Add samples for OCR Azure & AWS

Author: Sowmiya Loganathan

OCR/.NET/Perform-OCR-AWS-Textract/Perform-OCR-AWS-Textract.sln

@@ -0,0 +1,25 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio Version 17
+VisualStudioVersion = 17.3.32819.101
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Perform-OCR-AWS-Textract", "Perform-OCR-AWS-Textract\Perform-OCR-AWS-Textract.csproj", "{5E130BCC-E31C-4B60-AE1C-DD02937C32DA}"
+EndProject
+Global
+GlobalSection(SolutionConfigurationPlatforms) = preSolution
+Debug|Any CPU = Debug|Any CPU
+Release|Any CPU = Release|Any CPU
+EndGlobalSection
+GlobalSection(ProjectConfigurationPlatforms) = postSolution
+{5E130BCC-E31C-4B60-AE1C-DD02937C32DA}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+{5E130BCC-E31C-4B60-AE1C-DD02937C32DA}.Debug|Any CPU.Build.0 = Debug|Any CPU
+{5E130BCC-E31C-4B60-AE1C-DD02937C32DA}.Release|Any CPU.ActiveCfg = Release|Any CPU
+{5E130BCC-E31C-4B60-AE1C-DD02937C32DA}.Release|Any CPU.Build.0 = Release|Any CPU
+EndGlobalSection
+GlobalSection(SolutionProperties) = preSolution
+HideSolutionNode = FALSE
+EndGlobalSection
+GlobalSection(ExtensibilityGlobals) = postSolution
+SolutionGuid = {C33A5020-F48D-4553-922B-094C1D344A93}
+EndGlobalSection
+EndGlobal

OCR/.NET/Perform-OCR-AWS-Textract/Perform-OCR-AWS-Textract/AWSExternalOcrEngine.cs

@@ -0,0 +1,93 @@
+using System;
+using System.IO;
+using System.Threading.Tasks;
+using Syncfusion.OCRProcessor;
+using Syncfusion.Pdf.Graphics;
+using Syncfusion.Drawing;
+using Amazon;
+using Amazon.Textract;
+using Amazon.Textract.Model;
+
+
+namespace OCR.Test
+{
+ class AWSExternalOcrEngine : IOcrEngine
+ {
+ private string awsAccessKeyId = "AccessKeyID";
+ private string awsSecretAccessKey = "SecretAccessKey";
+ private float imageHeight;
+ private float imageWidth;
+ public OCRLayoutResult PerformOCR(Stream stream)
+ {
+ AmazonTextractClient clientText = Authenticate();
+ DetectDocumentTextResponse textResponse = GetAWSTextractResult(clientText, stream).Result; 
+ OCRLayoutResult oCRLayoutResult = ConvertAWSTextractResultToOcrLayoutResult(textResponse);
+ return oCRLayoutResult;
+ }
+
+ public AmazonTextractClient Authenticate()
+ {
+ AmazonTextractClient client = new AmazonTextractClient(awsAccessKeyId, awsSecretAccessKey, RegionEndpoint.USEast1);
+ return client;
+ }
+ 
+ public async Task<DetectDocumentTextResponse> GetAWSTextractResult(AmazonTextractClient client, Stream stream)
+ {
+ stream.Position = 0;
+ MemoryStream memoryStream = new MemoryStream();
+ stream.CopyTo(memoryStream);
+ PdfBitmap bitmap = new PdfBitmap(memoryStream);
+ imageHeight = bitmap.Height;
+ imageWidth = bitmap.Width;
+
+ DetectDocumentTextResponse response = await client.DetectDocumentTextAsync(new DetectDocumentTextRequest
+ {
+ Document = new Document
+ {
+ Bytes = memoryStream
+ }
+ });
+ return response;
+ }
+ 
+ public OCRLayoutResult ConvertAWSTextractResultToOcrLayoutResult(DetectDocumentTextResponse textResponse)
+ {
+ OCRLayoutResult layoutResult = new OCRLayoutResult();
+ Syncfusion.OCRProcessor.Page ocrPage = new Page();
+ Syncfusion.OCRProcessor.Line ocrLine;
+ Syncfusion.OCRProcessor.Word ocrWord;
+ layoutResult.ImageHeight = imageHeight;
+ layoutResult.ImageWidth = imageWidth;
+ foreach (var page in textResponse.Blocks)
+ { 
+ ocrLine = new Line();
+ if (page.BlockType == "WORD")
+ {
+ ocrWord = new Word();
+ ocrWord.Text = page.Text;
+ 
+ float left = page.Geometry.BoundingBox.Left;
+ float top = page.Geometry.BoundingBox.Top;
+ float width = page.Geometry.BoundingBox.Width;
+ float height = page.Geometry.BoundingBox.Height;
+ Rectangle rect = GetBoundingBox(left,top,width,height);
+ ocrWord.Rectangle = rect;
+ ocrLine.Add(ocrWord);
+ ocrPage.Add(ocrLine);
+ } 
+ }
+ layoutResult.Add(ocrPage);
+ return layoutResult;
+ }
+ public Rectangle GetBoundingBox(float left, float top, float width, float height)
+ {
+ int x = Convert.ToInt32(left * imageWidth);
+ int y = Convert.ToInt32(top * imageHeight);
+ int bboxWidth = Convert.ToInt32((width * imageWidth) + x);
+ int bboxHeight = Convert.ToInt32((height * imageHeight) + y);
+ Rectangle rect = new Rectangle(x,y, bboxWidth, bboxHeight);
+ return rect;
+ }
+ }
+}
+ 

OCR/.NET/Perform-OCR-AWS-Textract/Perform-OCR-AWS-Textract/OCR_Images/.NET-sample-creation-step1.png

@@ -0,0 +1,16 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+ <PropertyGroup>
+ <OutputType>Exe</OutputType>
+ <TargetFramework>net6.0</TargetFramework>
+ <RootNamespace>Perform_OCR_AWS_Textract</RootNamespace>
+ <ImplicitUsings>enable</ImplicitUsings>
+ <Nullable>enable</Nullable>
+ </PropertyGroup>
+
+ <ItemGroup>
+ <PackageReference Include="AWSSDK.Textract" Version="3.7.100.6" />
+ <PackageReference Include="Syncfusion.PDF.OCR.NET" Version="20.3.0.60" />
+ </ItemGroup>
+
+</Project>

OCR/.NET/Perform-OCR-AWS-Textract/Perform-OCR-AWS-Textract/OCR_Images/.NET-sample-creation-step2.png

@@ -0,0 +1,43 @@
+// See https://aka.ms/new-console-template for more information
+
+using Syncfusion.OCRProcessor;
+using Syncfusion.Pdf.Parsing;
+
+namespace OCR.Test
+{
+ class Program
+ {
+ static void Main(string[] args)
+ {
+ //Initialize the OCR processor.
+ using (OCRProcessor processor = new OCRProcessor())
+ {
+ //Load an existing PDF document.
+ FileStream stream = new FileStream("../../../Region.pdf", FileMode.Open);
+ PdfLoadedDocument lDoc = new PdfLoadedDocument(stream);
+
+ //Set the OCR language.
+ processor.Settings.Language = Languages.English;
+
+ //Initialize the AWS Textract external OCR engine.
+ IOcrEngine azureOcrEngine = new AWSExternalOcrEngine();
+ processor.ExternalEngine = azureOcrEngine;
+
+ //Perform OCR with input document.
+ string text = processor.PerformOCR(lDoc);
+
+ //Create file stream.
+ FileStream fileStream = new FileStream("../../../OCR.pdf", FileMode.CreateNew);
+
+ //Save the document into stream.
+ lDoc.Save(fileStream);
+
+ //Close the document.
+ lDoc.Close();
+ stream.Dispose();
+ fileStream.Dispose();
+ }
+ }
+ }
+}
+