Amazon Textract Textract를 사용하여 문서 텍스트 감지

문서에서 텍스트를 감지하려면 (API)

1. 아직 설정하지 않았다면 다음과 같이 하십시오.

   1. 을 사용하여 IAM 사용자를 생성 또는 업데이트합니다.AmazonTextractFullAccess과AmazonS3ReadOnlyAccess권한. 자세한 정보는 1단계: AWS 계정 설정 및 IAM 사용자 만들기을 참조하십시오.

   2. AWS CLI와 AWS SDK를 설치하고 구성합니다. 자세한 정보는 2단계: 설정AWS CLI과AWSSDK을 참조하십시오.

2. S3 버킷에 문서를 업로드합니다.

   지침은 단원을 참조하십시오.Amazon S3 객체 업로드의Amazon Simple Storage Service.

3. 다음 예제를 사용하여 DetectDocumentText 작업을 호출합니다.

   Java

   다음 예제 코드는 검색된 텍스트 줄 주위에 문서와 상자를 표시합니다.

   함수에서 수행main의 값을 바꿉니다.bucket과documentAmazon S3 버킷의 이름 및 2단계에서 사용한 문서 이름이 표시됩니다.

   //Calls DetectDocumentText.
   //Loads document from S3 bucket. Displays the document and bounding boxes around detected lines/words of text.
   package com.amazonaws.samples;
   
   import java.awt.*;
   import java.awt.image.BufferedImage;
   import java.util.List;
   import javax.imageio.ImageIO;
   import javax.swing.*;
   import com.amazonaws.services.s3.AmazonS3;
   import com.amazonaws.services.s3.AmazonS3ClientBuilder;
   import com.amazonaws.services.s3.model.S3ObjectInputStream;
   import com.amazonaws.client.builder.AwsClientBuilder.EndpointConfiguration;
   import com.amazonaws.services.textract.AmazonTextract;
   import com.amazonaws.services.textract.AmazonTextractClientBuilder;
   import com.amazonaws.services.textract.model.Block;
   import com.amazonaws.services.textract.model.BoundingBox;
   import com.amazonaws.services.textract.model.DetectDocumentTextRequest;
   import com.amazonaws.services.textract.model.DetectDocumentTextResult;
   import com.amazonaws.services.textract.model.Document;
   import com.amazonaws.services.textract.model.S3Object;
   import com.amazonaws.services.textract.model.Point;
   import com.amazonaws.services.textract.model.Relationship;
   
   public class DocumentText extends JPanel {
   
       private static final long serialVersionUID = 1L;
   
       BufferedImage image;
       DetectDocumentTextResult result;
   
       public DocumentText(DetectDocumentTextResult documentResult, BufferedImage bufImage) throws Exception {
           super();
           
           result = documentResult; // Results of text detection.
           image = bufImage; // The image containing the document.
   
       }
   
       // Draws the image and text bounding box.
       public void paintComponent(Graphics g) {
   
           int height = image.getHeight(this);
           int width = image.getWidth(this);
   
           Graphics2D g2d = (Graphics2D) g; // Create a Java2D version of g.
   
           // Draw the image.
           g2d.drawImage(image, 0, 0, image.getWidth(this) , image.getHeight(this), this);
   
           // Iterate through blocks and display polygons around lines of detected text.
           List<Block> blocks = result.getBlocks();
           for (Block block : blocks) {
               DisplayBlockInfo(block);
               if ((block.getBlockType()).equals("LINE")) {
                   ShowPolygon(height, width, block.getGeometry().getPolygon(), g2d);
                   /*
                     ShowBoundingBox(height, width, block.getGeometry().getBoundingBox(), g2d);
                    */
               } else { // its a word, so just show vertical lines.
                   ShowPolygonVerticals(height, width, block.getGeometry().getPolygon(), g2d);
               }
           }
       }
   
       // Show bounding box at supplied location.
       private void ShowBoundingBox(int imageHeight, int imageWidth, BoundingBox box, Graphics2D g2d) {
   
           float left = imageWidth * box.getLeft();
           float top = imageHeight * box.getTop();
   
           // Display bounding box.
           g2d.setColor(new Color(0, 212, 0));
           g2d.drawRect(Math.round(left), Math.round(top),
                   Math.round(imageWidth * box.getWidth()), Math.round(imageHeight * box.getHeight()));
   
       }
   
       // Shows polygon at supplied location
       private void ShowPolygon(int imageHeight, int imageWidth, List<Point> points, Graphics2D g2d) {
   
           g2d.setColor(new Color(0, 0, 0));
           Polygon polygon = new Polygon();
   
           // Construct polygon and display
           for (Point point : points) {
               polygon.addPoint((Math.round(point.getX() * imageWidth)),
                       Math.round(point.getY() * imageHeight));
           }
           g2d.drawPolygon(polygon);
       }
   
       // Draws only the vertical lines in the supplied polygon.
       private void ShowPolygonVerticals(int imageHeight, int imageWidth, List<Point> points, Graphics2D g2d) {
   
           g2d.setColor(new Color(0, 212, 0));
           Object[] parry = points.toArray();
           g2d.setStroke(new BasicStroke(2));
   
           g2d.drawLine(Math.round(((Point) parry[0]).getX() * imageWidth),
                   Math.round(((Point) parry[0]).getY() * imageHeight), Math.round(((Point) parry[3]).getX() * imageWidth),
                   Math.round(((Point) parry[3]).getY() * imageHeight));
   
           g2d.setColor(new Color(255, 0, 0));
           g2d.drawLine(Math.round(((Point) parry[1]).getX() * imageWidth),
                   Math.round(((Point) parry[1]).getY() * imageHeight), Math.round(((Point) parry[2]).getX() * imageWidth),
                   Math.round(((Point) parry[2]).getY() * imageHeight));
   
       }
       //Displays information from a block returned by text detection and text analysis
       private void DisplayBlockInfo(Block block) {
           System.out.println("Block Id : " + block.getId());
           if (block.getText()!=null)
               System.out.println("    Detected text: " + block.getText());
           System.out.println("    Type: " + block.getBlockType());
           
           if (block.getBlockType().equals("PAGE") !=true) {
               System.out.println("    Confidence: " + block.getConfidence().toString());
           }
           if(block.getBlockType().equals("CELL"))
           {
               System.out.println("    Cell information:");
               System.out.println("        Column: " + block.getColumnIndex());
               System.out.println("        Row: " + block.getRowIndex());
               System.out.println("        Column span: " + block.getColumnSpan());
               System.out.println("        Row span: " + block.getRowSpan());
   
           }
           
           System.out.println("    Relationships");
           List<Relationship> relationships=block.getRelationships();
           if(relationships!=null) {
               for (Relationship relationship : relationships) {
                   System.out.println("        Type: " + relationship.getType());
                   System.out.println("        IDs: " + relationship.getIds().toString());
               }
           } else {
               System.out.println("        No related Blocks");
           }
   
           System.out.println("    Geometry");
           System.out.println("        Bounding Box: " + block.getGeometry().getBoundingBox().toString());
           System.out.println("        Polygon: " + block.getGeometry().getPolygon().toString());
           
           List<String> entityTypes = block.getEntityTypes();
           
           System.out.println("    Entity Types");
           if(entityTypes!=null) {
               for (String entityType : entityTypes) {
                   System.out.println("        Entity Type: " + entityType);
               }
           } else {
               System.out.println("        No entity type");
           }
           if(block.getPage()!=null)
               System.out.println("    Page: " + block.getPage());            
           System.out.println();
       }
   
       public static void main(String arg[]) throws Exception {
           
           // The S3 bucket and document
           String document = "";
           String bucket = "";
   
           
           AmazonS3 s3client = AmazonS3ClientBuilder.standard()
                   .withEndpointConfiguration( 
                           new EndpointConfiguration("https://s3.amazonaws.com","us-east-1"))
                   .build();
           
                  
           // Get the document from S3
           com.amazonaws.services.s3.model.S3Object s3object = s3client.getObject(bucket, document);
           S3ObjectInputStream inputStream = s3object.getObjectContent();
           BufferedImage image = ImageIO.read(inputStream);
   
           // Call DetectDocumentText
           EndpointConfiguration endpoint = new EndpointConfiguration(
                   "https://textract.us-east-1.amazonaws.com", "us-east-1");
           AmazonTextract client = AmazonTextractClientBuilder.standard()
                   .withEndpointConfiguration(endpoint).build();
   
   
           DetectDocumentTextRequest request = new DetectDocumentTextRequest()
               .withDocument(new Document().withS3Object(new S3Object().withName(document).withBucket(bucket)));
   
           DetectDocumentTextResult result = client.detectDocumentText(request);
           
           // Create frame and panel.
           JFrame frame = new JFrame("RotateImage");
           frame.setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE);
           DocumentText panel = new DocumentText(result, image);
           panel.setPreferredSize(new Dimension(image.getWidth() , image.getHeight() ));
           frame.setContentPane(panel);
           frame.pack();
           frame.setVisible(true);
   
       }
   }
   

   AWS CLI

   이 AWS CLI 명령은 detect-document-text CLI 작업에 대한 JSON 출력을 표시합니다.

   다음 값 바꾸기Bucket과NameAmazon S3 버킷의 이름 및 2단계에서 사용한 문서 이름이 표시됩니다.

   aws textract detect-document-text \
    --document '{"S3Object":{"Bucket":"bucket","Name":"document"}}'

   Python

   다음 예제 코드는 감지된 텍스트 줄 주위에 문서와 상자를 표시합니다.

   함수에서 수행main의 값을 바꿉니다.bucket과documentAmazon S3 버킷의 이름 및 2단계에서 사용한 문서 이름이 표시됩니다.

   #Detects text in a document stored in an S3 bucket. Display polygon box around text and angled text 
   import boto3
   import io
   from io import BytesIO
   import sys
   
   import psutil
   import time
   
   import math
   from PIL import Image, ImageDraw, ImageFont
   
   
   # Displays information about a block returned by text detection and text analysis
   def DisplayBlockInformation(block):
       print('Id: {}'.format(block['Id']))
       if 'Text' in block:
           print('    Detected: ' + block['Text'])
       print('    Type: ' + block['BlockType'])
      
       if 'Confidence' in block:
           print('    Confidence: ' + "{:.2f}".format(block['Confidence']) + "%")
   
       if block['BlockType'] == 'CELL':
           print("    Cell information")
           print("        Column: " + str(block['ColumnIndex']))
           print("        Row: " + str(block['RowIndex']))
           print("        ColumnSpan: " + str(block['ColumnSpan']))
           print("        RowSpan: " + str(block['RowSpan']))    
       
       if 'Relationships' in block:
           print('    Relationships: {}'.format(block['Relationships']))
       print('    Geometry: ')
       print('        Bounding Box: {}'.format(block['Geometry']['BoundingBox']))
       print('        Polygon: {}'.format(block['Geometry']['Polygon']))
       
       if block['BlockType'] == "KEY_VALUE_SET":
           print ('    Entity Type: ' + block['EntityTypes'][0])
       if 'Page' in block:
           print('Page: ' + block['Page'])
       print()
   
   def process_text_detection(bucket, document):
   
       
       #Get the document from S3
       s3_connection = boto3.resource('s3')
                             
       s3_object = s3_connection.Object(bucket,document)
       s3_response = s3_object.get()
   
       stream = io.BytesIO(s3_response['Body'].read())
       image=Image.open(stream)
   
      
       # Detect text in the document
       
       client = boto3.client('textract')
       #process using image bytes                      
       #image_binary = stream.getvalue()
       #response = client.detect_document_text(Document={'Bytes': image_binary})
   
       #process using S3 object
       response = client.detect_document_text(
           Document={'S3Object': {'Bucket': bucket, 'Name': document}})
   
       #Get the text blocks
       blocks=response['Blocks']
       width, height =image.size  
       draw = ImageDraw.Draw(image)  
       print ('Detected Document Text')
      
       # Create image showing bounding box/polygon the detected lines/text
       for block in blocks:
               print('Type: ' + block['BlockType'])
               if block['BlockType'] != 'PAGE':
                   print('Detected: ' + block['Text'])
                   print('Confidence: ' + "{:.2f}".format(block['Confidence']) + "%")
   
               print('Id: {}'.format(block['Id']))
               if 'Relationships' in block:
                   print('Relationships: {}'.format(block['Relationships']))
               print('Bounding Box: {}'.format(block['Geometry']['BoundingBox']))
               print('Polygon: {}'.format(block['Geometry']['Polygon']))
               print()
               draw=ImageDraw.Draw(image)
               # Draw WORD - Green -  start of word, red - end of word
               if block['BlockType'] == "WORD":
                   draw.line([(width * block['Geometry']['Polygon'][0]['X'],
                   height * block['Geometry']['Polygon'][0]['Y']),
                   (width * block['Geometry']['Polygon'][3]['X'],
                   height * block['Geometry']['Polygon'][3]['Y'])],fill='green',
                   width=2)
               
                   draw.line([(width * block['Geometry']['Polygon'][1]['X'],
                   height * block['Geometry']['Polygon'][1]['Y']),
                   (width * block['Geometry']['Polygon'][2]['X'],
                   height * block['Geometry']['Polygon'][2]['Y'])],
                   fill='red',
                   width=2)    
   
                    
               # Draw box around entire LINE  
               if block['BlockType'] == "LINE":
                   points=[]
   
                   for polygon in block['Geometry']['Polygon']:
                       points.append((width * polygon['X'], height * polygon['Y']))
   
                   draw.polygon((points), outline='black')    
     
                   # Uncomment to draw bounding box
                   #box=block['Geometry']['BoundingBox']                    
                   #left = width * box['Left']
                   #top = height * box['Top']           
                   #draw.rectangle([left,top, left + (width * box['Width']), top +(height * box['Height'])],outline='black') 
   
   
       # Display the image
       image.show()
       # display image for 10 seconds
   
       
       return len(blocks)
   
   def main():
   
       bucket = ''
       document = ''
       block_count=process_text_detection(bucket,document)
       print("Blocks detected: " + str(block_count))
       
   if __name__ == "__main__":
       main()
   
   

   Node.js

   다음 Node.js 예제 코드는 검색된 텍스트 줄 주위에 문서와 상자를 표시하여 결과 이미지를 코드를 실행하는 디렉터리로 출력합니다. 그것은 다음을 사용합니다.image-size과images패키지.

   함수에서 수행main의 값을 바꿉니다.bucket과documentAmazon S3 버킷의 이름 및 2단계에서 사용한 문서 이름이 표시됩니다. 값 바꾸기regionConfig계정이 있는 리전의 이름을 사용합니다.

   async function main(){
   
   // Import AWS
   const AWS = require("aws-sdk")
   // Use Image-Size to get 
   const sizeOf = require('image-size');
   // Image tool to draw buffers
   const images = require("images");
   
   // Create a canvas and get the context
   const { createCanvas } = require('canvas')
   const canvas = createCanvas(200, 200)
   const ctx = canvas.getContext('2d')
   
   // Set variables
   const bucket = 'bucket-name' // the s3 bucket name
   const photo  = 'image-name' // the name of file
   const regionConfig = 'region'
   
   // Set region if needed
   AWS.config.update({region:regionConfig});
   
   // Connect to Textract
   const client = new AWS.Textract();
   // Connect to S3 to display image
   const s3 = new AWS.S3();
   
   // Define paramaters
   const params = {
     Document: {
       S3Object: {
         Bucket: bucket,
         Name: photo
       },
     },
   }
   
   // Function to display image
   async function getImage(){
     const imageData =  s3.getObject(
       {
           Bucket: bucket,
           Key: photo
         }
       
     ).promise();
     return imageData;
   }
   
   // get image
   var imageData = await getImage()
   
   // Get the height, width of the image
   const dimensions = sizeOf(imageData.Body)
   const width = dimensions.width
   const height = dimensions.height
   console.log(imageData.Body)
   console.log(width, height)
   
   canvas.width = width;
   canvas.height = height;
   
   try{
     // Call API and log response
     const res = await client.detectDocumentText(params).promise();
     var image = images(imageData.Body).size(width, height)
     //console.log the type of block, text, text type, and confidence
     res.Blocks.forEach(block => {
       console.log(`Block Type: ${block.BlockType}`),
       console.log(`Text: ${block.Text}`)
       console.log(`TextType: ${block.TextType}`)
       console.log(`Confidence: ${block.Confidence}`)
   
       // Draw box around detected text using polygons
       ctx.strokeStyle = 'rgba(0,0,0,0.5)';
       ctx.beginPath();
       block.Geometry.Polygon.forEach(({X, Y}) =>
       ctx.lineTo(width * X - 10, height * Y - 10)
       );
       ctx.closePath();
       ctx.stroke();
       console.log("-----")
     }) 
   
     // render image
     var buffer = canvas.toBuffer("image/png");
     image.draw(images(buffer), 10, 10)
     image.save("output-image.jpg");
     
   } catch (err){
   console.error(err);}
   
   }
   
   main()

4. 예제를 실행합니다. 파이썬과 Java 예제는 문서 이미지를 표시합니다. 검은색 상자는 감지된 텍스트의 각 줄을 둘러싸고 있습니다. 녹색 세로선은 감지된 단어의 시작입니다. 빨간색 세로선은 감지된 단어의 끝입니다. 이AWS CLI예제는 에 대한 JSON 출력만 표시합니다.DetectDocumentText작업을 수행합니다.