Detecting text in an image

To detect text in an image (API)

1. If you haven't already, complete the following prerequisites.

   1. Create or update a user with AmazonRekognitionFullAccess and AmazonS3ReadOnlyAccess permissions. For more information, see Step 1: Set up an AWS account and create a User.

   2. Install and configure the AWS Command Line Interface and the AWS SDKs. For more information, see Step 2: Set up the AWS CLI and AWS SDKs.

2. Upload the image that contains text to your S3 bucket.

   For instructions, see Uploading Objects into Amazon S3 in the Amazon Simple Storage Service User Guide.

3. Use the following examples to call the DetectText operation.

   Java

   The following example code displays lines and words that were detected in an image.

   Replace the values of bucket and photo with the names of the S3 bucket and image that you used in step 2.

   //Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
   //PDX-License-Identifier: MIT-0 (For details, see https://github.com/awsdocs/amazon-rekognition-developer-guide/blob/master/LICENSE-SAMPLECODE.)
   
   package aws.example.rekognition.image;
   import com.amazonaws.services.rekognition.AmazonRekognition;
   import com.amazonaws.services.rekognition.AmazonRekognitionClientBuilder;
   import com.amazonaws.services.rekognition.model.AmazonRekognitionException;
   import com.amazonaws.services.rekognition.model.Image;
   import com.amazonaws.services.rekognition.model.S3Object;
   import com.amazonaws.services.rekognition.model.DetectTextRequest;
   import com.amazonaws.services.rekognition.model.DetectTextResult;
   import com.amazonaws.services.rekognition.model.TextDetection;
   import java.util.List;
   
   
   
   public class DetectText {
   
      public static void main(String[] args) throws Exception {
         
     
         String photo = "inputtext.jpg";
         String bucket = "bucket";
   
         AmazonRekognition rekognitionClient = AmazonRekognitionClientBuilder.defaultClient();
   
        
         
         DetectTextRequest request = new DetectTextRequest()
                 .withImage(new Image()
                 .withS3Object(new S3Object()
                 .withName(photo)
                 .withBucket(bucket)));
       
   
         try {
            DetectTextResult result = rekognitionClient.detectText(request);
            List<TextDetection> textDetections = result.getTextDetections();
   
            System.out.println("Detected lines and words for " + photo);
            for (TextDetection text: textDetections) {
         
                    System.out.println("Detected: " + text.getDetectedText());
                    System.out.println("Confidence: " + text.getConfidence().toString());
                    System.out.println("Id : " + text.getId());
                    System.out.println("Parent Id: " + text.getParentId());
                    System.out.println("Type: " + text.getType());
                    System.out.println();
            }
         } catch(AmazonRekognitionException e) {
            e.printStackTrace();
         }
      }
   }

   Java V2

   This code is taken from the AWS Documentation SDK examples GitHub repository. See the full example here.

   /**
   *  To run this code example, ensure that you perform the Prerequisites as stated in the Amazon Rekognition Guide:
   *  https://docs.aws.amazon.com/rekognition/latest/dg/video-analyzing-with-sqs.html
   *
   * Also, ensure that set up your development environment, including your credentials.
   *
   * For information, see this documentation topic:
   *
   * https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
   */
   
   //snippet-start:[rekognition.java2.detect_text.import]
   import software.amazon.awssdk.auth.credentials.ProfileCredentialsProvider;
   import software.amazon.awssdk.core.SdkBytes;
   import software.amazon.awssdk.regions.Region;
   import software.amazon.awssdk.services.rekognition.RekognitionClient;
   import software.amazon.awssdk.services.rekognition.model.DetectTextRequest;
   import software.amazon.awssdk.services.rekognition.model.Image;
   import software.amazon.awssdk.services.rekognition.model.DetectTextResponse;
   import software.amazon.awssdk.services.rekognition.model.TextDetection;
   import software.amazon.awssdk.services.rekognition.model.RekognitionException;
   import java.io.FileInputStream;
   import java.io.FileNotFoundException;
   import java.io.InputStream;
   import java.util.List;
   //snippet-end:[rekognition.java2.detect_text.import]
   
   /**
   * Before running this Java V2 code example, set up your development environment, including your credentials.
   *
   * For more information, see the following documentation topic:
   *
   * https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
   */
   public class DetectTextImage {
   
    public static void main(String[] args) {
   
        final String usage = "\n" +
            "Usage: " +
            "   <sourceImage>\n\n" +
            "Where:\n" +
            "   sourceImage - The path to the image that contains text (for example, C:\\AWS\\pic1.png). \n\n";
   
      if (args.length != 1) {
            System.out.println(usage);
            System.exit(1);
        }
   
        String sourceImage = args[0] ;
        Region region = Region.US_WEST_2;
        RekognitionClient rekClient = RekognitionClient.builder()
            .region(region)
            .credentialsProvider(ProfileCredentialsProvider.create("default"))
            .build();
   
        detectTextLabels(rekClient, sourceImage );
        rekClient.close();
    }
   
    // snippet-start:[rekognition.java2.detect_text.main]
    public static void detectTextLabels(RekognitionClient rekClient, String sourceImage) {
   
        try {
            InputStream sourceStream = new FileInputStream(sourceImage);
            SdkBytes sourceBytes = SdkBytes.fromInputStream(sourceStream);
            Image souImage = Image.builder()
                .bytes(sourceBytes)
                .build();
   
            DetectTextRequest textRequest = DetectTextRequest.builder()
                .image(souImage)
                .build();
   
            DetectTextResponse textResponse = rekClient.detectText(textRequest);
            List<TextDetection> textCollection = textResponse.textDetections();
            System.out.println("Detected lines and words");
            for (TextDetection text: textCollection) {
                System.out.println("Detected: " + text.detectedText());
                System.out.println("Confidence: " + text.confidence().toString());
                System.out.println("Id : " + text.id());
                System.out.println("Parent Id: " + text.parentId());
                System.out.println("Type: " + text.type());
                System.out.println();
            }
   
        } catch (RekognitionException | FileNotFoundException e) {
            System.out.println(e.getMessage());
            System.exit(1);
        }
    }
    // snippet-end:[rekognition.java2.detect_text.main]

   AWS CLI

   This AWS CLI command displays the JSON output for the detect-text CLI operation.

   Replace the values of Bucket and Name with the names of the S3 bucket and image that you used in step 2.

   Replace the value of profile_name with the name of your developer profile.

   aws rekognition detect-text  --image "{"S3Object":{"Bucket":"bucket-name","Name":"image-name"}}" --profile default

   If you are accessing the CLI on a Windows device, use double quotes instead of single quotes and escape the inner double quotes by backslash (i.e. \) to address any parser errors you may encounter. For an example, see the following:

   aws rekognition detect-text  --image "{\"S3Object\":{\"Bucket\":\"bucket-name\",\"Name\":\"image-name\"}}" --profile default

   Python

   The following example code displays lines and words detected in an image.

   Replace the values of bucket and photo with the names of the S3bucket and image that you used in step 2. Replace the value of profile_name in the line that creates the Rekognition session with the name of your developer profile.

   # Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
   # PDX-License-Identifier: MIT-0 (For details, see https://github.com/awsdocs/amazon-rekognition-developer-guide/blob/master/LICENSE-SAMPLECODE.)
   
   import boto3
   
   def detect_text(photo, bucket):
   
       session = boto3.Session(profile_name='default')
       client = session.client('rekognition')
   
       response = client.detect_text(Image={'S3Object': {'Bucket': bucket, 'Name': photo}})
   
       textDetections = response['TextDetections']
       print('Detected text\n----------')
       for text in textDetections:
           print('Detected text:' + text['DetectedText'])
           print('Confidence: ' + "{:.2f}".format(text['Confidence']) + "%")
           print('Id: {}'.format(text['Id']))
           if 'ParentId' in text:
               print('Parent Id: {}'.format(text['ParentId']))
           print('Type:' + text['Type'])
           print()
       return len(textDetections)
   
   def main():
       bucket = 'bucket-name'
       photo = 'photo-name'
       text_count = detect_text(photo, bucket)
       print("Text detected: " + str(text_count))
   
   if __name__ == "__main__":
       main()

   .NET

   The following example code displays lines and words detected in an image.

   Replace the values of bucket and photo with the names of the S3 bucket and image that you used in step 2.

   //Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
   //PDX-License-Identifier: MIT-0 (For details, see https://github.com/awsdocs/amazon-rekognition-developer-guide/blob/master/LICENSE-SAMPLECODE.)
   
   using System;
   using Amazon.Rekognition;
   using Amazon.Rekognition.Model;
   
   public class DetectText
   {
       public static void Example()
       {
           String photo = "input.jpg";
           String bucket = "bucket";
   
           AmazonRekognitionClient rekognitionClient = new AmazonRekognitionClient();
   
           DetectTextRequest detectTextRequest = new DetectTextRequest()
           {
               Image = new Image()
               {
                   S3Object = new S3Object()
                   {
                       Name = photo,
                       Bucket = bucket
                   }
               }
           };
   
           try
           {
               DetectTextResponse detectTextResponse = rekognitionClient.DetectText(detectTextRequest);
               Console.WriteLine("Detected lines and words for " + photo);
               foreach (TextDetection text in detectTextResponse.TextDetections)
               {
                   Console.WriteLine("Detected: " + text.DetectedText);
                   Console.WriteLine("Confidence: " + text.Confidence);
                   Console.WriteLine("Id : " + text.Id);
                   Console.WriteLine("Parent Id: " + text.ParentId);
                   Console.WriteLine("Type: " + text.Type);
               }
           }
           catch (Exception e)
           {
               Console.WriteLine(e.Message);
           }
       }
   }

   Node.JS

   The following example code displays lines and words detected in an image.

   Replace the values of bucket and photo with the names of the S3bucket and image that you used in step 2. Replace the value of region with the region found in your .aws credentials. Replace the value of profile_name in the line that creates the Rekognition session with the name of your developer profile.

   var AWS = require('aws-sdk');
   
   const bucket = 'bucket' // the bucketname without s3://
   const photo  = 'photo' // the name of file
   
   const config = new AWS.Config({
     accessKeyId: process.env.AWS_ACCESS_KEY_ID,
     secretAccessKey: process.env.AWS_SECRET_ACCESS_KEY,
   }) 
   AWS.config.update({region:'region'});
   const client = new AWS.Rekognition();
   const params = {
     Image: {
       S3Object: {
         Bucket: bucket,
         Name: photo
       },
     },
   }
   client.detectText(params, function(err, response) {
     if (err) {
       console.log(err, err.stack); // handle error if an error occurred
     } else {
       console.log(`Detected Text for: ${photo}`)
       console.log(response)
       response.TextDetections.forEach(label => {
         console.log(`Detected Text: ${label.DetectedText}`),
         console.log(`Type: ${label.Type}`),
         console.log(`ID: ${label.Id}`),
         console.log(`Parent ID: ${label.ParentId}`),
         console.log(`Confidence: ${label.Confidence}`),
         console.log(`Polygon: `)
         console.log(label.Geometry.Polygon)
       } 
       )
     } 
   });