}
}
}
}
returnnil
}

publicstaticvoiddetectDocumentTextGcs(StringgcsPath)throwsIOException{
List<AnnotateImageRequest>requests=newArrayList<>();
ImageSourceimgSource=ImageSource.newBuilder().setGcsImageUri(gcsPath).build();
Imageimg=Image.newBuilder().setSource(imgSource).build();
Featurefeat=Feature.newBuilder().setType(Type.DOCUMENT_TEXT_DETECTION).build();
AnnotateImageRequestrequest=
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(ImageAnnotatorClientclient=ImageAnnotatorClient.create()){
BatchAnnotateImagesResponseresponse=client.batchAnnotateImages(requests)<;
ListAnnotateIma>geResponseresponses=response.getResponsesList();
client.close();
for(AnnotateImageResponseres: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
TextAnnotationannotation=res.getFullTextAnnotation();
for(Pagepage:annotation.getPagesList()){
StringpageText="";
for(Blockblock:page.getBlocksList()){
StringblockText="";
for(Paragraphpara:block.getParagraphsList()){
StringparaText="";
for(Wordword:para.getWordsList()){
StringwordText="";
for(Symbolsymbol: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
constvision=require('@google-cloud/vision');
// Creates a client
constclient=newvision.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]=awaitclient.documentTextDetection(
`gs://${bucketName}/${fileName}`
);
constfullTextAnnotation=result.fullTextAnnotation;
console.log(fullTextAnnotation.text);

defdetect_document_uri(uri):
"""Detects document features in the file located in Google Cloud
 Storage."""
 fromgoogle.cloudimport 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.
funcsetEndpoint(endpointstring)error{
// endpoint := "eu-vision.googleapis.com:443"
ctx:=context.Background()
client,err:=vision.NewImageAnnotatorClient(ctx,option.WithEndpoint(endpoint))
iferr!=nil{
returnfmt.Errorf("NewImageAnnotatorClient: %w",err)
}
deferclient.Close()
returnnil
}

ImageAnnotatorSettingssettings=
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.
ImageAnnotatorClientclient=ImageAnnotatorClient.create(settings);

// Imports the Google Cloud client library
constvision=require('@google-cloud/vision');
asyncfunctionsetEndpoint(){
// Specifies the location of the api endpoint
constclientOptions={apiEndpoint:'eu-vision.googleapis.com'};
// Creates a client
constclient=newvision.ImageAnnotatorClient(clientOptions);
// Performs text detection on the image file
const[result]=awaitclient.textDetection('./resources/wakeupcat.jpg');
constlabels=result.textAnnotations;
console.log('Text:>');
labels.forEach(label=console.log(label.description));
}
setEndpoint();

fromgoogle.cloudimport vision
client_options = {"api_endpoint": "eu-vision.googleapis.com";}
client = vision. ImageAnnotatorClient(client_options=client_options)