Azure AI services - Read Text in Images

 Azure AI services - Read Text in Images: 

Source :
https://github.com/MicrosoftLearning/AI-102-AIEngineer
1. Azure AI services | Azure AI services multi-service account

C# Code:

using Microsoft.Azure.CognitiveServices.Vision.ComputerVision;

using Microsoft.Azure.CognitiveServices.Vision.ComputerVision.Models;

using System;

using System.IO;

using System.Threading;

using System.Threading.Tasks;

// dotnet add package Microsoft.Azure.CognitiveServices.Vision.ComputerVision --version 6.0.0

namespace read_text

{

    class Program

    {

        private static ComputerVisionClient cvClient;

        static async Task Main(string[] args)

        {

            try

            {

                // Get config settings from AppSettings

                // IConfigurationBuilder builder =                 new ConfigurationBuilder().AddJsonFile("appsettings.json");

                // IConfigurationRoot configuration = builder.Build();

                string cogSvcEndpoint = "https://multiserviceaccount1.cognitiveservices.azure.com/";

               // configuration["CognitiveServicesEndpoint"];

                string cogSvcKey = "AjShjnYv3s56Ne4keUlZIqXJ799BAACYeBjFXJ3w3AAAEACOGAIif";                 // configuration["CognitiveServiceKey"];

                ApiKeyServiceClientCredentials credentials =                 new ApiKeyServiceClientCredentials(cogSvcKey);

                cvClient = new ComputerVisionClient(credentials)

                {

                    Endpoint = cogSvcEndpoint

                };

                // Menu for text reading functions

                Console.WriteLine("1: Use Read API for image\n2: Use Read API for document\n3:                 Read handwriting\nAny other key to quit");

                Console.WriteLine("Enter a number:");

                string command = Console.ReadLine();

                string imageFile;

                switch (command)

                {

                    case "1":

                        imageFile = "images/Lincoln.jpg";

                        await GetTextRead(imageFile);

                        break;

                    case "2":

                        imageFile = "images/Rome.pdf";

                        await GetTextRead(imageFile);

                        break;

                    case "3":

                        imageFile = "images/Note.jpg";

                        await GetTextRead(imageFile);

                        break;

                    default:

                        break;

                }

            }

            catch (Exception ex)

            {

                Console.WriteLine(ex.Message);

            }

        }

        static async Task GetTextRead(string imageFile)

        {

            Console.WriteLine($"Reading text in {imageFile}\n");

            // Use Read API to read text in image

            using (var imageData = File.OpenRead(imageFile))

            {

                var readOp = await cvClient.ReadInStreamAsync(imageData);

                // Get the async operation ID so we can check for the results

                string operationLocation = readOp.OperationLocation;

                string operationId = operationLocation.Substring(operationLocation.Length - 36);

                // Wait for the asynchronous operation to complete

                ReadOperationResult results;

                do

                {

                    Thread.Sleep(1000);

                    results = await cvClient.GetReadResultAsync(Guid.Parse(operationId));

                }

                while ((results.Status == OperationStatusCodes.Running ||

                        results.Status == OperationStatusCodes.NotStarted));

                // If the operation was successfully, process the text line by line

                if (results.Status == OperationStatusCodes.Succeeded)

                {

                    var textUrlFileResults = results.AnalyzeResult.ReadResults;

                    foreach (ReadResult page in textUrlFileResults)

                    {

                        foreach (Line line in page.Lines)

                        {

                            Console.WriteLine(line.Text);

                            // Uncomment the following line if you'd like to see the bounding box

                            //Console.WriteLine(line.BoundingBox);

                        }

                    }

                }

            }

        }

    }

}

Python Code:

# pip install python-dotenv

# pip install pillow

# pip install matplotlib

# pip install azure-cognitiveservices-vision-computervision==0.7.0

from dotenv import load_dotenv

import os

import time

from PIL import Image, ImageDraw

from matplotlib import pyplot as plt

# Import namespaces

from azure.cognitiveservices.vision.computervision import ComputerVisionClient

from azure.cognitiveservices.vision.computervision.models import OperationStatusCodes

from msrest.authentication import CognitiveServicesCredentials

def main():

    global cv_client

    try:

        # Get Configuration Settings

        load_dotenv()

        cog_endpoint = "https://multiserviceaccount1.cognitiveservices.azure.com/"         #os.getenv('COG_SERVICE_ENDPOINT')

        cog_key = "AjShjnYv3s56Ne4keUlZBAACYeBjFXJ3w3AAAEACOGAIif"         # os.getenv('COG_SERVICE_KEY')

        # Authenticate Azure AI Vision client

        credential = CognitiveServicesCredentials(cog_key)

        cv_client = ComputerVisionClient(cog_endpoint, credential)

        # Menu for text reading functions

        print('1: Use Read API for image\n2: Use Read API for document\n3: Read         handwriting\nAny other key to quit')

        command = input('Enter a number:')

        if command == '1':

            image_file = os.path.join('images','Lincoln.jpg')

            GetTextRead(image_file)

        elif command =='2':

            image_file = os.path.join('images','Rome.pdf')

            GetTextRead(image_file)

        elif command =='3':

            image_file = os.path.join('images','Note.jpg')

            GetTextRead(image_file)

    except Exception as ex:

        print(ex)

def GetTextRead(image_file):

    print('Reading text in {}\n'.format(image_file))

   

    # Use Read API to read text in image

    with open(image_file, mode="rb") as image_data:

        read_op = cv_client.read_in_stream(image_data, raw=True)

    # Get the async operation ID so we can check for the results

    operation_location = read_op.headers["Operation-Location"]

    operation_id = operation_location.split("/")[-1]

    # Wait for the asynchronous operation to complete

    while True:

        read_results = cv_client.get_read_result(operation_id)

        if read_results.status not in [OperationStatusCodes.running,         OperationStatusCodes.not_started]:

            break

        time.sleep(1)

    # If the operation was successfully, process the text line by line

    if read_results.status == OperationStatusCodes.succeeded:

        for page in read_results.analyze_result.read_results:

            for line in page.lines:

                print(line.text)

                # Uncomment the following line if you'd like to see the bounding box

                # print(line.bounding_box)

if __name__ == "__main__":

    main()

Input:

Output:

Input:
Save as PDF file.

Output:

Input:

Output: